diabetes case study answer key

Ohio State nav bar

The Ohio State University

• BuckeyeLink
• Find People
• Search Ohio State

Review Questions

QUESTION ONE

When Mr. Johnson was first diagnosed with Type 2 Diabetes Mellitus what classic symptoms should he have been told he would exhibit?  Select all that apply.

a. Visual changes, recurrent infections, and pruritis

b. Nausea, hypotension, and mental confusion

c. Polyuria, polyphagia, and polydipsia

d. Sweet fruity breath, Kussmaul breathing, and vomiting

QUESTION TWO

What risk factors increase the chances of developing Type II diabetes?

a. Smoking, race, diet, family history, and height

b. Family history, hygiene, smoking, increased age, and hypertension

c. Hygiene, lifestyle, genetics, smoking, and obesity

d. Family history, increased age, obesity, hypertension, and smoking

QUESTION THREE

What does insulin resistance mean?

a. The pancreas is underactive and can keep up with the production of insulin needed to overcome the high amount of glucose in the blood.

b. Glucose is raised above normal levels.

c. The inability for cells to absorb and use blood sugar for energy.

d. The pancreas is overactive and cannot keep up with the insulin demands due to an abundance of glucose in the blood.

QUESTION FOUR

What evidence-based suggestions can you provide your patients to prevent or manage Type II diabetes?

a. Eating whatever you desire as long as you work out.

b. Eating a healthy diet and exercising.

c. Eating a healthy diet only.

d. Staying inside all day under the blankets.

QUESTION FIVE

What are the long term effects of untreated Type 2 Diabetes Mellitus? [Select all that apply]

a. Blindness

b. Kidney Disease

c. Tinnitus

d. Peripheral Neuropathy

Answer:  A & C

Visual changes, recurrent infections, and pruritis are all complications of Type 2 Diabetes Mellitus. Although polyuria, polyphagia, and polydipsia are known as the classic symptoms for Type 1 Diabetes Mellitus, they are also present in Type 2 Diabetes Mellitus. Nausea, hypotension and mental confusion are signs of hypoglycemia.  Sweet fruity breath, Kussmaul respirations, and vomiting are signs of diabetic ketoacidosis.

Reference: McCance, K. L., Huether, S. E., Brashers, V. L., & Rote, N. S. (2019). Pathophysiology: the biologic basis for disease in adults and children  (8th ed.). St. Louis, MO: Elsevier.

Answer: D, risk factors for type II diabetes include obesity, diet, lack of exercise, race, increased age, and family history.

Maintaining a healthy weight and engaging in physical activity helps to control weight, uses glucose for energy and allows cells to be more sensitive to insulin. Having a family history increases the risk of type II diabetes.  For unclear reasons, African Americans, Hispanics, American Indians, and Asian Americans have an increased risk of developing type II diabetes. An increase in age is also a risk factor due to weight gain and the tendency to be less active.  A diet high in red meats, processed carbohydrates, sugar, and saturated and trans fat increases the risk of type II diabetes. Options A, B, and C are incorrect. Height and hygiene are not contributing factors.

Type 2 diabetes. (2019, January 9). Retrieved from https://www.mayoclinic.org/diseases-conditions/type-2-diabetes/symptoms-causes/syc-20351193 .

Answer: C. Insulin resistance is the inability for cells to absorb and use blood sugar for energy due to cells being desensitized to insulin.

Cells that are desensitized to insulin do not take up insulin thus not taking up glucose to use for energy. Option A is incorrect, the pancreas becomes overactive when there is a high level of glucose in the blood but does not define insulin resistance. Option B is the lab value result of a patient with diabetes. Option D is what happens with type II diabetes but does not define insulin resistance.

Felman, A. (2019, March 26). Insulin resistance: Causes, symptoms, and prevention. Retrieved from https://www.medicalnewstoday.com/articles/305567.php.

Answer: B. Eating a healthy diet and exercising to maintain a healthy weight or lose weight.

Eating a healthy diet, high in fruits and vegetables and low in carbs helps the pancreas not get overworked creating insulin thus keeping blood glucose levels in a normal range. Exercising allows for hypertrophy of the muscles which respond better to insulin after exercise. Therefore, an active person can help prevent or reverse insulin resistance. Option A does not help a patient manage their diabetes if the same high carb, high sugar foods are being consumed. Option C should be complimented with exercise to help the muscles respond better to insulin. Option D will only worsen diabetes due to a lack of exercise.

The Diabetes Diet. (2019, June 19). Retrieved from https://www.helpguide.org/articles/diets/the-diabetes-diet.htm.

Answers: A, B, C & D

This patient already wears glasses, so he is at risk for blindness due to the risk of glaucoma, cataracts, and diabetic retinopathy from persistent hyperglycemia. Kidney disease can occur from untreated diabetes due to persistent hypertension and strain on the kidneys. Diabetes is the leading cause of kidney failure in the U.S. Tinnitus is ringing in the ears caused by inadequate blood flow to vessels in the ear due to hyperglycemia. Peripheral neuropathy occurs from nerve damage as well from high levels of glucose in the bloodstream. This increases the risk of infection and amputation of feet.

Felson, S. (Ed.). (2019, May 6). Diabetes Complications: How Uncontrolled Diabetes Affects Your Body. Retrieved from https://www.webmd.com/diabetes/guide/risks-complications-uncontrolled-diabetes#1.Holcát,

M. (2007, May). Tinnitus and diabetes. Retrieved from https://www.ncbi.nlm.nih.gov/pubmed/17642439.

McCance, K. L., Huether, S. E., Brashers, V. L., & Rote, N. S. (2018).  Pathophysiology: the biologic basis for disease in adults and children . St. Louis, MO: Elsevier.

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings

Preview improvements coming to the PMC website in October 2024. Learn More or Try it out now .

• Advanced Search
• Journal List
• HHS Author Manuscripts

Case 6–2020: A 34-Year-Old Woman with Hyperglycemia

Presentation of case.

Dr. Max C. Petersen (Medicine): A 34-year-old woman was evaluated in the diabetes clinic of this hospital for hyperglycemia.

Eleven years before this presentation, the blood glucose level was 126 mg per deciliter (7.0 mmol per liter) on routine laboratory evaluation, which was performed as part of an annual well visit. The patient could not recall whether she had been fasting at the time the test had been performed. One year later, the fasting blood glucose level was 112 mg per deciliter (6.2 mmol per liter; reference range, <100 mg per deciliter [<5.6 mmol per liter]).

Nine years before this presentation, a randomly obtained blood glucose level was 217 mg per deciliter (12.0 mmol per liter), and the patient reported polyuria. At that time, the glycated hemoglobin level was 5.8% (reference range, 4.3 to 5.6); the hemoglobin level was normal. One year later, the glycated hemoglobin level was 5.9%. The height was 165.1 cm, the weight 72.6 kg, and the body-mass index (BMI; the weight in kilograms divided by the square of the height in meters) 26.6. The patient received a diagnosis of prediabetes and was referred to a nutritionist. She made changes to her diet and lost 4.5 kg of body weight over a 6-month period; the glycated hemoglobin level was 5.5%.

Six years before this presentation, the patient became pregnant with her first child. Her prepregnancy BMI was 24.5. At 26 weeks of gestation, the result of a 1-hour oral glucose challenge test (i.e., the blood glucose level obtained 1 hour after the oral administration of a 50-g glucose load in the nonfasting state) was 186 mg per deciliter (10.3 mmol per liter; reference range, <140 mg per deciliter [<7.8 mmol per liter]). She declined a 3-hour oral glucose tolerance test; a presumptive diagnosis of gestational diabetes was made. She was asked to follow a meal plan for gestational diabetes and was treated with insulin during the pregnancy. Serial ultrasound examinations for fetal growth and monitoring were performed. At 34 weeks of gestation, the fetal abdominal circumference was in the 76th percentile for gestational age. Polyhydramnios developed at 37 weeks of gestation. The child was born at 39 weeks 3 days of gestation, weighed 3.9 kg at birth, and had hypoglycemia after birth, which subsequently resolved. Six weeks post partum, the patient’s fasting blood glucose level was 120 mg per deciliter (6.7 mmol per liter), and the result of a 2-hour oral glucose tolerance test (i.e., the blood glucose level obtained 2 hours after the oral administration of a 75-g glucose load in the fasting state) was 131 mg per deciliter (7.3 mmol per liter; reference range, <140 mg per deciliter). Three months post partum, the glycated hemoglobin level was 6.1%. Lifestyle modification for diabetes prevention was recommended.

Four and a half years before this presentation, the patient became pregnant with her second child. Her prepregnancy BMI was 25.1. At 5 weeks of gestation, she had an elevated blood glucose level. Insulin therapy was started at 6 weeks of gestation, and episodes of hypoglycemia occurred during the pregnancy. Serial ultrasound examinations for fetal growth and monitoring were performed. At 28 weeks of gestation, the fetal abdominal circumference was in the 35th percentile for gestational age, and the amniotic fluid level was normal. Labor was induced at 38 weeks of gestation; the child weighed 2.6 kg at birth. Neonatal blood glucose levels were reported as stable after birth. Six weeks post partum, the patient’s fasting blood glucose level was 133 mg per deciliter (7.4 mmol per liter), and the result of a 2-hour oral glucose tolerance test was 236 mg per deciliter (13.1 mmol per liter). The patient received a diagnosis of type 2 diabetes mellitus; lifestyle modification was recommended. Three months post partum, the glycated hemoglobin level was 5.9% and the BMI was 30.0. Over the next 2 years, she followed a low-carbohydrate diet and regular exercise plan and self-monitored the blood glucose level.

Two years before this presentation, the patient became pregnant with her third child. Blood glucose levels were again elevated, and insulin therapy was started early in gestation. She had episodes of hypoglycemia that led to adjustment of her insulin regimen. The child was born at 38 weeks 5 days of gestation, weighed 3.0 kg at birth, and had hypoglycemia that resolved 48 hours after birth. After the birth of her third child, the patient started to receive metformin, which had no effect on the glycated hemoglobin level, despite adjustment of the therapy to the maximal dose.

One year before this presentation, the patient became pregnant with her fourth child. Insulin therapy was again started early in gestation. The patient reported that episodes of hypoglycemia occurred. Polyhydramnios developed. The child was born at 38 weeks 6 days of gestation and weighed 3.5 kg. The patient sought care at the diabetes clinic of this hospital for clarification of her diagnosis.

The patient reported following a low-carbohydrate diet and exercising 5 days per week. There was no fatigue, change in appetite, change in vision, chest pain, shortness of breath, polydipsia, or polyuria. There was no history of anemia, pancreatitis, hirsutism, proximal muscle weakness, easy bruising, headache, sweating, tachycardia, gallstones, or diarrhea. Her menstrual periods were normal. She had not noticed any changes in her facial features or the size of her hands or feet.

The patient had a history of acne and low-back pain. Her only medication was metformin. She had no known medication allergies. She lived with her husband and four children in a suburban community in New England and worked as an administrator. She did not smoke tobacco or use illicit drugs, and she rarely drank alcohol. She identified as non-Hispanic white. Both of her grandmothers had type 2 diabetes mellitus. Her father had hypertension, was overweight, and had received a diagnosis of type 2 diabetes at 50 years of age. Her mother was not overweight and had received a diagnosis of type 2 diabetes at 48 years of age. The patient had two sisters, neither of whom had a history of diabetes or gestational diabetes. There was no family history of hemochromatosis.

On examination, the patient appeared well. The blood pressure was 126/76 mm Hg, and the heart rate 76 beats per minute. The BMI was 25.4. The physical examination was normal. The glycated hemoglobin level was 6.2%.

A diagnostic test was performed.

DIFFERENTIAL DIAGNOSIS

Dr. Miriam S. Udler: I am aware of the diagnosis in this case and participated in the care of this patient. This healthy 34-year-old woman, who had a BMI just above the upper limit of the normal range, presented with a history of hyperglycemia of varying degrees since 24 years of age. When she was not pregnant, she was treated with lifestyle measures as well as metformin therapy for a short period, and she maintained a well-controlled blood glucose level. In thinking about this case, it is helpful to characterize the extent of the hyperglycemia and then to consider its possible causes.

CHARACTERIZING HYPERGLYCEMIA

This patient’s hyperglycemia reached a threshold that was diagnostic of diabetes 1 on two occasions: when she was 25 years of age, she had a randomly obtained blood glucose level of 217 mg per deciliter with polyuria (with diabetes defined as a level of ≥200 mg per deciliter [≥11.1 mmol per liter] with symptoms), and when she was 30 years of age, she had on the same encounter a fasting blood glucose level of 133 mg per deciliter (with diabetes defined as a level of ≥126 mg per deciliter) and a result on a 2-hour oral glucose tolerance test of 236 mg per deciliter (with diabetes defined as a level of ≥200 mg per deciliter). On both of these occasions, her glycated hemoglobin level was in the prediabetes range (defined as 5.7 to 6.4%). In establishing the diagnosis of diabetes, the various blood glucose studies and glycated hemoglobin testing may provide discordant information because the tests have different sensitivities for this diagnosis, with glycated hemoglobin testing being the least sensitive. 2 Also, there are situations in which the glycated hemoglobin level can be inaccurate; for example, the patient may have recently received a blood transfusion or may have a condition that alters the life span of red cells, such as anemia, hemoglobinopathy, or pregnancy. 3 These conditions were not present in this patient at the time that the glycated hemoglobin measurements were obtained. In addition, since the glycated hemoglobin level reflects the average glucose level typically over a 3-month period, discordance with timed blood glucose measurements can occur if there has been a recent change in glycemic control. This patient had long-standing mild hyperglycemia but met criteria for diabetes on the basis of the blood glucose levels noted.

Type 1 and Type 2 Diabetes

Now that we have characterized the patient’s hyperglycemia as meeting criteria for diabetes, it is important to consider the possible types. More than 90% of adults with diabetes have type 2 diabetes, which is due to progressive loss of insulin secretion by beta cells that frequently occurs in the context of insulin resistance. This patient had received a diagnosis of type 2 diabetes; however, some patients with diabetes may be given a diagnosis of type 2 diabetes on the basis of not having features of type 1 diabetes, which is characterized by autoimmune destruction of the pancreatic beta cells that leads to rapid development of insulin dependence, with ketoacidosis often present at diagnosis.

Type 1 diabetes accounts for approximately 6% of all cases of diabetes in adults (≥18 years of age) in the United States, 4 and 80% of these cases are diagnosed before the patient is 20 years of age. 5 Since this patient’s diabetes was essentially nonprogressive over a period of at least 9 years, she most likely does not have type 1 diabetes. It is therefore not surprising that she had received a diagnosis of type 2 diabetes, but there are several other types of diabetes to consider, particularly since some features of her case do not fit with a typical case of type 2 diabetes, such as her age at diagnosis, the presence of hyperglycemia despite a nearly normal BMI, and the mild and nonprogressive nature of her disease over the course of many years.

Less Common Types of Diabetes

Latent autoimmune diabetes in adults (LADA) is a mild form of autoimmune diabetes that should be considered in this patient. However, there is controversy as to whether LADA truly represents an entity that is distinct from type 1 diabetes. 6 Both patients with type 1 diabetes and patients with LADA commonly have elevated levels of diabetes-associated autoantibodies; however, LADA has been defined by an older age at onset (typically >25 years) and slower progression to insulin dependence (over a period of >6 months). 7 This patient had not been tested for diabetes-associated autoantibodies. I ordered these tests to help evaluate for LADA, but this was not my leading diagnosis because of her young age at diagnosis and nonprogressive clinical course over a period of at least 9 years.

If the patient’s diabetes had been confined to pregnancy, we might consider gestational diabetes, but she had hyperglycemia outside of pregnancy. Several medications can cause hyperglycemia, including glucocorticoids, atypical antipsychotic agents, cancer immunotherapies, and some antiretroviral therapies and immunosuppressive agents used in transplantation. 8 However, this patient was not receiving any of these medications. Another cause of diabetes to consider is destruction of the pancreas due to, for example, cystic fibrosis, a tumor, or pancreatitis, but none of these were present. Secondary endocrine disorders — including excess cortisol production, excess growth hormone production, and pheochromocytoma — were considered to be unlikely in this patient on the basis of the history, review of symptoms, and physical examination.

Monogenic Diabetes

A final category to consider is monogenic diabetes, which is caused by alteration of a single gene. Types of monogenic diabetes include maturity-onset diabetes of the young (MODY), neonatal diabetes, and syndromic forms of diabetes. Monogenic diabetes accounts for 1 to 6% of cases of diabetes in children 9 and approximately 0.4% of cases in adults. 10 Neonatal diabetes is diagnosed typically within the first 6 months of life; syndromic forms of monogenic diabetes have other abnormal features, including particular organ dysfunction. Neither condition is applicable to this patient.

MODY is an autosomal dominant condition characterized by primary pancreatic beta-cell dysfunction that causes mild diabetes that is diagnosed during adolescence or early adulthood. As early as 1964, the nomenclature “maturity-onset diabetes of the young” was used to describe cases that resembled adult-onset type 2 diabetes in terms of the slow progression to insulin use (as compared with the rapid progression in type 1 diabetes) but occurred in relatively young patients. 11 Several genes cause distinct forms of MODY that have specific disease features that inform treatment, and thus MODY is a clinically important diagnosis. Most forms of MODY cause isolated abnormal glucose levels (in contrast to syndromic monogenic diabetes), a manifestation that has contributed to its frequent misdiagnosis as type 1 or type 2 diabetes. 12

Genetic Basis of MODY

Although at least 13 genes have been associated with MODY, 3 genes — GCK , which encodes glucokinase, and HNF1A and HNF4A , which encode hepatocyte nuclear factors 1A and 4A, respectively — account for most cases. MODY associated with GCK (known as GCK-MODY) is characterized by mild, nonprogressive hyperglycemia that is present since birth, whereas the forms of MODY associated with HNF1A and HNF4A (known as HNF1A-MODY and HNF4A-MODY, respectively) are characterized by the development of diabetes, typically in the early teen years or young adulthood, that is initially mild and then progresses such that affected patients may receive insulin before diagnosis.

In patients with GCK-MODY, genetic variants reduce the function of glucokinase, the enzyme in pancreatic beta cells that functions as a glucose sensor and controls the rate of entry of glucose into the glycolytic pathway. As a result, reduced sensitivity to glucose-induced insulin secretion causes asymptomatic mild fasting hyperglycemia, with an upward shift in the normal range of the fasting blood glucose level to 100 to 145 mg per deciliter (5.6 to 8.0 mmol per liter), and also causes an upward shift in postprandial blood glucose levels, but with tight regulation maintained ( Fig. 1 ). 13 This mild hyperglycemia is not thought to confer a predisposition to complications of diabetes, 14 is largely unaltered by treatment, 15 and does not necessitate treatment outside of pregnancy.

Key features suggesting maturity-onset diabetes of the young (MODY) in this patient were an age of less than 35 years at the diagnosis of diabetes, a strong family history of diabetes with an autosomal dominant pattern of inheritance, and hyperglycemia despite a close-to-normal body-mass index. None of these features is an absolute criterion. MODY is caused by single gene–mediated disruption of pancreatic beta-cell function. In MODY associated with the GCK gene (known as GCK-MODY), disrupted glucokinase function causes a mild upward shift in glucose levels through-out the day and does not necessitate treatment. 13 In the pedigree, circles represent female family members, squares male family members, blue family members affected by diabetes, and green unaffected family members. The arrow indicates the patient.

In contrast to GCK-MODY, the disorders HNF1A-MODY and HNF4A-MODY result in progressive hyperglycemia that eventually leads to treatment. 16 Initially, there may be a normal fasting glucose level and large spikes in postprandial glucose levels (to >80 mg per deciliter [>4.4 mmol per liter]). 17 Patients can often be treated with oral agents and discontinue insulin therapy started before the diagnosis of MODY. 18 Of note, patients with HNF1A-MODY or HNF4A-MODY are typically sensitive to treatment with sulfonylureas 19 but may also respond to glucagon-like peptide-1 receptor agonists. 20

This patient had received a diagnosis of diabetes before 35 years of age, had a family history of diabetes involving multiple generations, and was not obese. These features are suggestive of MODY but do not represent absolute criteria for the condition ( Fig. 1 ). 1 Negative testing for diabetes-associated autoantibodies would further increase the likelihood of MODY. There are methods to calculate a patient’s risk of having MODY associated with GCK , HNF1A , or HNF4A . 21 , 22 Using an online calculator ( www.diabetesgenes.org/mody-probability-calculator ), we estimate that the probability of this patient having MODY is at least 75.5%. Genetic testing would be needed to confirm this diagnosis, and in patients at an increased risk for MODY, multigene panel testing has been shown to be cost-effective. 23 , 24

DR. MIRIAM S. UDLER’S DIAGNOSIS

Maturity-onset diabetes of the young, most likely due to a GCK variant.

DIAGNOSTIC TESTING

Dr. Christina A. Austin-Tse: A diagnostic sequencing test of five genes associated with MODY was performed. One clinically significant variant was identified in the GCK gene (NM_000162.3): a c.787T→C transition resulting in the p.Ser263Pro missense change. Review of the literature and variant databases revealed that this variant had been previously identified in at least three patients with early-onset diabetes and had segregated with disease in at least three affected members of two families (GeneDx: personal communication). 25 , 26 Furthermore, the variant was rare in large population databases (occurring in 1 out of 128,844 European chromosomes in gnomAD 27 ), a feature consistent with a disease-causing role. Although the serine residue at position 263 was not highly conserved, multiple in vitro functional studies have shown that the p.Ser263Pro variant negatively affects the stability of the glucokinase enzyme. 26 , 28 – 30 As a result, this variant met criteria to be classified as “likely pathogenic.” 31 As mentioned previously, a diagnosis of GCK-MODY is consistent with this patient’s clinical features. On subsequent testing of additional family members, the same “likely pathogenic” variant was identified in the patient’s father and second child, both of whom had documented hyperglycemia.

DISCUSSION OF MANAGEMENT

Dr. Udler: In this patient, the diagnosis of GCK-MODY means that it is normal for her blood glucose level to be mildly elevated. She can stop taking metformin because discontinuation is not expected to substantially alter her glycated hemoglobin level 15 , 32 and because she is not at risk for complications of diabetes. 14 However, she should continue to maintain a healthy lifestyle. Although patients with GCK-MODY are not typically treated for hyperglycemia outside of pregnancy, they may need to be treated during pregnancy.

It is possible for a patient to have type 1 or type 2 diabetes in addition to MODY, so this patient should be screened for diabetes according to recommendations for the general population (e.g., in the event that she has a risk factor for diabetes, such as obesity). 1 Since the mild hyperglycemia associated with GCK-MODY is asymptomatic (and probably unrelated to the polyuria that this patient had described in the past), the development of symptoms of hyperglycemia, such as polyuria, polydipsia, or blurry vision, should prompt additional evaluation. In patients with GCK-MODY, the glycated hemoglobin level is typically below 7.5%, 33 so a value rising above that threshold or a sudden large increase in the glycated hemoglobin level could indicate concomitant diabetes from another cause, which would need to be evaluated and treated.

This patient’s family members are at risk for having the same GCK variant, with a 50% chance of offspring inheriting a variant from an affected parent. Since the hyperglycemia associated with GCK-MODY is present from birth, it is necessary to perform genetic testing only in family members with demonstrated hyperglycemia. I offered site-specific genetic testing to the patient’s parents and second child.

Dr. Meridale V. Baggett (Medicine): Dr. Powe, would you tell us how you would treat this patient during pregnancy?

Dr. Camille E. Powe: During the patient’s first pregnancy, routine screening led to a presumptive diagnosis of gestational diabetes, the most common cause of hyperglycemia in pregnancy. Hyperglycemia in pregnancy is associated with adverse pregnancy outcomes, 34 and treatment lowers the risk of such outcomes. 35 , 36 Two of the most common complications — fetal overgrowth (which can lead to birth injuries, shoulder dystocia, and an increased risk of cesarean delivery) and neonatal hypoglycemia — are thought to be the result of fetal hyperinsulinemia. 37 Maternal glucose is freely transported across the placenta, and excess glucose augments insulin secretion from the fetal pancreas. In fetal life, insulin is a potent growth factor, and neonates who have hyperinsulinemia in utero often continue to secrete excess insulin in the first few days of life. In the treatment of pregnant women with diabetes, we strive for strict blood sugar control (fasting blood glucose level, <95 mg per deciliter [<5.3 mmol per liter]; 2-hour postprandial blood glucose level, <120 mg per deciliter) to decrease the risk of these and other hyperglycemia-associated adverse pregnancy outcomes. 38 – 40

In the third trimester of the patient’s first pregnancy, obstetrical ultrasound examination revealed a fetal abdominal circumference in the 76th percentile for gestational age and polyhydramnios, signs of fetal exposure to maternal hyperglycemia. 40 – 42 Case series involving families with GCK-MODY have shown that the effect of maternal hyperglycemia on the fetus depends on whether the fetus inherits the pathogenic GCK variant. 43 – 48 Fetuses that do not inherit the maternal variant have overgrowth, presumably due to fetal hyperinsulinemia ( Fig. 2A ). In contrast, fetuses that inherit the variant do not have overgrowth and are born at a weight that is near the average for gestational age, despite maternal hyperglycemia, presumably because the variant results in decreased insulin secretion ( Fig. 2B ). Fetuses that inherit GCK-MODY from their fathers and have euglycemic mothers appear to be undergrown, most likely because their insulin secretion is lower than normal when they and their mothers are euglycemic ( Fig. 2D ). Because fetal overgrowth and polyhydramnios occurred during this patient’s first pregnancy and neonatal hypoglycemia developed after the birth, the patient’s first child is probably not affected by GCK-MODY.

Pathogenic variants that lead to GCK-MODY, when carried by a fetus, change the usual relationship of maternal hyperglycemia to fetal hyperinsulinemia and fetal overgrowth. GCK-MODY–affected fetuses have lower insulin secretion than unaffected fetuses in response to the same maternal blood glucose level. In a hyperglycemic mother carrying a fetus who is unaffected by GCK-MODY, excessive fetal growth is usually apparent (Panel A). Studies involving GCK-MODY–affected hyperglycemic mothers have shown that fetal growth is normal despite maternal hyperglycemia when a fetus has the maternal GCK variant (Panel B). The goal of treatment of maternal hyperglycemia when a fetus is unaffected by GCK-MODY is to establish euglycemia to normalize fetal insulin levels and growth (Panel C); whether this can be accomplished in the case of maternal GCK-MODY is controversial, given the genetically determined elevated maternal glycemic set point. In the context of maternal euglycemia, GCK-MODY–affected fetuses may be at risk for fetal growth restriction (Panel D).

In accordance with standard care for pregnant women with diabetes who do not meet glycemic targets after dietary modification, 38 , 39 the patient was treated with insulin during her pregnancies. In her second pregnancy, treatment was begun early, after hyperglycemia was detected in the first trimester. Because she had not yet received the diagnosis of GCK-MODY during any of her pregnancies, no consideration of this condition was given during her obstetrical treatment. Whether treatment affects the risk of hyperglycemia-associated adverse pregnancy outcomes in pregnant women with known GCK-MODY is controversial, with several case series showing that the birth weight percentile in unaffected neonates remains consistent regardless of whether the mother is treated with insulin. 44 , 45 Evidence suggests that it may be difficult to overcome a genetically determined glycemic set point in patients with GCK-MODY with the use of pharmacotherapy, 15 , 32 and affected patients may have symptoms of hypoglycemia when the blood glucose level is normal because of an enhanced counterregulatory response. 49 , 50 Still, to the extent that it is possible, it would be desirable to safely lower the blood glucose level in a woman with GCK-MODY who is pregnant with an unaffected fetus in order to decrease the risk of fetal overgrowth and other consequences of mildly elevated glucose levels ( Fig. 2C ). 46 , 47 , 51 In contrast, there is evidence that lowering the blood glucose level in a pregnant woman with GCK-MODY could lead to fetal growth restriction if the fetus is affected ( Fig. 2D ). 45 , 52 During this patient’s second pregnancy, she was treated with insulin beginning in the first trimester, and her daughter’s birth weight was near the 16th percentile for gestational age; this outcome is consistent with the daughter’s ultimate diagnosis of GCK-MODY.

Expert opinion suggests that, in pregnant women with GCK-MODY, insulin therapy should be deferred until fetal growth is assessed by means of ultrasound examination beginning in the late second trimester. If there is evidence of fetal overgrowth, the fetus is presumed to be unaffected by GCK-MODY and insulin therapy is initiated. 53 After I have counseled women with GCK-MODY on the potential risks and benefits of insulin treatment during pregnancy, I have sometimes used a strategy of treating hyperglycemia from early in pregnancy using modified glycemic targets that are less stringent than the targets typically used during pregnancy. This strategy attempts to balance the risk of growth restriction in an affected fetus (as well as maternal hypoglycemia) with the potential benefit of glucose-lowering therapy for an unaffected fetus.

Dr. Udler: The patient stopped taking metformin, and subsequent glycated hemoglobin levels remained unchanged, at 6.2%. Her father and 5-year-old daughter (second child) both tested positive for the same GCK variant. Her father had a BMI of 36 and a glycated hemoglobin level of 7.8%, so I counseled him that he most likely had type 2 diabetes in addition to GCK-MODY. He is currently being treated with metformin and lifestyle measures. The patient’s daughter now has a clear diagnosis to explain her hyperglycemia, which will help in preventing misdiagnosis of type 1 diabetes, given her young age, and will be important for the management of any future pregnancies. She will not need any medical follow-up for GCK-MODY until she is considering pregnancy.

FINAL DIAGNOSIS

Maturity-onset diabetes of the young due to a GCK variant.

Acknowledgments

We thank Dr. Andrew Hattersley and Dr. Sarah Bernstein for helpful comments on an earlier draft of the manuscript.

This case was presented at the Medical Case Conference.

No potential conflict of interest relevant to this article was reported.

Disclosure forms provided by the authors are available with the full text of this article at NEJM.org .

• Previous Article
• Next Article

Case Presentation

Case study: a patient with uncontrolled type 2 diabetes and complex comorbidities whose diabetes care is managed by an advanced practice nurse.

• Split-Screen
• Article contents
• Figures & tables
• Supplementary Data
• Peer Review
• Open the PDF for in another window
• Cite Icon Cite
• Get Permissions

Geralyn Spollett; Case Study: A Patient With Uncontrolled Type 2 Diabetes and Complex Comorbidities Whose Diabetes Care Is Managed by an Advanced Practice Nurse. Diabetes Spectr 1 January 2003; 16 (1): 32–36. https://doi.org/10.2337/diaspect.16.1.32

Download citation file:

• Ris (Zotero)
• Reference Manager

The specialized role of nursing in the care and education of people with diabetes has been in existence for more than 30 years. Diabetes education carried out by nurses has moved beyond the hospital bedside into a variety of health care settings. Among the disciplines involved in diabetes education, nursing has played a pivotal role in the diabetes team management concept. This was well illustrated in the Diabetes Control and Complications Trial (DCCT) by the effectiveness of nurse managers in coordinating and delivering diabetes self-management education. These nurse managers not only performed administrative tasks crucial to the outcomes of the DCCT, but also participated directly in patient care. 1  

The emergence and subsequent growth of advanced practice in nursing during the past 20 years has expanded the direct care component, incorporating aspects of both nursing and medical care while maintaining the teaching and counseling roles. Both the clinical nurse specialist (CNS) and nurse practitioner (NP) models, when applied to chronic disease management, create enhanced patient-provider relationships in which self-care education and counseling is provided within the context of disease state management. Clement 2 commented in a review of diabetes self-management education issues that unless ongoing management is part of an education program, knowledge may increase but most clinical outcomes only minimally improve. Advanced practice nurses by the very nature of their scope of practice effectively combine both education and management into their delivery of care.

Operating beyond the role of educator, advanced practice nurses holistically assess patients’ needs with the understanding of patients’ primary role in the improvement and maintenance of their own health and wellness. In conducting assessments, advanced practice nurses carefully explore patients’ medical history and perform focused physical exams. At the completion of assessments, advanced practice nurses, in conjunction with patients, identify management goals and determine appropriate plans of care. A review of patients’ self-care management skills and application/adaptation to lifestyle is incorporated in initial histories, physical exams, and plans of care.

Many advanced practice nurses (NPs, CNSs, nurse midwives, and nurse anesthetists) may prescribe and adjust medication through prescriptive authority granted to them by their state nursing regulatory body. Currently, all 50 states have some form of prescriptive authority for advanced practice nurses. 3 The ability to prescribe and adjust medication is a valuable asset in caring for individuals with diabetes. It is a crucial component in the care of people with type 1 diabetes, and it becomes increasingly important in the care of patients with type 2 diabetes who have a constellation of comorbidities, all of which must be managed for successful disease outcomes.

Many studies have documented the effectiveness of advanced practice nurses in managing common primary care issues. 4 NP care has been associated with a high level of satisfaction among health services consumers. In diabetes, the role of advanced practice nurses has significantly contributed to improved outcomes in the management of type 2 diabetes, 5 in specialized diabetes foot care programs, 6 in the management of diabetes in pregnancy, 7 and in the care of pediatric type 1 diabetic patients and their parents. 8 , 9 Furthermore, NPs have also been effective providers of diabetes care among disadvantaged urban African-American patients. 10 Primary management of these patients by NPs led to improved metabolic control regardless of whether weight loss was achieved.

The following case study illustrates the clinical role of advanced practice nurses in the management of a patient with type 2 diabetes.

A.B. is a retired 69-year-old man with a 5-year history of type 2 diabetes. Although he was diagnosed in 1997, he had symptoms indicating hyperglycemia for 2 years before diagnosis. He had fasting blood glucose records indicating values of 118–127 mg/dl, which were described to him as indicative of “borderline diabetes.” He also remembered past episodes of nocturia associated with large pasta meals and Italian pastries. At the time of initial diagnosis, he was advised to lose weight (“at least 10 lb.”), but no further action was taken.

Referred by his family physician to the diabetes specialty clinic, A.B. presents with recent weight gain, suboptimal diabetes control, and foot pain. He has been trying to lose weight and increase his exercise for the past 6 months without success. He had been started on glyburide (Diabeta), 2.5 mg every morning, but had stopped taking it because of dizziness, often accompanied by sweating and a feeling of mild agitation, in the late afternoon.

A.B. also takes atorvastatin (Lipitor), 10 mg daily, for hypercholesterolemia (elevated LDL cholesterol, low HDL cholesterol, and elevated triglycerides). He has tolerated this medication and adheres to the daily schedule. During the past 6 months, he has also taken chromium picolinate, gymnema sylvestre, and a “pancreas elixir” in an attempt to improve his diabetes control. He stopped these supplements when he did not see any positive results.

He does not test his blood glucose levels at home and expresses doubt that this procedure would help him improve his diabetes control. “What would knowing the numbers do for me?,” he asks. “The doctor already knows the sugars are high.”

A.B. states that he has “never been sick a day in my life.” He recently sold his business and has become very active in a variety of volunteer organizations. He lives with his wife of 48 years and has two married children. Although both his mother and father had type 2 diabetes, A.B. has limited knowledge regarding diabetes self-care management and states that he does not understand why he has diabetes since he never eats sugar. In the past, his wife has encouraged him to treat his diabetes with herbal remedies and weight-loss supplements, and she frequently scans the Internet for the latest diabetes remedies.

During the past year, A.B. has gained 22 lb. Since retiring, he has been more physically active, playing golf once a week and gardening, but he has been unable to lose more than 2–3 lb. He has never seen a dietitian and has not been instructed in self-monitoring of blood glucose (SMBG).

A.B.’s diet history reveals excessive carbohydrate intake in the form of bread and pasta. His normal dinners consist of 2 cups of cooked pasta with homemade sauce and three to four slices of Italian bread. During the day, he often has “a slice or two” of bread with butter or olive oil. He also eats eight to ten pieces of fresh fruit per day at meals and as snacks. He prefers chicken and fish, but it is usually served with a tomato or cream sauce accompanied by pasta. His wife has offered to make him plain grilled meats, but he finds them “tasteless.” He drinks 8 oz. of red wine with dinner each evening. He stopped smoking more than 10 years ago, he reports, “when the cost of cigarettes topped a buck-fifty.”

The medical documents that A.B. brings to this appointment indicate that his hemoglobin A 1c (A1C) has never been <8%. His blood pressure has been measured at 150/70, 148/92, and 166/88 mmHg on separate occasions during the past year at the local senior center screening clinic. Although he was told that his blood pressure was “up a little,” he was not aware of the need to keep his blood pressure ≤130/80 mmHg for both cardiovascular and renal health. 11  

A.B. has never had a foot exam as part of his primary care exams, nor has he been instructed in preventive foot care. However, his medical records also indicate that he has had no surgeries or hospitalizations, his immunizations are up to date, and, in general, he has been remarkably healthy for many years.

Physical Exam

A physical examination reveals the following:

Weight: 178 lb; height: 5′2″; body mass index (BMI): 32.6 kg/m 2

Fasting capillary glucose: 166 mg/dl

Blood pressure: lying, right arm 154/96 mmHg; sitting, right arm 140/90 mmHg

Pulse: 88 bpm; respirations 20 per minute

Eyes: corrective lenses, pupils equal and reactive to light and accommodation, Fundi-clear, no arteriolovenous nicking, no retinopathy

Thyroid: nonpalpable

Lungs: clear to auscultation

Heart: Rate and rhythm regular, no murmurs or gallops

Vascular assessment: no carotid bruits; femoral, popliteal, and dorsalis pedis pulses 2+ bilaterally

Neurological assessment: diminished vibratory sense to the forefoot, absent ankle reflexes, monofilament (5.07 Semmes-Weinstein) felt only above the ankle

Lab Results

Results of laboratory tests (drawn 5 days before the office visit) are as follows:

Glucose (fasting): 178 mg/dl (normal range: 65–109 mg/dl)

Creatinine: 1.0 mg/dl (normal range: 0.5–1.4 mg/dl)

Blood urea nitrogen: 18 mg/dl (normal range: 7–30 mg/dl)

Sodium: 141 mg/dl (normal range: 135–146 mg/dl)

Potassium: 4.3 mg/dl (normal range: 3.5–5.3 mg/dl)

Lipid panel

    • Total cholesterol: 162 mg/dl (normal: <200 mg/dl)

    • HDL cholesterol: 43 mg/dl (normal: ≥40 mg/dl)

    • LDL cholesterol (calculated): 84 mg/dl (normal: <100 mg/dl)

    • Triglycerides: 177 mg/dl (normal: <150 mg/dl)

    • Cholesterol-to-HDL ratio: 3.8 (normal: <5.0)

AST: 14 IU/l (normal: 0–40 IU/l)

ALT: 19 IU/l (normal: 5–40 IU/l)

Alkaline phosphotase: 56 IU/l (normal: 35–125 IU/l)

A1C: 8.1% (normal: 4–6%)

Urine microalbumin: 45 mg (normal: <30 mg)

Based on A.B.’s medical history, records, physical exam, and lab results, he is assessed as follows:

Uncontrolled type 2 diabetes (A1C >7%)

Obesity (BMI 32.4 kg/m 2 )

Hyperlipidemia (controlled with atorvastatin)

Peripheral neuropathy (distal and symmetrical by exam)

Hypertension (by previous chart data and exam)

Elevated urine microalbumin level

Self-care management/lifestyle deficits

    • Limited exercise

    • High carbohydrate intake

    • No SMBG program

Poor understanding of diabetes

A.B. presented with uncontrolled type 2 diabetes and a complex set of comorbidities, all of which needed treatment. The first task of the NP who provided his care was to select the most pressing health care issues and prioritize his medical care to address them. Although A.B. stated that his need to lose weight was his chief reason for seeking diabetes specialty care, his elevated glucose levels and his hypertension also needed to be addressed at the initial visit.

The patient and his wife agreed that a referral to a dietitian was their first priority. A.B. acknowledged that he had little dietary information to help him achieve weight loss and that his current weight was unhealthy and “embarrassing.” He recognized that his glucose control was affected by large portions of bread and pasta and agreed to start improving dietary control by reducing his portion size by one-third during the week before his dietary consultation. Weight loss would also be an important first step in reducing his blood pressure.

The NP contacted the registered dietitian (RD) by telephone and referred the patient for a medical nutrition therapy assessment with a focus on weight loss and improved diabetes control. A.B.’s appointment was scheduled for the following week. The RD requested that during the intervening week, the patient keep a food journal recording his food intake at meals and snacks. She asked that the patient also try to estimate portion sizes.

Although his physical activity had increased since his retirement, it was fairly sporadic and weather-dependent. After further discussion, he realized that a week or more would often pass without any significant form of exercise and that most of his exercise was seasonal. Whatever weight he had lost during the summer was regained in the winter, when he was again quite sedentary.

A.B.’s wife suggested that the two of them could walk each morning after breakfast. She also felt that a treadmill at home would be the best solution for getting sufficient exercise in inclement weather. After a short discussion about the positive effect exercise can have on glucose control, the patient and his wife agreed to walk 15–20 minutes each day between 9:00 and 10:00 a.m.

A first-line medication for this patient had to be targeted to improving glucose control without contributing to weight gain. Thiazolidinediones (i.e., rosiglitizone [Avandia] or pioglitizone [Actos]) effectively address insulin resistance but have been associated with weight gain. 12 A sulfonylurea or meglitinide (i.e., repaglinide [Prandin]) can reduce postprandial elevations caused by increased carbohydrate intake, but they are also associated with some weight gain. 12 When glyburide was previously prescribed, the patient exhibited signs and symptoms of hypoglycemia (unconfirmed by SMBG). α-Glucosidase inhibitors (i.e., acarbose [Precose]) can help with postprandial hyperglycemia rise by blunting the effect of the entry of carbohydrate-related glucose into the system. However, acarbose requires slow titration, has multiple gastrointestinal (GI) side effects, and reduces A1C by only 0.5–0.9%. 13 Acarbose may be considered as a second-line therapy for A.B. but would not fully address his elevated A1C results. Metformin (Glucophage), which reduces hepatic glucose production and improves insulin resistance, is not associated with hypoglycemia and can lower A1C results by 1%. Although GI side effects can occur, they are usually self-limiting and can be further reduced by slow titration to dose efficacy. 14  

After reviewing these options and discussing the need for improved glycemic control, the NP prescribed metformin, 500 mg twice a day. Possible GI side effects and the need to avoid alcohol were of concern to A.B., but he agreed that medication was necessary and that metformin was his best option. The NP advised him to take the medication with food to reduce GI side effects.

The NP also discussed with the patient a titration schedule that increased the dosage to 1,000 mg twice a day over a 4-week period. She wrote out this plan, including a date and time for telephone contact and medication evaluation, and gave it to the patient.

During the visit, A.B. and his wife learned to use a glucose meter that features a simple two-step procedure. The patient agreed to use the meter twice a day, at breakfast and dinner, while the metformin dose was being titrated. He understood the need for glucose readings to guide the choice of medication and to evaluate the effects of his dietary changes, but he felt that it would not be “a forever thing.”

The NP reviewed glycemic goals with the patient and his wife and assisted them in deciding on initial short-term goals for weight loss, exercise, and medication. Glucose monitoring would serve as a guide and assist the patient in modifying his lifestyle.

A.B. drew the line at starting an antihypertensive medication—the angiotensin-converting enzyme (ACE) inhibitor enalapril (Vasotec), 5 mg daily. He stated that one new medication at a time was enough and that “too many medications would make a sick man out of me.” His perception of the state of his health as being represented by the number of medications prescribed for him gave the advanced practice nurse an important insight into the patient’s health belief system. The patient’s wife also believed that a “natural solution” was better than medication for treating blood pressure.

Although the use of an ACE inhibitor was indicated both by the level of hypertension and by the presence of microalbuminuria, the decision to wait until the next office visit to further evaluate the need for antihypertensive medication afforded the patient and his wife time to consider the importance of adding this pharmacotherapy. They were quite willing to read any materials that addressed the prevention of diabetes complications. However, both the patient and his wife voiced a strong desire to focus their energies on changes in food and physical activity. The NP expressed support for their decision. Because A.B. was obese, weight loss would be beneficial for many of his health issues.

Because he has a sedentary lifestyle, is >35 years old, has hypertension and peripheral neuropathy, and is being treated for hypercholestrolemia, the NP performed an electrocardiogram in the office and referred the patient for an exercise tolerance test. 11 In doing this, the NP acknowledged and respected the mutually set goals, but also provided appropriate pre-exercise screening for the patient’s protection and safety.

In her role as diabetes educator, the NP taught A.B. and his wife the importance of foot care, demonstrating to the patient his inability to feel the light touch of the monofilament. She explained that the loss of protective sensation from peripheral neuropathy means that he will need to be more vigilant in checking his feet for any skin lesions caused by poorly fitting footwear worn during exercise.

At the conclusion of the visit, the NP assured A.B. that she would share the plan of care they had developed with his primary care physician, collaborating with him and discussing the findings of any diagnostic tests and procedures. She would also work in partnership with the RD to reinforce medical nutrition therapies and improve his glucose control. In this way, the NP would facilitate the continuity of care and keep vital pathways of communication open.

Advanced practice nurses are ideally suited to play an integral role in the education and medical management of people with diabetes. 15 The combination of clinical skills and expertise in teaching and counseling enhances the delivery of care in a manner that is both cost-reducing and effective. Inherent in the role of advanced practice nurses is the understanding of shared responsibility for health care outcomes. This partnering of nurse with patient not only improves care but strengthens the patient’s role as self-manager.

Geralyn Spollett, MSN, C-ANP, CDE, is associate director and an adult nurse practitioner at the Yale Diabetes Center, Department of Endocrinology and Metabolism, at Yale University in New Haven, Conn. She is an associate editor of Diabetes Spectrum.

Note of disclosure: Ms. Spollett has received honoraria for speaking engagements from Novo Nordisk Pharmaceuticals, Inc., and Aventis and has been a paid consultant for Aventis. Both companies produce products and devices for the treatment of diabetes.

Email alerts

• Advanced Practice Care: Advanced Practice Care in Diabetes: Epilogue
• Advanced Practice Care: Advanced Practice Care in Diabetes: Preface
• Online ISSN 1944-7353
• Print ISSN 1040-9165
• Diabetes Care
• Clinical Diabetes
• Diabetes Spectrum
• Standards of Medical Care in Diabetes
• Scientific Sessions Abstracts
• BMJ Open Diabetes Research & Care
• ShopDiabetes.org
• ADA Professional Books

Clinical Compendia

• Clinical Compendia Home
• Latest News
• DiabetesPro SmartBrief
• Special Collections
• DiabetesPro®
• Diabetes Food Hub™
• Insulin Affordability
• Know Diabetes By Heart™
• About the ADA
• Journal Policies
• For Reviewers
• Advertising in ADA Journals
• Reprints and Permission for Reuse
• Copyright Notice/Public Access Policy
• ADA Professional Membership
• ADA Member Directory
• Diabetes.org
• X (Twitter)
• Cookie Policy
• Accessibility
• Terms & Conditions
• Get Adobe Acrobat Reader
• © Copyright American Diabetes Association

This Feature Is Available To Subscribers Only

Sign In or Create an Account

• Diabetes & Primary Care
• Vol:23 | No:04

Interactive case study: Hypoglycaemia and type 2 diabetes

• 12 Aug 2021

Share this article + Add to reading list – Remove from reading list ↓ Download pdf

Diabetes & Primary Care ’s series of interactive case studies is aimed at GPs, practice nurses and other professionals in primary and community care who would like to broaden their understanding of type 2 diabetes.

The four mini-case studies created for this issue of the journal cover various aspects relating to hypoglycaemia and type 2 diabetes.

The format uses typical clinical scenarios as tools for learning. Information is provided in short sections, with most ending in a question to answer before moving on to the next section.

Working through the case studies will improve your knowledge and problem-solving skills in type 2 diabetes by encouraging you to make evidence-based decisions in the context of individual cases.

You are invited to respond to the questions by typing in your answers. In this way, you are actively involved in the learning process, which is hopefully a much more effective way to learn. By actively engaging with these case histories, I hope you will feel more confident and empowered to manage such presentations effectively in the future.

Active, 76-year-old Jean, who has type 2 diabetes, has experienced dizziness, confusion and speech slurring after gardening for several hours. A capillary blood glucose reading of 2.3 mmol/L was found.

How would you respond to her episode?

John, a 49-year-old HGV driver, uses metformin, gliclazide and alogliptin for his type 2 diabetes. Occasionally, he experiences mild symptoms of hypoglycaemia.

Would you make any changes to his medication?

Chinua has had type 2 diabetes for 13 years. He has recently switched from a basal insulin to a twice-daily premixed insulin. He has heard that his risk of experiencing hypoglycaemia may be higher.

What symptoms should Chinua be looking out for?

65-year-old Candice has collapsed at her type 2 diabetes review. Her capillary glucose reading is 1.7 mmol/L.

How can you manage this episode of severe hypoglycaemia?

By working through these interactive cases, you will consider the following issues and more:

• What constitutes hypoglycaemia.
• Its causes and risk factors in type 2 diabetes.
• Practical advice on its detection and management.
• Strategies for minimising the risk.

Click here to access new interactive case studies

Interactive case study: Non-diabetic hyperglycaemia – Prediabetes

Diabetes distilled: smoking cessation cuts excess mortality rates after as little as 3 years, impact of freestyle libre 2 on diabetes distress and glycaemic control in people on twice-daily pre-mixed insulin, updated guidance from the pcds and abcd: managing the national glp-1 ra shortage, diabetes distilled: fib-4 – a diagnostic and prognostic marker for liver and cardiovascular events and mortality, at a glance factsheet: tirzepatide for management of type 2 diabetes, editorial: lipid management, tirzepatide and hybrid closed-loop: what does new nice guidance recommend.

Diagnosing and managing non-diabetic hyperglycaemia.

17 Apr 2024

The mortality benefits of smoking cessation may be greater and accrue more rapidly than previously understood.

Expanding CGM eligibility criteria to include this patient group may be beneficial.

27 Mar 2024

Advice on selecting alternative glucose-lowering therapies when GLP-1 RAs used in the management of type 2 diabetes in adults are unavailable.

22 Mar 2024

Sign up to all DiabetesontheNet journals

• CPD Learning
• Journal of Diabetes Nursing
• Diabetes Care for Children & Young People
• The Diabetic Foot Journal
• Diabetes Digest

Useful information

• Terms and conditions
• Privacy policy
• Editorial policies and ethics

By clicking ‘Subscribe’, you are agreeing that DiabetesontheNet.com are able to email you periodic newsletters. You may unsubscribe from these at any time. Your info is safe with us and we will never sell or trade your details. For information please review our Privacy Policy .

Are you a healthcare professional?  This website is for healthcare professionals only. To continue, please confirm that you are a healthcare professional below.

We use cookies  responsibly to ensure that we give you the best experience on our website. If you continue without changing your browser settings, we’ll assume that you are happy to receive all cookies on this website.  Read about how we use cookies .

• Publications
• Conferences & Events
• Professional Learning
• Science Standards
• Awards & Competitions
• Daily Do Lesson Plans
• Free Resources
• American Rescue Plan
• For Preservice Teachers
• NCCSTS Case Collection
• Partner Jobs in Education
• Interactive eBooks+
• Digital Catalog
• Regional Product Representatives
• e-Newsletters
• Bestselling Books
• Latest Books
• Popular Book Series
• Prospective Authors
• Web Seminars
• Exhibits & Sponsorship
• Conference Reviewers
• National Conference • Denver 24
• Leaders Institute 2024
• National Conference • New Orleans 24
• Submit a Proposal
• Latest Resources
• Professional Learning Units & Courses
• For Districts
• Online Course Providers
• Schools & Districts
• College Professors & Students
• The Standards
• Teachers and Admin
• eCYBERMISSION
• Toshiba/NSTA ExploraVision
• Junior Science & Humanities Symposium
• Teaching Awards
• Climate Change
• Earth & Space Science
• New Science Teachers
• Early Childhood
• Middle School
• High School
• Postsecondary
• Informal Education
• Journal Articles
• Lesson Plans
• e-newsletters
• Science & Children
• Science Scope
• The Science Teacher
• Journal of College Sci. Teaching
• Connected Science Learning
• NSTA Reports
• Next-Gen Navigator
• Science Update
• Teacher Tip Tuesday
• Trans. Sci. Learning

MyNSTA Community

• My Collections

A Case of Diabetes Insipidus

By David F. Dean (rr)

Share Start a Discussion

“Amanda Richards,” a 20-year-old junior in college, is majoring in biology and hopes to be a pediatrician one day. For about a month, she has been waking up frequently at night to go to the bathroom. Most recently, she has noticed that she needs to go to the bathroom during the day more often, almost hourly. Students read about these symptoms and then answer a set of directed questions designed to teach facts and principles of physiology using reference books, textbooks, the Internet, and each other as sources of information. The case has been used in a sophomore-level course in human anatomy and physiology as well as in senior-level course in general physiology.

Download Case

Date Posted

• Learn about the similarities and dissimilarities between diabetes insipidus and diabetes mellitus.
• Understand the basic differences between the four types of diabetes insipidus.
• Be able to define and describe excessive thirst and urination in adults.
• Understand the methods by which diabetes insipidus is diagnosed and treated.
• Learn about other conditions which produce symptoms similar to those produced by diabetes insipidus.
• Be able to describe the physiological effects of antidiuretic hormone other than the maintenance of body water balance.

Pituitary diabetes insipidus; diabetic; antidiuretic hormone; ADH; vasopressin; osmoreceptors; osmolarity; polyuria; polydipsia; supraoptic nuclei; kidney function

Subject Headings

EDUCATIONAL LEVEL

Undergraduate lower division, Undergraduate upper division

TOPICAL AREAS

TYPE/METHODS

Teaching Notes & Answer Key

Teaching notes.

Case teaching notes are protected and access to them is limited to paid subscribed instructors. To become a paid subscriber, purchase a subscription here .

Teaching notes are intended to help teachers select and adopt a case. They typically include a summary of the case, teaching objectives, information about the intended audience, details about how the case may be taught, and a list of references and resources.

Download Notes

Answer Keys are protected and access to them is limited to paid subscribed instructors. To become a paid subscriber, purchase a subscription here .

Download Answer Key

Materials & Media

Supplemental materials, you may also like.

Web Seminar

Join us on Thursday, June 13, 2024, from 7:00 PM to 8:00 PM ET, to learn about the science and technology of firefighting. Wildfires have become an e...

Join us on Thursday, October 10, 2024, from 7:00 to 8:00 PM ET, for a Science Update web seminar presented by NOAA about climate science and marine sa...

• Open access
• Published: 18 April 2024

The predictive power of data: machine learning analysis for Covid-19 mortality based on personal, clinical, preclinical, and laboratory variables in a case–control study

• Maryam Seyedtabib   ORCID: orcid.org/0000-0003-1599-9374 1 ,
• Roya Najafi-Vosough   ORCID: orcid.org/0000-0003-2871-5748 2 &
• Naser Kamyari   ORCID: orcid.org/0000-0001-6245-5447 3  

BMC Infectious Diseases volume  24 , Article number:  411 ( 2024 ) Cite this article

95 Accesses

1 Altmetric

Metrics details

Background and purpose

The COVID-19 pandemic has presented unprecedented public health challenges worldwide. Understanding the factors contributing to COVID-19 mortality is critical for effective management and intervention strategies. This study aims to unlock the predictive power of data collected from personal, clinical, preclinical, and laboratory variables through machine learning (ML) analyses.

A retrospective study was conducted in 2022 in a large hospital in Abadan, Iran. Data were collected and categorized into demographic, clinical, comorbid, treatment, initial vital signs, symptoms, and laboratory test groups. The collected data were subjected to ML analysis to identify predictive factors associated with COVID-19 mortality. Five algorithms were used to analyze the data set and derive the latent predictive power of the variables by the shapely additive explanation values.

Results highlight key factors associated with COVID-19 mortality, including age, comorbidities (hypertension, diabetes), specific treatments (antibiotics, remdesivir, favipiravir, vitamin zinc), and clinical indicators (heart rate, respiratory rate, temperature). Notably, specific symptoms (productive cough, dyspnea, delirium) and laboratory values (D-dimer, ESR) also play a critical role in predicting outcomes. This study highlights the importance of feature selection and the impact of data quantity and quality on model performance.

This study highlights the potential of ML analysis to improve the accuracy of COVID-19 mortality prediction and emphasizes the need for a comprehensive approach that considers multiple feature categories. It highlights the critical role of data quality and quantity in improving model performance and contributes to our understanding of the multifaceted factors that influence COVID-19 outcomes.

Peer Review reports

Introduction

The World Health Organization (WHO) has declared COVID-19 a global pandemic in March 2020 [ 1 ]. The first cases of SARSCoV-2, a new severe acute respiratory syndrome coronavirus, were detected in Wuhan, China, and rapidly spread to become a global public health problem [ 2 ]. The clinical presentation and symptoms of COVID-19 may be similar to those of Middle East Respiratory Syndrome (MERS) and Severe Acute Respiratory Syndrome (SARS), however the rate of spread is higher [ 3 ]. By December 31, 2022, the pandemic had caused more than 729 million cases and nearly 6.7 million deaths (0.92%) were confirmed in 219 countries worldwide [ 4 ]. For many countries, figuring out what measures to take to prevent death or serious illness is a major challenge. Due to the complexity of transmission and the lack of proven treatments, COVID-19 is a major challenge worldwide [ 5 , 6 ]. In middle- and low-income countries, the situation is even more catastrophic due to high illiteracy rates, a very poor health care system, and lack of intensive care units [ 5 ]. In addition, understanding the factors contributing to COVID-19 mortality is critical for effective management and intervention strategies [ 6 ].

Numerous studies have shown several factors associated with COVID-19 outcomes, including socioeconomic, environmental, individual demographic, and health factors [ 7 , 8 , 9 ]. Risk factors for COVID -19 mortality vary by study and population studied [ 10 ]. Age [ 11 , 12 ], comorbidities such as hypertension, cardiovascular disease, diabetes, and COPD [ 13 , 14 , 15 ], sex [ 13 ], race/ethnicity [ 11 ], dementia, and neurologic disease [ 16 , 17 ], are some of the factors associated with COVID-19 mortality. Laboratory factors such as elevated levels of inflammatory markers, lymphopenia, elevated creatinine levels, and ALT are also associated with COVID-19 mortality [ 5 , 18 ]. Understanding these multiple risk factors is critical to accurately diagnose and treat COVID-19 patients.

Accurate diagnosis and treatment of the disease requires a comprehensive assessment that considers a variety of factors. These factors include personal factors such as medical history, lifestyle, and genetics; clinical factors such as observations on physical examinations and physician reports; preclinical factors such as early detection through screening or surveillance; laboratory factors such as results of diagnostic tests and medical imaging; and patient-reported signs and symptoms. However, the variety of characteristics associated with COVID-19 makes it difficult for physicians to accurately classify COVID-19 patients during the pandemic.

In today's digital transformation era, machine learning plays a vital role in various industries, including healthcare, where substantial data is generated daily [ 19 , 20 , 21 ]. Numerous studies have explored machine learning (ML) and explainable artificial intelligence (AI) in predicting COVID-19 prognosis and diagnosis [ 22 , 23 , 24 , 25 ]. Chadaga et al. have developed decision support systems and triage prediction systems using clinical markers and biomarkers [ 22 , 23 ]. Similarly, Khanna et al. have developed a ML and explainable AI system for COVID-19 triage prediction [ 24 ]. Zoabi has also made contributions in this field, developing ML models that predict COVID-19 test results with high accuracy based on a small number of features such as gender, age, contact with an infected person and initial clinical symptoms [ 25 ]. These studies emphasize the potential of ML and explainable AI to improve COVID-19 prediction and diagnosis. Nonetheless, the efficacy of ML algorithms heavily relies on the quality and quantity of data utilized for training. Recent research has indicated that deep learning algorithms' performance can be significantly enhanced compared to traditional ML methods by increasing the volume of data used [ 26 ]. However, it is crucial to acknowledge that the impact of data volume on model performance can vary based on data characteristics and experimental setup, highlighting the need for careful consideration and analysis when selecting data for model training. While the studies emphasize the importance of features in training ML algorithms for COVID-19 prediction and diagnosis, additional research is required on methods to enhance the interpretability of features.

Therefore, the primary aim of this study is to identify the key factors associated with mortality in COVID -19 patients admitted to hospitals in Abadan, Iran. For this purpose, seven categories of factors were selected, including demographic, clinical and conditions, comorbidities, treatments, initial vital signs, symptoms, and laboratory tests, and machine learning algorithms were employed. The predictive power of the data was assessed using 139 predictor variables across seven feature sets. Our next goal is to improve the interpretability of the extracted important features. To achieve this goal, we will utilize the innovative SHAP analysis, which illustrates the impact of features through a diagram.

Materials and methods

Study population and data collection.

Using data from the COVID-19 hospital-based registry database, a retrospective study was conducted from April 2020 to December 2022 at Ayatollah Talleghani Hospital (a COVID‑19 referral center) in Abadan City, Iran.

A total of 14,938 patients were initially screened for eligibility for the study. Of these, 9509 patients were excluded because their transcriptase polymerase chain reaction (RT-PCR) test results were negative or unspecified. The exclusion of patients due to incomplete or missing data is a common issue in medical research, particularly in the use of electronic medical records (EMRs) [ 27 ]. In addition, 1623 patients were excluded because their medical records contained more than 70% incomplete or missing data. In addition, patients younger than 18 years were not included in the study. The criterion for excluding 1623 patients due to "70% incomplete or missing data" means that the medical records of these patients did not contain at least 30% of the data required for a meaningful analysis. This threshold was set to ensure that the dataset used for the study contained a sufficient amount of complete and reliable information to draw accurate conclusions. Incomplete or missing data in a medical record may relate to key variables such as patient demographics, symptoms, lab results, treatment information, outcomes, or other data points important to the research. Insufficient data can affect the validity and reliability of study results and lead to potential bias or inaccuracies in the findings. It is important to exclude such incomplete records to maintain the quality and integrity of the research findings and to ensure that the conclusions drawn are based on robust and reliable data. After these exclusions, 3806 patients remained. Of these patients, 474 died due to COVID -19, while the remaining 3332 patients recovered and were included in the control group. To obtain a balanced sample, the control group was selected with a propensity score matching (PSM). The PSM refers to a statistical technique used to create a balanced comparison group by matching individuals in the control group (in this case, the survived group) with individuals in the case group (in this case, the deceased group) based on their propensity scores. In this study, the propensity scores for each person represented the probability of death (coded as a binary outcome; survived = 0, deceased = 1) calculated from a set of covariates (demographic factors) using the matchit function from the MatchIt library. Two individuals, one from the deceased group and one from the survived group, are considered matched if the difference between their propensity scores is small. Non-matching participants are discarded. The matching aims to reduce bias by making the distribution of observed characteristics similar between groups, which ultimately improves the comparability of groups in observational studies [ 28 ]. In total, the study included 1063 COVID-19 patients who belonged to either the deceased group (case = 474) or the survived group (control = 589) (Fig.  1 ).

Flowchart describing the process of patient selection

In the COVID‑19 hospital‑based registry database, one hundred forty primary features in eight main classes including patient’s demographics (eight features), clinical and conditions features (16 features), comorbidities (18 features), treatment (17 features), initial vital sign (14 features), symptoms during hospitalization (31 features), laboratory results (35 features), and an output (0 for survived and 1 for deceased) was recorded for COVID-19 patients. The main features included in the hospital-based COVID-19 registry database are provided in Appendix Table  1 .

To ensure the accuracy of the recorded information, discharged patients or their relatives were called and asked to review some of the recorded information (demographic information, symptoms, and medical history). Clinical symptoms and vital signs were referenced to the first day of hospitalization (at admission). Laboratory test results were also referenced to the patient’s first blood sample at the time of hospitalization.

The study analyzed 140 variables in patients' records, normalizing continuous variables and creating a binary feature to categorize patients based on outcomes. To address the issue of an imbalanced dataset, the Synthetic Minority Over-sampling Technique (SMOTE) was utilized. Some classes were combined to simplify variables. For missing data, an imputation technique was applied, assuming a random distribution [ 29 ]. Little's MCAR test was performed with the naniar package to assess whether missing data in a dataset is missing completely at random (MCAR) [ 30 ]. The null hypothesis in this test is that the data are MCAR, and the test statistic is a chi-square value.

The Ethics Committee of Abadan University of Medical Science approved the research protocol (No. IR.ABADANUMS.REC.1401.095).

Predictor variables

All data were collected in eight categories, including demographic, clinical and conditions, comorbidities, treatment, initial vital signs, symptoms, and laboratory tests in medical records, for a total of 140 variables.

The "Demographics" category encompasses eight features, three of which are binary variables and five of which are categorical. The "Clinical Conditions" category includes 16 features, comprising one quantitative variable, 12 binary variables, and five categorical features. " Comorbidities ", " Treatment ", and " Symptoms " each have 18, 17, and 30 binary features, respectively. Also, there is one quantitative variable in symptoms category. The "Initial Vital Signs" category features 11 quantitative variables, two binary variables, and one categorical variable. Finally, the "Laboratory Tests" category comprises 35 features, with 33 being quantitative, one categorical, and one binary (Appendix Table  1 ).

Outcome variable

The primary outcome variable was mortality, with December 31, 2022, as the last date of follow‐up. The feature shows the class variable, which is binary. For any patient in the survivor group, the outcome is 0; otherwise, it is 1. In this study, 44.59% ( n  = 474) of the samples were in the deceased group and were labeled 1.

Data balancing

In case–control studies, it is common to have unequal size groups since cases are typically fewer than controls [ 31 ]. However, in case–control studies with equal sizes, data balancing may not be necessary for ML algorithms [ 32 ]. When using ML algorithms, data balancing is generally important when there is an imbalance between classes, i.e., when one class has significantly fewer observations than the other [ 33 ]. In such cases, balancing can improve the performance of the algorithm by reducing the bias in favor of the majority class [ 34 ]. For case–control studies of the same size, the balance of the classes has already been reached and balancing may not be necessary. However, it is always recommended to evaluate the performance of the ML algorithm with the given data set to determine the need for data balancing. This is because unbalanced case–control ratios can cause inflated type I error rates and deflated type I error rates in balanced studies [ 35 ].

Feature selection

Feature selection is about selecting important variables from a large dataset to be used in a ML model to achieve better performance and efficiency. Another goal of feature selection is to reduce computational effort by eliminating irrelevant or redundant features [ 36 , 37 ]. Before generating predictions, it is important to perform feature selection to improve the accuracy of clinical decisions and reduce errors [ 37 ]. To identify the best predictors, researchers often compare the effectiveness of different feature selection methods. In this study, we used five common methods, including Decision Tree (DT), eXtreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), Naïve Bayes (NB), and Random Forest (RF), to select relevant features for predicting mortality of COVID -19 patients. To avoid overfitting, we performed ten-fold cross-validation when training our dataset. This approach may help ensure that our model is optimized for accurate predictions of health status in COVID -19 patients.

Model development, evaluation, and clarity

In this study, the predictive models were developed with five ML algorithms, including DT, XGBoost, SVM, NB, and RF, using the R programming language (v4.3.1) and its packages [ 38 ]. We used cross-validation (CV) to tune the hyperparameters of our models based on the training subset of the dataset. For training and evaluating our ML models, we used a common technique called tenfold cross validation [ 39 ]. The primary training dataset was divided into ten folding, each containing 10% of the total data, using a technique called stratified random sampling. For each of the 30% of the data, a ML model was built and trained on the remaining 70% of the data. The performance of the model was then evaluated on the 30%-fold sample. This process was repeated 100 times with different training and test combinations, and the average performance was reported.

Performance measures include sensitivity (recall), specificity, accuracy, F1-score, and the area under the receiver operating characteristics curve (AUC ROC). Sensitivity is defined as TP / (TP + FN), whereas specificity is TN / (TN + FP). F1-score is defined as the harmonic mean of Precision and Recall with equal weight, where Precision equals TP + TN / total. Also, AUC refers to the area under the ROC curve. In the evaluation of ML techniques, values were classified as poor if below 50%, ok if between 50 and 80%, good if between 80 and 90%, and very good if greater than 90%. These criteria are commonly used in reporting model evaluations [ 40 , 41 ].

Finally, the shapely additive explanation (SHAP) method was used to provide clarity and understanding of the models. SHAP uses cooperative game theory to determine how each feature contributes to the prediction of ML models. This approach allows the computation of the contribution of each feature to model performance [ 42 , 43 ]. For this purpose, the package shapr was used, which includes a modified iteration of the kernel SHAP approach that takes into account the interdependence of the features when computing the Shapley values [ 44 ].

Patient characteristics

Table 1 shows the baseline characteristics of patients infected with COVID-19, including demographic data such as age and sex and other factors such as occupation, place of residence, marital status, education level, BMI, and season of admission. A total of 1063 adult patients (≥ 18 years) were enrolled in the study, of whom 589 (55.41%) survived and 474 (44.59%) died. Analysis showed that age was significantly different between the two groups, with a mean age of 54.70 ± 15.60 in the survivor group versus 65.53 ± 15.18 in the deceased group ( P  < 0.001). There was also a significant association between age and survival, with a higher proportion of patients aged < 40 years in the survivor group (77.0%) than in the deceased group (23.0%) ( P  < 0.001). No significant differences were found between the two groups in terms of sex, occupation, place of residence, marital status, and time of admission. However, there was a significant association between educational level and survival, with a lower proportion of patients with a college degree in the deceased group (37.2%) than in the survivor group (62.8%) ( P  = 0.017). BMI also differed significantly between the two groups, with the proportion of patients with a BMI > 30 (kg/cm 2 ) being higher in the deceased group (56.5%) than in the survivor group (43.5%) ( P  < 0.001).

Clinical and conditions

Important insights into the various clinical and condition characteristics associated with COVID-19 infection outcomes provides in Table  2 . The results show that patients who survived the infection had a significantly shorter hospitalization time (2.20 ± 1.63 days) compared to those who died (4.05 ± 3.10 days) ( P  < 0.001). Patients who were admitted as elective cases had a higher survival rate (84.6%) compared to those who were admitted as urgent (61.3%) or emergency (47.4%) cases. There were no significant differences with regard to the number of infections or family infection history. However, patients who had a history of travel had a lower decease rate (40.1%).

A significantly higher proportion of deceased patients had cases requiring CPR (54.7% vs. 45.3%). Patients who had underlying medical conditions had a significantly lower survival rate (38.3%), with hyperlipidemia being the most prevalent condition (18.7%). Patients who had a history of alcohol consumption (12.5%), transplantation (30.0%), chemotropic (21.4%) or special drug use (0.0%), and immunosuppressive drug use (30.0%) also had a lower survival rate. Pregnant patients (44.4%) had similar survival outcomes compared to non-pregnant patients (55.6%). Patients who were recent or current smokers (36.4%) also had a significantly lower survival rate.

Comorbidities

Table 3 summarizes the comorbidity characteristics of COVID-19 infected patients. Out of 1063 patients, 54.84% had comorbidities. Chi-Square tests for individual comorbidities showed that most of them had a significant association with COVID-19 outcomes, with P -values less than 0.05. Among the various comorbidities, hypertension (HTN) and diabetes mellitus (DM) were the most prevalent, with 12% and 11.5% of patients having these conditions, respectively. The highest fatality rates were observed among patients with cardiovascular disease (95.5%), chronic kidney disease (62.5%), gastrointestinal (GI) (93.3%), and liver diseases (73.3%). Conversely, patients with neurology comorbidities had the lowest fatality rate (0%). These results highlight the significant role of comorbidities in COVID-19 outcomes and emphasize the need for special attention to be paid to patients with pre-existing health conditions.

The treatment characteristics of the COVID-19 patients and the resulting outcomes are shown in Table  4 . The table shows the frequency of patients who received different types of medications or therapies during their treatment. According to the results, the use of antibiotics (35.1%), remdesivir (29.6%), favipiravir (36.0%), and Vitamin zinc (33.5%) was significantly associated with a lower mortality rate ( P  < 0.001), suggesting that these medications may have a positive impact on patient outcomes. On the other hand, the use of Heparin (66.1%), Insulin (82.6%), Antifungal (89.6%), ACE inhibitors (78.1%), and Angiotensin II Receptor Blockers (ARB) (83.8%) was significantly associated with increased mortality ( P  < 0.001), suggesting that these medications may have a negative effect on the patient's outcome. Also, It seems that taking hydroxychloroquine (51.0%) is associated with a worse outcome at lower significance ( P  = 0.022). The use of Atrovent, Corticosteroids and Non-Steroidal Anti-Inflammatory Drugs (NSAIDs) did not show a significant association with survival or mortality rates. Similarly, the use of Intravenous Immunoglobulin (IVIg), Vitamin C, Vitamin D, and Diuretic did not show a significant association with the patient’s outcome.

Initial vital signs

Table 5 provides initial vital sign characteristics of COVID-19 patients, including heart rate, respiratory rate, temperature, blood pressure, oxygen therapy, and radiography test result. The findings shows that deceased patients had higher HR (83.03 bpm vs. 76.14 bpm, P  < 0.001), lower RR (11.40 bpm vs. 16.25 bpm, P  < 0.001), higher temperature (37.43 °C vs. 36.91 °C, P  < 0.001), higher SBP (128.16 mmHg vs. 123.33 mmHg, P  < 0.001), and higher O 2 requirements (invasive: 75.0% vs. 25.0%, P  < 0.001) compared to the survived patients. Additionally, deceased patients had higher MAP (99.35 mmHg vs. 96.08 mmHg, P  = 0.005), and lower SPO 2 percentage (81.29% vs. 91.95%, P  < 0.001) compared to the survived patients. Furthermore, deceased patients had higher PEEP levels (5.83 cmH2O vs. 0.69 cmH2O, P  < 0.001), higher FiO2 levels (51.43% vs. 8.97%, P  < 0.001), and more frequent bilateral pneumonia (63.0% vs. 37.0%, P  < 0.001) compared to the survived patients. There appears to be no relationship between diastolic blood pressure and treatment outcome (83.44 mmHg vs. 85.61 mmHg).

Table 6 provides information on the symptoms of patients infected with COVID-19 by survival outcome. The table also shows the frequency of symptoms among patients. The most common symptom reported by patients was fever, which occurred in 67.0% of surviving and deceased patients. Dyspnea and nonproductive cough were the second and third most common symptoms, reported by 40.4% and 29.3% of the total sample, respectively. Other common symptoms listed in the Table were malodor (28.7%), dyspepsia (28.4%), and myalgia (25.6%).

The P -values reported in the table show that some symptoms are significantly associated with death, including productive cough, dyspnea, sore throat, headache, delirium, olfactory symptoms, dyspepsia, nausea, vomiting, sepsis, respiratory failure, heart failure, MODS, coagulopathy, secondary infection, stroke, acidosis, and admission to the intensive care unit. Surviving and deceased patients also differed significantly in the average number of days spent in the ICU. There was no significant association between patient outcomes and symptoms such as nonproductive cough, chills, diarrhea, chest pain, and hyperglycemia.

Laboratory tests

Table 7 shows the laboratory values of COVID-19 patients with the average values of the different laboratory results. The results show that the deceased patients had significantly lower levels of red blood cells (3.78 × 106/µL vs. 5.01 × 106/µL), hemoglobin (11.22 g/dL vs. 14.10 g/dL), and hematocrit (34.10% vs. 42.46%), whereas basophils and white blood cells did not differ significantly between the two groups. The percentage of neutrophils (65.59% vs. 62.58%) and monocytes (4.34% vs. 3.93%) was significantly higher in deceased patients, while the percentage of lymphocytes and eosinophils did not differ significantly between the two groups. In addition, deceased patients had higher levels of certain biomarkers, including D-dimer (1.347 mgFEU/L vs. 0.155 mgFEU/L), lactate dehydrogenase (174.61 U/L vs. 128.48 U/L), aspartate aminotransferase (93.09 U/L vs. 39.63 U/L), alanine aminotransferase (74.48 U/L vs. 28.70 U/L), alkaline phosphatase (119.51 IU/L vs. 81.34 IU/L), creatine phosphokinase-MB (4.65 IU/L vs. 3.33 IU/L), and positive troponin I (56.5% vs. 43.5%). The proportion of patients with positive C-reactive protein was also higher in the deceased group.

Other laboratory values with statistically significant differences between the two groups ( P  < 0.001) were INR, ESR, BUN, Cr, Na, K, P, PLT, TSH, T3, and T4. The surviving patients generally had lower values in these laboratory characteristics than the deceased patients.

Model performance and evaluation

Five ML algorithms, namely DT, XGBoost, SVM, NB, and RF, were used in this study to build mortality prediction models COVID -19. The models were based on the optimal feature set selected in a previous step and were trained on the same data set. The effectiveness of the models was evaluated by calculating sensitivity, specificity, accuracy, F1 score, and AUC metrics. Table 8 shows the results of this performance evaluation. The average values are expressed from the test set as the mean (standard deviation).

The results show that the performance of the models varies widely in the different feature categories. The Laboratory Tests category achieved the highest performance, with all models scoring 100% in all metrics. The Symptoms and initial Vital Signs categories also show high performance, with XGBoost achieving the highest accuracy of 98.03% and DT achieving the highest sensitivity of 92.79%.

The Clinical and Conditions category also showed high performance, with all models showing accuracy above 91%. XGBoost achieved the highest sensitivity and specificity of 92.74% and 92.96%, respectively. In contrast, the Demographics category showed the lowest performance, with all models achieving less than 66.5% accuracy.

In summary, the results suggest that certain feature categories may be more useful than others in predicting mortality from COVID-19 and that some ML models may perform better than others depending on the feature category used.

Feature importance

SHapley Additive exPlanations (SHAP) values indicate the importance or contribution of each feature in predicting model output. These values help to understand the influence and importance of each feature on the model's decision-making process.

In Fig.  2 , the mean absolute SHAP values are shown to depict global feature importance. Figure  2 shows the contribution of each feature within its respective group as calculated by the XGBoost prediction model using SHAP. According to the SHAP method, the features that had the greatest impact on predicting COVID-19 mortality were, in descending order: D-dimer, CPR, PEEP, underlying disease, ESR, antifungal treatment, PaO2, age, dyspnea, and nausea.

Feature importance based on SHAP-values. The mean absolute SHAP values are depicted, to illustrate global feature importance. The SHAP values change in the spectrum from dark (higher) to light (lower) color

On the other hand, Fig.  3 presents the local explanation summary that indicates the direction of the relationship between a variable and COVID-19 outcome. As shown in Fig.  3 (I to VII), older age and very low BMI were the two demographic factors with the greatest impact on model outcome, followed by clinical factors such as higher CPR, hospitalization, and hyperlipidemia. Higher mortality rates were associated with patients who smoked and had traveled in the past 14 days. Patients with underlying diseases, especially HTN, died more frequently. In contrast, the use of remdesivir, Vit Zn, and favipiravir is associated with lower mortality. Initial vital signs such as high PEEP, low PaO2 and RR had the greatest impact, as did symptoms such as dyspnea, MODS, sore throat and LOC. A higher risk of mortality is observed in patients with higher D-dimer levels and ESR as the most consequential laboratory tests, followed by K, AST and CPK-MB.

The SHAP-based feature importance of all categories (I to VII) for COVID‑19 mortality prediction, calculated with the XGBoost model. The local explanatory summary shows the direction of the relationship between a feature and patient outcome. Positive SHAP values indicate death, whereas negative SHAP values indicate survival. As the color scale shows, higher values are blue while lower values are orenge

Using the feature types listed in Appendix Table  1 , Fig.  4 shows that the performance of ML algorithms can be improved by increasing the number of features used in training, especially in distinguishing between symptoms, comorbidities, and treatments. In addition, the amount and quality of data used for training can significantly affect algorithm performance, with laboratory tests being more informative than initial vital signs. Regarding the influence of features, quantitative features tend to have a more positive effect on performance than qualitative features; clinical conditions tend to be more informative than demographic data. Thus, both the amount of data and the type of features used have a significant impact on the performance of ML algorithms.

Association between feature sets and performance of machine learning algorithms in predicting COVID-19’s mortality

The COVID-19 pandemic has presented unprecedented public health challenges worldwide and requires a deep understanding of the factors contributing to COVID-19 mortality to enable effective management and intervention. This study used machine learning analysis to uncover the predictive power of an extensive dataset that includes wide range of personal, clinical, preclinical, and laboratory variables associated with COVID-19 mortality.

This study confirms previous research on COVID-19 outcomes that highlighted age as a significant predictor of mortality [ 45 , 46 , 47 ], along with comorbidities such as hypertension and diabetes [ 48 , 49 ]. Underlying conditions such as cardiovascular and renal disease also contribute to mortality risk [ 50 , 51 ].

Regarding treatment, antibiotics, remdesivir, favipiravir, and vitamin zinc are associated with lower mortality [ 52 , 53 ], whereas heparin, insulin, antifungals, ACE, and ARBs are associated with higher mortality [ 54 ]. This underscores the importance of drug choice in COVID -19 treatment.

Initial vital signs such as heart rate, respiratory rate, temperature, and oxygen therapy differ between surviving and deceased patients [ 55 ]. Deceased patients often have increased heart rate, lower respiratory rate, higher temperature, and increased oxygen requirements, which can serve as early indicators of disease severity.

Symptoms such as productive cough, dyspnea, and delirium are significantly associated with COVID-19 mortality, emphasizing the need for immediate monitoring and intervention [ 56 ]. Laboratory tests show altered hematologic and biochemical markers in deceased patients, underscoring the importance of routine laboratory monitoring in COVID-19 patients [ 57 , 58 ].

The ML algorithms were used in the study to predict mortality COVID-19 based on these multilayered variables. XGBoost and Random Forest performed better than other algorithms and had high recall, specificity, accuracy, F1 score, and AUC. This highlights the potential of ML, particularly the XGBoost algorithm, in improving prediction accuracy for COVID-19 mortality [ 59 ]. The study also highlighted the importance of drug choice in treatment and the potential of ML algorithms, particularly XGBoost, in improving prediction accuracy. However, the study's findings differ from those of Moulaei [ 60 ], Nopour [ 61 ], and Mehraeen [ 62 ] in terms of the best-performing ML algorithm and the most influential variables. While Moulaei [ 60 ] found that the random forest algorithm had the best performance, Nopour [ 61 ] and Ikemura [ 63 ] identified the artificial neural network and stacked ensemble models, respectively, as the most effective. Additionally, the most influential variables in predicting mortality varied across the studies, with Moulaei [ 60 ] highlighting dyspnea, ICU admission, and oxygen therapy, and Ikemura [ 63 ] identifying systolic and diastolic blood pressure, age, and other biomarkers. These differences may be attributed to variations in the datasets, feature selection, and model training.

However, it is important to note that the choice of algorithm should be tailored to the specific dataset and research question. In addition, the results suggest that a comprehensive approach that incorporates different feature categories may lead to more accurate prediction of COVID-19 mortality. In general, the results suggest that the performance of ML models is influenced by the number and type of features in each category. While some models consistently perform well across different categories (e.g., XGBoost), others perform better for specific types of features (e.g., SVM for Demographics).

Analysis of the importance of characteristics using SHAP values revealed critical factors affecting model results. D-dimer values, CPR, PEEP, underlying diseases, and ESR emerged as the most important features, highlighting the importance of these variables in predicting COVID-19 mortality. These results provide valuable insights into the underlying mechanisms and risk factors associated with severe COVID-19 outcomes.

The types of features used in ML models fall into two broad categories: quantitative (numerical) and qualitative (binary or categorical). The performance of ML methods can vary depending on the type of features used. Some algorithms work better with quantitative features, while others work better with qualitative features. For example, decision trees and random forests work well with both types of features [ 64 ], while neural networks often work better with quantitative features [ 65 , 66 ]. Accordingly, we consider these levels for the features under study to better assess the impact of the data.

The success of ML algorithms depends largely on the quality and quantity of the data on which they are trained [ 67 , 68 , 69 ]. Recent research, including the 2021 study by Sarker IH. [ 26 ], has shown that a larger amount of data can significantly improve the performance of deep learning algorithms compared to traditional machine learning techniques. However, it should be noted that the effect of data size on model performance depends on several factors, such as data characteristics and experimental design. This underscores the importance of carefully and judiciously selecting data for training.

Limitations

One of the limitations of this study is that it relies on data collected from a single hospital in Abadan, Iran. The data may not be representative of the diversity of COVID -19 cases in different regions, and there may be differences in data quality and completeness. In addition, retrospectively collected data may have biases and inaccuracies. Although the study included a substantial number of COVID -19 patients, the sample size may still limit the generalizability of the results, especially for less common subgroups or certain demographic characteristics.

Future works

Future studies could adopt a multi-center approach to improve the scope and depth of research on COVID-19 outcomes. This could include working with multiple hospitals in different regions of Iran to ensure a more diverse and representative sample. By conducting prospective studies, researchers can collect data in real time, which reduces the biases associated with retrospective data collection and increases the reliability of the results. Increasing sample size, conducting longitudinal studies to track patient progression, and implementing quality assurance measures are critical to improving generalizability, understanding long-term effects, and ensuring data accuracy in future research efforts. Collectively, these strategies aim to address the limitations of individual studies and make an important contribution to a more comprehensive understanding of COVID-19 outcomes in different populations and settings.

Conclusions

In summary, this study demonstrates the potential of ML algorithms in predicting COVID-19 mortality based on a comprehensive set of features. In addition, the interpretability of the models using SHAP-based feature importance, which revealed the variables strongly correlated with mortality. This study highlights the power of data-driven approaches in addressing critical public health challenges such as the COVID-19 pandemic. The results suggest that the performance of ML models is influenced by the number and type of features in each feature set. These findings may be a valuable resource for health professionals to identify high-risk patients COVID-19 and allocate resources effectively.

Availability of data and materials

The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.

Abbreviations

World Health Organization

Middle east respiratory syndrome

Severe acute respiratory syndrome

Reverse transcription polymerase chain reaction

Propensity score matching

Synthetic minority over-sampling technique

Missing completely at random

Decision tree

EXtreme gradient boosting

Support vector machine

Naïve bayes

Random forest

Cross-validation

True positive

True negative

False positive

False negative

• Machine learning

Artificial Intelligence

Shapely additive explanation

Cardiopulmonary Resuscitation

Hypertension

Diabetes mellitus

Cardiovascular disease

Chronic Kidney disease

Chronic obstructive pulmonary disease

Human immunodeficiency virus

Hepatitis B virus

Such as influenza, pneumonia, asthma, bronchitis, and chronic obstructive airways disease

Gastrointestinal

Such as epilepsy, learning disabilities, neuromuscular disorders, autism, ADD, brain tumors, and cerebral palsy

Such as fatty liver disease and cirrhosis

Blood disease

Skin diseases

Mental disorders

Intravenous immunoglobulin

Non-steroidal anti-Inflammatory drugs

Angiotensin converting enzyme inhibitors

Angiotensin II receptor blockers

Beats per minute

Respiratory rate

Temperatures

Systolic blood pressure

Diastolic blood pressure

Mean arterial pressure

Oxygen saturation

Partial pressure of oxygen in the alveoli

Positive end-expiratory pressure

Fraction of inspired oxygen

Radiography (X-ray) test result

Smell disorders

Indigestion

Level of consciousness

Multiple organ dysfunction syndrome

Coughing up blood; Coagulopathy: bleeding disorder

High blood glucose

Intensive care unit

Red blood cell

White blood cell

Low-density lipoprotein

High-density lipoprotein

Prothrombin time

Partial thromboplastin time

International normalized ratio

Erythrocyte sedimentation rate

C-reactive-protein

Lactate dehydrogenase

Aspartate aminotransferase

Alanine aminotransferase

Alkaline phosphatase

Creatine phosphokinase-MB

Blood urea nitrogen

Thyroid stimulating hormone

Triiodothyronine

Coronavirus disease (COVID-19) pandemic. Available from: https://www.who.int/europe/emergencies/situations/covid-19 . [cited 2023 Sep 5].

Moolla I, Hiilamo H. Health system characteristics and COVID-19 performance in high-income countries. BMC Health Serv Res. 2023;23(1):1–14. https://doi.org/10.1186/s12913-023-09206-z . [cited 2023 Sep 5].

Article   Google Scholar  

Peeri NC, Shrestha N, Rahman MS, Zaki R, Tan Z, Bibi S, et al. The SARS, MERS and novel coronavirus (COVID-19) epidemics, the newest and biggest global health threats: what lessons have we learned? Int J Epidemiol. 2020;49(3):717–26.

Article   PubMed   Google Scholar  

WHO Coronavirus (COVID-19) Dashboard | WHO Coronavirus (COVID-19) Dashboard With Vaccination Data. Available from: https://covid19.who.int/ . [cited 2023 Sep 5].

Dessie ZG, Zewotir T. Mortality-related risk factors of COVID-19: a systematic review and meta-analysis of 42 studies and 423,117 patients. BMC Infect Dis. 2021;21(1):1–28. https://doi.org/10.1186/s12879-021-06536-3 . [cited 2023 Sep 5].

Article   CAS   Google Scholar  

Wong ELY, Ho KF, Wong SYS, Cheung AWL, Yau PSY, Dong D, et al. Views on Workplace Policies and its Impact on Health-Related Quality of Life During Coronavirus Disease (COVID-19) Pandemic: Cross-Sectional Survey of Employees. Int J Heal Policy Manag. 2022;11(3):344–53. Available from: https://www.ijhpm.com/article_3879.html .

Google Scholar  

Drefahl S, Wallace M, Mussino E, Aradhya S, Kolk M, Brandén M, et al. A population-based cohort study of socio-demographic risk factors for COVID-19 deaths in Sweden. Nat Commun. 2020;11(1):5097.

Article   CAS   PubMed   PubMed Central   Google Scholar  

Islam N, Khunti K, Dambha-Miller H, Kawachi I, Marmot M. COVID-19 mortality: a complex interplay of sex, gender and ethnicity. Eur J Public Health. 2020;30(5):847–8.

Sarmadi M, Marufi N, Moghaddam VK. Association of COVID-19 global distribution and environmental and demographic factors: An updated three-month study. Environ Res. 2020;188:109748.

Aghazadeh-Attari J, Mohebbi I, Mansorian B, Ahmadzadeh J, Mirza-Aghazadeh-Attari M, Mobaraki K, et al. Epidemiological factors and worldwide pattern of Middle East respiratory syndrome coronavirus from 2013 to 2016. Int J Gen Med. 2018;11:121–5.

Risk of COVID-19-Related Mortality. Available from: https://www.cdc.gov/coronavirus/2019-ncov/science/data-review/risk.html . [cited 2023 Aug 26].

Bhaskaran K, Bacon S, Evans SJW, Bates CJ, Rentsch CT, MacKenna B, et al. Factors associated with deaths due to COVID-19 versus other causes: population-based cohort analysis of UK primary care data and linked national death registrations within the OpenSAFELY platform. Lancet Reg Heal. 2021;6:100-9.

Dessie ZG, Zewotir T. Mortality-related risk factors of COVID-19: a systematic review and meta-analysis of 42 studies and 423,117 patients. BMC Infect Dis. 2021;21(1):855. https://doi.org/10.1186/s12879-021-06536-3 .

Talebi SS, Hosseinzadeh A, Zare F, Daliri S, JamaliAtergeleh H, Khosravi A, et al. Risk Factors Associated with Mortality in COVID-19 Patient’s: Survival Analysis. Iran J Public Health. 2022;51(3):652–8.

PubMed   PubMed Central   Google Scholar  

Singh J, Alam A, Samal J, Maeurer M, Ehtesham NZ, Chakaya J, et al. Role of multiple factors likely contributing to severity-mortality of COVID-19. Infect Genet Evol J Mol Epidemiol Evol Genet Infect Dis. 2021;96:105101.

CAS   Google Scholar  

Bhaskaran K, Bacon S, Evans SJ, Bates CJ, Rentsch CT, MacKenna B, et al. Factors associated with deaths due to COVID-19 versus other causes: population-based cohort analysis of UK primary care data and linked national death registrations within the OpenSAFELY platform. Lancet Reg Heal - Eur. 2021;6:100109. Available from:  https://www.pmc/articles/PMC8106239/ . [cited 2023 Aug 26].

Ge E, Li Y, Wu S, Candido E, Wei X. Association of pre-existing comorbidities with mortality and disease severity among 167,500 individuals with COVID-19 in Canada: A population-based cohort study. PLoS One. 2021;16(10):e0258154. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0258154 . [cited 2023 Aug 26].

Tian S, Liu H, Liao M, Wu Y, Yang C, Cai Y, et al. Analysis of mortality in patients with COVID-19: clinical and laboratory parameters. Open Forum Infect Dis. 2020;7(5). Available from:  https://dx.doi.org/10.1093/ofid/ofaa152 . [cited 2023 Aug 26].

Rashidi HH, Tran N, Albahra S, Dang LT. Machine learning in health care and laboratory medicine: General overview of supervised learning and Auto-ML. Int J Lab Hematol. 2021;43:15–22.

Najafi-Vosough R, Faradmal J, Hosseini SK, Moghimbeigi A, Mahjub H. Predicting hospital readmission in heart failure patients in Iran: a comparison of various machine learning methods. Healthc Inform Res. 2021;27(4):307–14.

Article   PubMed   PubMed Central   Google Scholar  

Alanazi A. Using machine learning for healthcare challenges and opportunities. Informatics Med Unlocked. 2022;100924:1–5.

Chadaga K, Prabhu S, Sampathila N, Chadaga R, Umakanth S, Bhat D, et al. Explainable artificial intelligence approaches for COVID-19 prognosis prediction using clinical markers. Sci Rep. 2024;14(1):1783.

Chadaga K, Prabhu S, Bhat V, Sampathila N, Umakanth S, Chadaga R, et al. An explainable multi-class decision support framework to predict COVID-19 prognosis utilizing biomarkers. Cogent Eng. 2023;10(2):2272361.

Khanna VV, Chadaga K, Sampathila N, Prabhu S, Chadaga R. A machine learning and explainable artificial intelligence triage-prediction system for COVID-19. Decis Anal J. 2023;100246:1–14.

Zoabi Y, Deri-Rozov S, Shomron N. Machine learning-based prediction of COVID-19 diagnosis based on symptoms. npj Digit Med. 2021;4(1):1–5.

IH Sarker 2021 Machine Learning: Algorithms, Real-World Applications and Research Directions SN Comput Sci. 2 3 160 Available from: https://doi.org/10.1007/s42979-021-00592-x .

Jones JA, Farnell B. Missing and Incomplete Data Reduces the Value of General Practice Electronic Medical Records as Data Sources in Research. Aust J Prim Health. 2007;13(1):74–80. Available from: https://www.publish.csiro.au/py/py07010 . [cited 2023 Dec 16].

Austin PC. An Introduction to Propensity Score Methods for Reducing the Effects of Confounding in Observational Studies. Multivariate Behav Res. 2011;46(3):399–424.

Torjusen H, Lieblein G, Næs T, Haugen M, Meltzer HM, Brantsæter AL. Food patterns and dietary quality associated with organic food consumption during pregnancy; Data from a large cohort of pregnant women in Norway. BMC Public Health. 2012;12(1):1–11.

Little RJA. A test of missing completely at random for multivariate data with missing values. J Am Stat Assoc. 1988;83(404):1198–202.

Tenny S, Kerndt CC, Hoffman MR. Case Control Studies. Encycl Pharm Pract Clin Pharm Vol 1-3 [Internet]. 2023;1–3:V2-356-V2-366. [cited 2024 Apr 14] Available from: https://www.ncbi.nlm.nih.gov/books/NBK448143/ .

Stanfill B, Reehl S, Bramer L, Nakayasu ES, Rich SS, Metz TO, et al. Extending Classification Algorithms to Case-Control Studies. Biomed Eng Comput Biol. 2019;10:117959721985895. Available from: https://www.pmc/articles/PMC6630079/ .[cited 2023 Sep 3].

Mulugeta G, Zewotir T, Tegegne AS, Juhar LH, Muleta MB. Classification of imbalanced data using machine learning algorithms to predict the risk of renal graft failures in Ethiopia. BMC Med Inform Decis Mak. 2023;23(1):1–17. https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-023-02185-5 . [cited 2023 Sep 3].

Sadeghi S, Khalili D, Ramezankhani A, Mansournia MA, Parsaeian M. Diabetes mellitus risk prediction in the presence of class imbalance using flexible machine learning methods. BMC Med Inform Decis Mak. 2022;22(1):36. https://doi.org/10.1186/s12911-022-01775-z .

Zhou W, Nielsen JB, Fritsche LG, Dey R, Gabrielsen ME, Wolford BN, et al. Efficiently controlling for case-control imbalance and sample relatedness in large-scale genetic association studies. Nat Genet. 2018;50(9):1335. Available from:  https://www.pmc/articles/PMC6119127/ . [cited 2023 Sep 3].

Miao J, Niu L. A Survey on Feature Selection. Procedia Comput Sci. 2016;91(1):919–26.

Remeseiro B, Bolon-Canedo V. A review of feature selection methods in medical applications. Comput Biol Med. 2019;112:103375.

Article   CAS   PubMed   Google Scholar  

R Studio Team. A language and environment for statistical computing. R Found Stat Comput. 2021;1.

Training Sets, Test Sets, and 10-fold Cross-validation - KDnuggets. Available from: https://www.kdnuggets.com/2018/01/training-test-sets-cross-validation.html . [cited 2023 Sep 4].

Hossin M, Sulaiman MN. A review on evaluation metrics for data classification evaluations. Int J data Min Knowl Manag Process. 2015;5(2):1.

Seyedtabib M, Kamyari N. Predicting polypharmacy in half a million adults in the Iranian population: comparison of machine learning algorithms. BMC Med Inform Decis Mak. 2023;23(1):84. https://doi.org/10.1186/s12911-023-02177-5 .

Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2017;30:4765–74.

Greenwell B. Fastshap: Fast approximate shapley values. Man R Packag v0 05. 2020;9–12.  https://www.CRANR-projectorg/package=fastshap . Last accessed.

Aas K, Jullum M, Løland A. Explaining individual predictions when features are dependent: More accurate approximations to Shapley values. Artif Intell. 2021;298:103502.

Mesas AE, Cavero-Redondo I, Álvarez-Bueno C, Sarriá Cabrera MA, de Maffei Andrade S, Sequí-Dominguez I, et al. Predictors of in-hospital COVID-19 mortality: A comprehensive systematic review and meta-analysis exploring differences by age, sex and health conditions. PLoS One. 2020;15(11):e0241742.

Yanez ND, Weiss NS, Romand J-A, Treggiari MM. COVID-19 mortality risk for older men and women. BMC Public Health. 2020;20(1):1–7.

Sasson I. Age and COVID-19 mortality. Demogr Res. 2021;44:379–96.

Huang I, Lim MA, Pranata R. Diabetes mellitus is associated with increased mortality and severity of disease in COVID-19 pneumonia–a systematic review, meta-analysis, and meta-regression. Diabetes Metab Syndr Clin Res Rev. 2020;14(4):395–403.

Albitar O, Ballouze R, Ooi JP, Ghadzi SMS. Risk factors for mortality among COVID-19 patients. Diabetes Res Clin Pract. 2020;166:108293.

Di Castelnuovo A, Bonaccio M, Costanzo S, Gialluisi A, Antinori A, Berselli N, et al. Common cardiovascular risk factors and in-hospital mortality in 3,894 patients with COVID-19: survival analysis and machine learning-based findings from the multicentre Italian CORIST Study. Nutr Metab Cardiovasc Dis. 2020;30(11):1899–913.

Ssentongo P, Ssentongo AE, Heilbrunn ES, Ba DM, Chinchilli VM. Association of cardiovascular disease and 10 other pre-existing comorbidities with COVID-19 mortality: A systematic review and meta-analysis. PLoS ONE. 2020;15(8):e0238215.

Beran A, Mhanna M, Srour O, Ayesh H, Stewart JM, Hjouj M, et al. Clinical significance of micronutrient supplements in patients with coronavirus disease 2019: A comprehensive systematic review and meta-analysis. Clin Nutr ESPEN. 2022;48:167–77.

Perveen RA, Nasir M, Murshed M, Nazneen R, Ahmad SN. Remdesivir and favipiravir changes hepato-renal profile in COVID-19 patients: a cross sectional observation in Bangladesh. Int J Med Sci Clin Inven. 2021;8(1):5196–201.

El-Arif G, Khazaal S, Farhat A, Harb J, Annweiler C, Wu Y, et al. Angiotensin II Type I Receptor (AT1R): the gate towards COVID-19-associated diseases. Molecules. 2022;27(7):2048.

Ikram AS, Pillay S. Admission vital signs as predictors of COVID-19 mortality: a retrospective cross-sectional study. BMC Emerg Med. 2022;22(1):1–10.

Martí-Pastor A, Moreno-Perez O, Lobato-Martínez E, Valero-Sempere F, Amo-Lozano A, Martínez-García M-Á, et al. Association between Clinical Frailty Scale (CFS) and clinical presentation and outcomes in older inpatients with COVID-19. BMC Geriatr. 2023;23(1):1.

Lippi G, Plebani M. Laboratory abnormalities in patients with COVID-2019 infection. Clin Chem Lab Med. 2020;58(7):1131–4.

Naghashpour M, Ghiassian H, Mobarak S, Adelipour M, Piri M, Seyedtabib M, et al. Profiling serum levels of glutathione reductase and interleukin-10 in positive and negative-PCR COVID-19 outpatients: A comparative study from southwestern Iran. J Med Virol. 2022;94(4):1457–64.

Sharifi-Kia A, Nahvijou A, Sheikhtaheri A. Machine learning-based mortality prediction models for smoker COVID-19 patients. BMC Med Inform Decis Mak. 2023;23(1):1–15.

Moulaei K, Shanbehzadeh M, Mohammadi-Taghiabad Z, Kazemi-Arpanahi H. Comparing machine learning algorithms for predicting COVID-19 mortality. BMC Med Inform Decis Mak. 2022;22(1):2. https://doi.org/10.1186/s12911-021-01742-0 .

Nopour R, Erfannia L, Mehrabi N, Mashoufi M, Mahdavi A, Shanbehzadeh M. Comparison of Two Statistical Models for Predicting Mortality in COVID-19 Patients in Iran. Shiraz E-Medical J 2022 236 [Internet]. 2022;23(6):119172. [cited 2024 Apr 14] Available from: https://brieflands.com/articles/semj-119172 .

Mehraeen E, Karimi A, Barzegary A, Vahedi F, Afsahi AM, Dadras O, et al. Predictors of mortality in patients with COVID-19–a systematic review. Eur J Integr Med. 2020;40:101226.

Ikemura K, Bellin E, Yagi Y, Billett H, Saada M, Simone K, et al. Using Automated Machine Learning to Predict the Mortality of Patients With COVID-19: Prediction Model Development Study. J Med Internet Res [Internet]. 2021;23(2):e23458. Available from: https://www.jmir.org/2021/2/e23458 .

Breiman L. Random forests. Mach Learn. 2001;45:5–32.

Hinton G, Srivastava N, Swersky K. Neural networks for machine learning lecture 6a overview of mini-batch gradient descent. Cited on. 2012;14(8):2.

Zheng A, Casari A. Feature Engineering for Machine Learning: Principles and Techniques for Data Scientists. O’Reilly [Internet]. 2018;218. [cited 2024 Apr 14] Available from: https://www.amazon.com/Feature-Engineering-Machine-Learning-Principles/dp/1491953241 .

Adamson AS, Smith A. Machine Learning and Health Care Disparities in Dermatology. JAMA Dermatology. 2018;154(11):1247–8. Available from:  https://jamanetwork.com/journals/jamadermatology/fullarticle/2688587 . [cited 2023 Sep 15].

Kavakiotis I, Tsave O, Salifoglou A, Maglaveras N, Vlahavas I, Chouvarda I. Machine Learning and Data Mining Methods in Diabetes Research. Comput Struct Biotechnol J. 2017;1(15):104–16.

Schmidt J, Marques MRG, Botti S, Marques MAL. Recent advances and applications of machine learning in solid-state materials science. Comput Mater. 2019;5(1):83. https://doi.org/10.1038/s41524-019-0221-0 .

Download references

Acknowledgements

We thank the Research Deputy of the Abadan University of Medical Sciences for financially supporting this project.

Summary points

∙ How can datasets improve mortality prediction using ML models for COVID-19 patients?

∙ In order, quantity and quality variables have more effect on the model performances.

∙ Intelligent techniques such as SHAP analysis can be used to improve the interpretability of features in ML algorithms.

∙ Well-structured data are critical to help health professionals identify at-risk patients and improve pandemic outcomes.

This research was supported by grant No. 1456 from the Abadan University of Medical Sciences. However, the funding source did not influence the study design, data collection, analysis and interpretation, report writing, or decision to publish the article.

Author information

Authors and affiliations.

Department of Biostatistics and Epidemiology, School of Health, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran

Maryam Seyedtabib

Research Center for Health Sciences, Hamadan University of Medical Sciences, Hamadan, Iran

Roya Najafi-Vosough

Department of Biostatistics and Epidemiology, School of Health, Abadan University of Medical Sciences, Abadan, Iran

Naser Kamyari

You can also search for this author in PubMed   Google Scholar

Contributions

MS: Conceptualization, Methodology, Validation, Formal analysis, Investigation, Resources, Data curation, Writing–original draft, writing—review & editing, Visualization, Project administration. RNV: Conceptualization, Data curation, Formal analysis, Investigation, Writing–original draft, writing—review & editing. NK: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing–original draft, writing—review & editing, Visualization, Supervision.

Corresponding author

Correspondence to Naser Kamyari .

Ethics declarations

Ethics approval and consent to participate.

This study was approved by the Research Ethics Committee (REC) of Abadan University of Medical Sciences under the ID number IR.ABADANUMS.REC.1401.095. Methods used complied with all relevant ethical guidelines and regulations. The Ethics Committee of Abadan University of Medical Sciences waived the requirement for written informed consent from study participants.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Supplementary material 1., rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Seyedtabib, M., Najafi-Vosough, R. & Kamyari, N. The predictive power of data: machine learning analysis for Covid-19 mortality based on personal, clinical, preclinical, and laboratory variables in a case–control study. BMC Infect Dis 24 , 411 (2024). https://doi.org/10.1186/s12879-024-09298-w

Download citation

Received : 22 December 2023

Accepted : 05 April 2024

Published : 18 April 2024

DOI : https://doi.org/10.1186/s12879-024-09298-w

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Predictive model
• Coronavirus disease
• Data quality
• Performance

BMC Infectious Diseases

ISSN: 1471-2334

• Submission enquiries: [email protected]
• General enquiries: [email protected]