Related Experiment Video

Updated: Oct 1, 2025

Modeling and Evaluation of Murine Diabetic Cardiomyopathy Model
06:22

Modeling and Evaluation of Murine Diabetic Cardiomyopathy Model

Published on: November 29, 2024

788

COVID-19 mortality risk assessments for individuals with and without diabetes mellitus: Machine learning models

Heydar Khadem1, Hoda Nemat1, Mohammad R Eissa1

  • 1Department of Electronic and Electrical Engineering, University of Sheffield, UK.

Computers in Biology and Medicine
|March 7, 2022
PubMed

Insights

Machine learning models predict COVID-19 mortality risk in patients with and without diabetes mellitus. SHAP values enabled patient clustering for effective risk stratification.

Area of Science:

  • * Computational biology and bioinformatics
  • * Medical informatics and machine learning
  • * Public health and epidemiology

Background:

  • * Coronavirus disease-2019 (COVID-19) poses a significant global health threat.
  • * Diabetes mellitus (DM) is a common comorbidity that may influence COVID-19 outcomes.
  • * Accurate mortality risk prediction and stratification are crucial for managing hospitalized COVID-19 patients.

Purpose of the Study:

  • * To develop and validate machine learning models for predicting in-hospital mortality in COVID-19 patients.
  • * To compare model performance between COVID-19 patients with and without diabetes mellitus.
  • * To utilize model interpretation techniques for patient risk stratification.

Main Methods:

  • * Retrospective analysis of routinely collected clinical data from 156 COVID-19 patients with DM and 349 without DM.
  • * Development of a random forest classifier to predict COVID-19 fatality.
  • * Application of SHapley Additive exPlanations (SHAP) for model interpretability.
  • * Utilization of k-means clustering on SHAP values for patient stratification.

Main Results:

  • * The random forest model achieved high accuracy in predicting mortality for both cohorts (DM: 82%, non-DM: 80%).
  • * Area Under the Curve (AUC) values indicated good discriminative ability (DM: 80%, non-DM: 84%).
  • * SHAP analysis provided insights into global and local predictor influences, facilitating three distinct patient clusters with varying mortality rates (DM: 8%, 20%, 76%; non-DM: 2.7%, 28%, 41.9%).

Conclusions:

  • * Machine learning models, enhanced by interpretation modules, offer a functional approach to COVID-19 mortality risk prediction.
  • * SHAP-based clustering provides a valuable tool for stratifying COVID-19 patients into distinct risk groups.
  • * These methods can aid clinicians in tailoring treatment and resource allocation for hospitalized COVID-19 patients, particularly those with diabetes.

Keywords:
COVID-19Diabetes mellitusMachine learningModel interpretationRisk assessment

More Related Videos

Constructing and Visualizing Models using Mime-based Machine-learning Framework06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

928
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.2K

Related Concept Videos

Diabetes Mellitus: Type 2 and Gestational01:22

Diabetes Mellitus: Type 2 and Gestational

Type 2 diabetes, characterized by insulin resistance, arises when the insulin receptors on cells lose responsiveness to insulin, diminishing the cell's capacity to take up glucose, resulting in elevated blood glucose levels. To receive a diagnosis of Type 2 diabetes, a series of blood glucose tests are necessary to assess whether the blood glucose falls within normal parameters. If the result is out of the normal range, a patient may be diagnosed as prediabetic or diabetic, depending on the...
3.1K
Pathophysiology of Diabetes01:20

Pathophysiology of Diabetes

Diabetes mellitus is a chronic metabolic disorder characterized by hyperglycemia. The four categories of diabetes are type 1 diabetes, type 2 diabetes, other specific types of diabetes, and gestational diabetes.
Type 1 diabetes is characterized by autoimmune-mediated destruction of pancreatic β cells, with environmental factors potentially triggering this process in genetically susceptible individuals. Despite many not having a family history, certain genes increase susceptibility,...
1.5K
Diabetes Mellitus: Overview and Type I Subtype01:22

Diabetes Mellitus: Overview and Type I Subtype

Diabetes mellitus is a chronic metabolic disorder characterized by high blood glucose levels due to inadequate insulin production, insulin resistance, or both. The condition affects millions worldwide and can significantly impact their health and quality of life.
Type 1 diabetes is an autoimmune disease in which the immune system mistakenly attacks and destroys the insulin-producing beta cells in the pancreas. As a result, the body is unable to produce sufficient insulin, and individuals with...
3.4K
Diabetes: Symptoms, Diagnosis, and Complications01:15

Diabetes: Symptoms, Diagnosis, and Complications

For most patients, experiencing several weeks of polyuria, polydipsia, fatigue, and significant weight loss may indicate the presence of diabetes. Furthermore, adults displaying the phenotypic appearance of type 2 diabetes (particularly those who are obese and not initially insulin-requiring), may have islet cell autoantibodies, suggesting autoimmune-mediated β cell destruction and a diagnosis of latent autoimmune diabetes of adults (LADA). The categorization of glucose homeostasis is...
867
Diabetes: Management and Pharmacotherapy01:15

Diabetes: Management and Pharmacotherapy

The therapy for diabetes aims to alleviate hyperglycemia-related symptoms, prevent acute metabolic decompensation, and reduce chronic end-organ complications. Glycemic control is evaluated through short-term (self-monitoring, continuous glucose monitoring) and long-term (A1c, fructosamine) metrics, enabling near real-time tracking of blood glucose levels and reflecting glycemic control over specific time frames.
Insulin remains the cornerstone of treatment for most patients with type 1 and many...
427
Steps in Outbreak Investigation01:18

Steps in Outbreak Investigation

In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
243