COVID-19 mortality risk assessments for individuals with and without diabetes mellitus: Machine learning models integrated with interpretation framework. (May 2022)

• Record Type: Journal Article
• Authors: Khadem, Heydar; Nemat, Hoda; Eissa, Mohammad R.; Elliott, Jackie; Benaissa, Mohammed
• Is Part Of: Computers in biology and medicine. Volume 144(2022)
• Publication Date: 2022-05
• Subjects: Machine learning -- COVID-19 -- Diabetes mellitus -- Risk assessment -- Model interpretation; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.105361
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: This research develops machine learning models equipped with interpretation modules for mortality risk prediction and stratification in cohorts of hospitalised coronavirus disease-2019 (COVID-19) patients with and without diabetes mellitus (DM). To this end, routinely collected clinical data from 156 COVID-19 patients with DM and 349 COVID-19 patients without DM were scrutinised. First, a random forest classifier forecasted in-hospital COVID-19 fatality utilising admission data for each cohort. For the DM cohort, the model predicted mortality risk with the accuracy of 82%, area under the receiver operating characteristic curve (AUC) of 80%, sensitivity of 80%, and specificity of 56%. For the non-DM cohort, the achieved accuracy, AUC, sensitivity, and specificity were 80%, 84%, 91%, and 56%, respectively. The models were then interpreted using SHapley Additive exPlanations (SHAP), which explained predictors' global and local influences on model outputs. Finally, the k-means algorithm was applied to cluster patients on their SHAP values. The algorithm demarcated patients into three clusters. Average mortality rates within the generated clusters were 8%, 20%, and 76% for the DM cohort, 2.7%, 28%, and 41.9% for the non-DM cohort, providing a functional method of risk stratification. Highlights: Cohorts of hospitalised COVID-19 patients with and without diabetes are studied. Machine learning models are designed for mortality risk assessments in each cohort. SHAP is incorporated to expand the models' transparency and knowledge discovery. SHAP clustering produces outcomes with utility in risk stratification practice. Exploitation of interpretable machine learning in COVID-19 research is promoted.