Introduction: Predicting the mortality risk of COVID-19 patients based on patient’s physiological conditions and demographic characteristics can help optimize resource consumption along with the provision of effective medical services for patients. In the current study, we aimed to develop several machine learning models to forecast the mortality risk in COVID-19 patients, evaluate their performance, and select the model with the highest predictive power.
Material and methods: We conducted a retrospective analysis of the records belonging to COVID-19 patients admitted to one of the main hospitals of Qazvin located in the northwest of Iran over 12 months period. We selected 29 variables for developing machine learning models incorporating demographic factors, physical symptoms, comorbidities, and laboratory test results. The outcome variable was mortality as a binary variable. Logistic regression analysis was conducted to identify risk factors of in-hospital death.
Results: In prediction of mortality, Ensemble demonstrated the maximum values of accuracy (0.8071, 95%CI: 0.7787, 0.8356), F1-score (0.8121 95%CI: 0.7900, 0.8341), and AUROC (0.8079, 95%CI: 0.7800, 0.8358). Including fourteen top-scored features identified by maximum relevance minimum redundancy algorithm into the subset of predictors of ensemble classifier such as BUN level, shortness of breath, seizure, disease history, fever, gender, body pain, WBC, diarrhea, sore throat, blood oxygen level, muscular pain, lack of taste and history of drug (medication) use are sufficient for this classifier to reach to its best predictive power for prediction of mortality risk of COVID-19 patients.
Conclusions: Study findings revealed that old age, lower oxygen saturation level, underlying medical conditions, shortness of breath, seizure, fever, sore throat, and body pain, besides serum BUN, WBC, and CRP levels, were significantly associated with increased mortality risk of COVID-19 patients. Machine learning algorithms can help healthcare systems by predicting and reduction of the mortality risk of COVID-19 patients.
