![]() Smoking, alanine aminotransferase, and platelet count were found to be the three lowest predictors of COVID-19 mortality. After performing the feature selection, out of 38 features, dyspnea, ICU admission, and oxygen therapy were found as the top three predictors. 664) and the median age was 57.25 years old (interquartile 18–100). ![]() The study participants were 1500 patients the number of men was found to be higher than that of women (836 vs. Finally, to assess the models’ performance, the metrics derived from the confusion matrix were calculated. Afterwards, several ML algorithms were trained to predict COVID-19 mortality. In this study, after feature selection, based on the confirmed predictors, information about 1500 eligible patients (1386 survivors and 144 deaths) obtained from the registry of Ayatollah Taleghani Hospital, Abadan city, Iran, was extracted. So, our study aimed to compare several ML algorithms to predict the COVID-19 mortality using the patient’s data at the first time of admission and choose the best performing algorithm as a predictive tool for decision-making. Machine learning (ML) algorithms can be used as a potential solution for predicting mortality in COVID-19 hospitalized patients. The coronavirus disease (COVID-19) hospitalized patients are always at risk of death.
0 Comments
Leave a Reply. |