We aimed to create the prediction model of in-hospital mortality using machine learning methods for patients with COVID-19 treated with steroid and remdesivir.
Study design and setting:
We reviewed 1,571 hospitalized patients with laboratory confirmed COVID-19 from the Mount Sinai Health System treated with both steroid and remdesivir. The important variables associated with in-hospital mortality were identified using LASSO and SHAP through light gradient boosting model (GBM). The data before February 17th , 2021 (N=769) was randomly split into training and testing datasets; 80% vs. 20%, respectively. Light GBM models were created with train data and area under the curves (AUCs) were calculated. Additionally, we calculated AUC with the data between February 17th , 2021 and March 30th , 2021 (N=802).
Of the 1,571 patients admitted due to COVID-19, 331 (21.1%) died during hospitalization. Through LASSO and SHAP, we selected 6 important variables; age, hypertension, oxygen saturation, blood urea nitrogen, intensive care unit admission and endotracheal intubation. AUCs using training and testing datasets derived from the data before February 17th , 2021 were 0.871/0.911. Additionally, light GBM model has high predictability for the latest data (AUC: 0.881). (covid-risk-model.herokuapp.com/).
High-value prediction model was created to estimate in-hospital mortality for COVID-19 patients treated with steroid and remdesivir. This article is protected by copyright. All rights reserved.
COVID-19; New York; machine learning; mortality; remdesivir; steroid.