Development and Validation of a Machine Learning Model for Prediction of Response to Corticosteroid Therapy In COVID-19 Patients

Abstract

Background: Corticosteroid has been proved to be one of the few effective treatments for COVID-19 patients. However, not all the patients were suitable for corticosteroid therapy. In this study, we aimed to propose a machine learning model to forecast the response to corticosteroid therapy in COVID-19 patients.Methods: We retrospectively collected 666 COVID-19 patients receiving corticosteroid therapy between January 27, 2020, and March 30, 2020, from two hospitals in China. The response to corticosteroid therapy was evaluated by hospitalization time, oxygen supply duration, and the outcomes of patients. Least Absolute Shrinkage and Selection Operator (LASSO) was applied for feature selection. Five machine learning algorithms were applied in the training cohort and assessed in an internal and an external validation dataset, respectively.Findings: Two (C reactive protein, lymphocyte percent) of 36 candidate immune/inflammatory features were finally used for model development. All five models displayed promising predictive performance. Notably, the ensemble model, PRCTC (prediction of response to corticosteroid therapy in COVID-19 patients), derived from Support Vector Machine (SVM), Gradient Boosted Decision Tree (GBDT), and Neural Network (NN) achieved the best performance with an area under the curve (AUC) of 0·810 (95% confidence interval [CI] 0·760–0·861) in internal validation cohort and 0·845 (95% CI 0·779–0·911) in external validation cohort to predict patients’ response to corticosteroid therapy.Interpretation: PRCTC proposed with robustness, universality, and scalability is hopeful to provide tangible and prompt clinical decision support in management of COVID-19 patients, and potentially extends to other medication prediction.Funding: Natural Science Foundation of China.Declaration of Interests: All authors declared no competing interest.Ethics Approval Statement: This study was approved by the Research Ethics Commission of Tongji Medical College, Huazhong University of Science and Technology (TJIRB20200406) with waived informed consent by the Ethics Commission mentioned above.