Continual Deterioration Prediction for Hospitalized COVID-19 Patients

TL;DR

This study introduces a temporal stratification approach for daily prediction of COVID-19 patient deterioration, demonstrating high accuracy and emphasizing the importance of time-varying effects of clinical variables.

Contribution

The paper proposes a novel temporal stratification method that segments data by remaining hospital stay to improve deterioration prediction accuracy.

Findings

Achieved 0.98 AUROC in predictions

Validated the time-varying effects of clinical variables

Built and evaluated prototype models using public data

Abstract

Leading up to August 2020, COVID-19 has spread to almost every country in the world, causing millions of infected and hundreds of thousands of deaths. In this paper, we first verify the assumption that clinical variables could have time-varying effects on COVID-19 outcomes. Then, we develop a temporal stratification approach to make daily predictions on patients' outcome at the end of hospital stay. Training data is segmented by the remaining length of stay, which is a proxy for the patient's overall condition. Based on this, a sequence of predictive models are built, one for each time segment. Thanks to the publicly shared data, we were able to build and evaluate prototype models. Preliminary experiments show 0.98 AUROC, 0.91 F1 score and 0.97 AUPR on continuous deterioration prediction, encouraging further development of the model as well as validations on different datasets. We also verify the key assumption which motivates our method. Clinical variables could have time-varying effects on COVID-19 outcomes. That is to say, the feature importance of a variable in the predictive model varies at different disease stages.