Learning and Predicting from Dynamic Models for COVID-19 Patient Monitoring

TL;DR

This paper discusses the challenges and methods for learning from data to improve COVID-19 patient care, emphasizing model development, communication, and continuous evaluation in a clinical setting.

Contribution

It introduces and compares prospective and retrospective statistical models for COVID-19 patient prediction, highlighting their application and validation in a real hospital cohort.

Findings

Validated models on 1,678 patients

Emphasized graphical tools for clinician understanding

Demonstrated the importance of continuous model revision

Abstract

COVID-19 has challenged health systems to learn how to learn. This paper describes the context, methods and challenges for learning to improve COVID-19 care at one academic health center. Challenges to learning include: (1) choosing a right clinical target; (2) designing methods for accurate predictions by borrowing strength from prior patients' experiences; (3) communicating the methodology to clinicians so they understand and trust it; (4) communicating the predictions to the patient at the moment of clinical decision; and (5) continuously evaluating and revising the methods so they adapt to changing patients and clinical demands. To illustrate these challenges, this paper contrasts two statistical modeling approaches - prospective longitudinal models in common use and retrospective analogues complementary in the COVID-19 context - for predicting future biomarker trajectories and major clinical events. The methods are applied to and validated on a cohort of 1,678 patients who were hospitalized with COVID-19 during the early months of the pandemic. We emphasize graphical tools to promote physician learning and inform clinical decision making.