key: cord-0960892-27xven7p
authors: Shi, Shaobo; Cao, Qiqi
title: A new mission awaits: Machine learning to predict COVID-19 related complications
date: 2022-05-08
journal: JACC: Advances
DOI: 10.1016/j.jacadv.2022.100045
sha: 654bb933737ef6198e85a9b14bb7ec72feff89ac
doc_id: 960892
cord_uid: 27xven7p

[Figure: see text]

and other related disciplines. Teams must work together to create new tools, new drugs, and new solutions to solve this urgent problem.

Risk stratification is crucially important for the hospitalized patient with COVID-19 so that treatment strategies can be planned to minimize morbidity and mortality. Previous studies on risk stratification have used traditional and interpretable modeling methods to predict mortality. In the current study, Shade et al. 2 apply machine learning techniques to create a real-time tool, named COVID-HEART, to predict adverse events (AM/CA and TE) in COVID-19 patients and to provide a continuously evolving warning system for impending events. COVID-HEART was derived from routinely acquired clinical parameters and biomarkers and achieved excellent predicting capability for the two outcomes (AM/CA and TE), with better performance in predicting AM/CA than TE. In practice, COVID-HEART comprehensively assesses the combined effects of many variables and provides a novel and accurate risk score.

Despite the encouraging findings, several issues need to be considered when developing and using these types of clinical tools. The COVID-HEART model used real-world data and the importance of raw data cleanliness is very important for any machine learning model. Although many types of clinical data were included, additional variables may be important. 

Real-Time Prediction of Cardiovascular Complications in Hospitalized Patients with COVID-19

Association of Cardiac Injury With Mortality in Hospitalized Patients With COVID-19 in Wuhan, China

Risk stratification of patients admitted to hospital with covid-19 using the ISARIC WHO Clinical Characterisation Protocol: development and validation of the 4C Mortality Score

Omicron SARS-CoV-2 variant: a new chapter in the COVID-19 pandemic