A Review of Challenges and Opportunities in Machine Learning for Health

TL;DR

This paper reviews the unique challenges of applying machine learning to electronic health records and discusses opportunities for advancing healthcare through ML innovations.

Contribution

It provides a comprehensive overview of the specific hurdles in ML for healthcare and suggests directions for future research and development.

Findings

EHR data often has poor disease labels

Multiple endotypes complicate disease modeling

Healthy individuals are underrepresented in datasets

Abstract

Modern electronic health records (EHRs) provide data to answer clinically meaningful questions. The growing data in EHRs makes healthcare ripe for the use of machine learning. However, learning in a clinical setting presents unique challenges that complicate the use of common machine learning methodologies. For example, diseases in EHRs are poorly labeled, conditions can encompass multiple underlying endotypes, and healthy individuals are underrepresented. This article serves as a primer to illuminate these challenges and highlights opportunities for members of the machine learning community to contribute to healthcare.