A Review of Challenges and Opportunities in Machine Learning for Health

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.

Updated version

References in corpus (16)

• Towards A Rigorous Science of Interpretable Machine Learning
• Predicting Cardiovascular Risk Factors from Retinal Fundus Photographs using Deep Learning
• Understanding Black-box Predictions via Influence Functions
• Zero-Shot Learning Through Cross-Modal Transfer
• Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model
• Poincaré Embeddings for Learning Hierarchical Representations
• Adversarial Attacks Against Medical Deep Learning Systems
• Reliable Decision Support using Counterfactual Models
• Towards Vision-Based Smart Hospitals: A System for Tracking and Monitoring Hand Hygiene Compliance
• Feature Robustness in Non-stationary Health Records: Caveats to Deployable Model Performance in Common Clinical Machine Learning Tasks
• A Framework for Individualizing Predictions of Disease Trajectories by Exploiting Multi-Resolution Structure
• Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier
• Detecting hip fractures with radiologist-level performance using deep neural networks
• Multi-task Prediction of Disease Onsets from Longitudinal Lab Tests
• A Bayesian Nonparametric Approach for Estimating Individualized Treatment-Response Curves
• Adversarial Examples for Electrocardiograms

Cited by in corpus (24)

• What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use
• Ethical Framework for Harnessing the Power of AI in Healthcare and Beyond
• Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions
• Hurtful Words: Quantifying Biases in Clinical Contextual Word Embeddings
• ClinicalVis: Supporting Clinical Task-Focused Design Evaluation
• Beyond Ads: Sequential Decision-Making Algorithms in Law and Public Policy
• Representation Learning for Electronic Health Records
• Sex Trouble: Common pitfalls in incorporating sex/gender in medical machine learning and how to avoid them
• Semi-supervised Rare Disease Detection Using Generative Adversarial Network
• Clinically Labeled Contrastive Learning for OCT Biomarker Classification
• OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning
• A Multidatabase ExTRaction PipEline (METRE) for Facile Cross Validation in Critical Care Research
• Synthetic Observational Health Data with GANs: from slow adoption to a boom in medical research and ultimately digital twins?
• Rare Disease Detection by Sequence Modeling with Generative Adversarial Networks
• Supervised machine learning for microbiomics: bridging the gap between current and best practices
• CLAID: Closing the Loop on AI & Data Collection -- A Cross-Platform Transparent Computing Middleware Framework for Smart Edge-Cloud and Digital Biomarker Applications
• Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings
• InfoShape: Task-Based Neural Data Shaping via Mutual Information
• On the Morality of Artificial Intelligence
• AI Assisted Annotator using Reinforcement Learning
• Empirical Analysis of Zipf's Law, Power Law, and Lognormal Distributions in Medical Discharge Reports
• Causal thinking for decision making on Electronic Health Records: why and how
• Semantic coordinates analysis reveals language changes in the AI field
• Modeling Treatment Delays for Patients using Feature Label Pairs in a Time Series