Improving Clinical Decision Support through Interpretable Machine Learning and Error Handling in Electronic Health Records

TL;DR

This paper introduces Trust-MAPS, a novel algorithm that incorporates clinical domain knowledge into machine learning models for electronic health records, improving error handling, interpretability, and predictive accuracy in sepsis detection.

Contribution

Trust-MAPS translates clinical knowledge into mathematical constraints, enabling error detection, interpretability, and enhanced predictive performance in clinical ML applications.

Findings

Achieved AUROC of 0.91 for early sepsis prediction, a 15% improvement over baseline.

Demonstrated that trust-scores are clinically meaningful features.

First method to mathematically encode clinical domain knowledge into ML models for EHR data.

Abstract

The objective of this work is to develop an Electronic Medical Record (EMR) data processing tool that confers clinical context to Machine Learning (ML) algorithms for error handling, bias mitigation and interpretability. We present Trust-MAPS, an algorithm that translates clinical domain knowledge into high-dimensional, mixed-integer programming models that capture physiological and biological constraints on clinical measurements. EMR data is projected onto this constrained space, effectively bringing outliers to fall within a physiologically feasible range. We then compute the distance of each data point from the constrained space modeling healthy physiology to quantify deviation from the norm. These distances, termed "trust-scores," are integrated into the feature space for downstream ML applications. We demonstrate the utility of Trust-MAPS by training a binary classifier for early sepsis prediction on data from the 2019 PhysioNet Computing in Cardiology Challenge, using the XGBoost algorithm and applying SMOTE for overcoming class-imbalance. The Trust-MAPS framework shows desirable behavior in handling potential errors and boosting predictive performance. We achieve an AUROC of 0.91 (0.89, 0.92 : 95% CI) for predicting sepsis 6 hours before onset - a marked 15% improvement over a baseline model trained without Trust-MAPS. Trust-scores emerge as clinically meaningful features that not only boost predictive performance for clinical decision support tasks, but also lend interpretability to ML models. This work is the first to translate clinical domain knowledge into mathematical constraints, model cross-vital dependencies, and identify aberrations in high-dimensional medical data. Our method allows for error handling in EMR, and confers interpretability and superior predictive power to models trained for clinical decision support.