Enhancing Model Interpretability and Accuracy for Disease Progression Prediction via Phenotype-Based Patient Similarity Learning

TL;DR

This paper introduces a phenotype-based patient similarity learning method using non-negative matrix factorization to improve disease prediction accuracy and interpretability from longitudinal EHR data.

Contribution

It proposes a novel approach to learn patient similarity features as phenotypes, enhancing model interpretability and predictive performance in disease prognosis.

Findings

Phenotypes are coherent and disease-indicative.

Improved prediction accuracy for CLL diagnosis.

Enhanced interpretability of patient similarities.

Abstract

Models have been proposed to extract temporal patterns from longitudinal electronic health records (EHR) for clinical predictive models. However, the common relations among patients (e.g., receiving the same medical treatments) were rarely considered. In this paper, we propose to learn patient similarity features as phenotypes from the aggregated patient-medical service matrix using non-negative matrix factorization. On real-world medical claim data, we show that the learned phenotypes are coherent within each group, and also explanatory and indicative of targeted diseases. We conducted experiments to predict the diagnoses for Chronic Lymphocytic Leukemia (CLL) patients. Results show that the phenotype-based similarity features can improve prediction over multiple baselines, including logistic regression, random forest, convolutional neural network, and more.