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

2019/09/26 by Yue Wang, Tong Wu, Wang, Yue +5
Biochemistry, Genetics and Molecular Biology · Computer Science · Health Professions · #Applications (stat.AP) #Artificial Intelligence in Healthcare #Biomedical Text Mining and Ontologies #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #Machine Learning in Healthcare

paper · pdf · doi:10.48550/arxiv.1909.11913

openalex publication_date 2019/09/26 · openalex created_date 2019/10/03 · openalex updated_date 2026/07/28

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.

Citations

• Adam: A Method for Stochastic Optimization
• Learning to Diagnose with LSTM Recurrent Neural Networks
• Deep Survival Analysis
• Wide & Deep Learning for Recommender Systems
• Rare Disease Detection by Sequence Modeling with Generative Adversarial Networks
• RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism

Related

• Predicting Treatment Initiation from Clinical Time Series Data via Graph-Augmented Time-Sensitive Model
• Measuring Patient Similarities via a Deep Architecture with Medical Concept Embedding
• Learning Patient Representations from Text
• Hybrid Feature- and Similarity-Based Models for Joint Prediction and Interpretation
• Temporal Phenotyping using Deep Predictive Clustering of Disease Progression