A Bayesian Approach to Modelling Longitudinal Data in Electronic Health Records

TL;DR

This paper introduces a Bayesian nonparametric model using ensemble of trees to effectively analyze sparse, diverse longitudinal EHR data for improved survival prediction.

Contribution

It presents a novel Bayesian ensemble tree approach that models complex variable interactions over time without predefined assumptions.

Findings

Improved survival prediction accuracy on PBC patient data.

Effective handling of sparse and diverse longitudinal data.

Demonstrated flexibility of the model in EHR analysis.

Abstract

Analyzing electronic health records (EHR) poses significant challenges because often few samples are available describing a patient's health and, when available, their information content is highly diverse. The problem we consider is how to integrate sparsely sampled longitudinal data, missing measurements informative of the underlying health status and fixed demographic information to produce estimated survival distributions updated through a patient's follow up. We propose a nonparametric probabilistic model that generates survival trajectories from an ensemble of Bayesian trees that learns variable interactions over time without specifying beforehand the longitudinal process. We show performance improvements on Primary Biliary Cirrhosis patient data.