Data mining for censored time-to-event data: A Bayesian network model for predicting cardiovascular risk from electronic health record data

TL;DR

This paper introduces a Bayesian network model trained on electronic health data to predict five-year cardiovascular risk, effectively handling censored data and outperforming traditional models like Cox regression.

Contribution

It presents a novel machine learning approach using Bayesian networks tailored for censored time-to-event data from electronic health records, improving prediction accuracy.

Findings

Outperforms Cox proportional hazards model in predictive accuracy.

Effectively handles right-censored data in electronic health records.

Demonstrates applicability on large U.S. healthcare system data.

Abstract

Models for predicting the risk of cardiovascular events based on individual patient characteristics are important tools for managing patient care. Most current and commonly used risk prediction models have been built from carefully selected epidemiological cohorts. However, the homogeneity and limited size of such cohorts restricts the predictive power and generalizability of these risk models to other populations. Electronic health data (EHD) from large health care systems provide access to data on large, heterogeneous, and contemporaneous patient populations. The unique features and challenges of EHD, including missing risk factor information, non-linear relationships between risk factors and cardiovascular event outcomes, and differing effects from different patient subgroups, demand novel machine learning approaches to risk model development. In this paper, we present a machine learning approach based on Bayesian networks trained on EHD to predict the probability of having a cardiovascular event within five years. In such data, event status may be unknown for some individuals as the event time is right-censored due to disenrollment and incomplete follow-up. Since many traditional data mining methods are not well-suited for such data, we describe how to modify both modelling and assessment techniques to account for censored observation times. We show that our approach can lead to better predictive performance than the Cox proportional hazards model (i.e., a regression-based approach commonly used for censored, time-to-event data) or a Bayesian network with {\em{ad hoc}} approaches to right-censoring. Our techniques are motivated by and illustrated on data from a large U.S. Midwestern health care system.