A Bayesian approach for unadjudicated events in cardiovascular disease cohort studies

TL;DR

This paper introduces a Bayesian method that leverages related cohort data and machine learning to improve the accuracy of cardiovascular event classification in epidemiological studies, addressing ICD-9 code misclassification issues.

Contribution

It develops a novel Bayesian joint modeling approach combined with Bayesian additive regression trees to estimate true adjudicated events from ICD-9 coded data.

Findings

Method accurately predicts adjudicated events in simulations.

Applied to ARIC data, it improves event classification accuracy.

Demonstrates robustness in handling ICD-9 code misclassification.

Abstract

An important issue in joint modelling for outcomes and longitudinal risk factors in cohort studies is to have an accurate assessment of events. Events determined based on ICD-9 codes can be very inaccurate, in particular for cardiovascular disease (CVD) where ICD-9 codes may overestimate the frequency of CVD. Motivated by the lack of adjudicated events in the Established Populations for Epidemiologic Studies of the Elderly (EPESE) cohort, we develop methods that use a related cohort Atherosclerosis Risk in Communities (ARIC), with both ICD-9 code events and adjudicated events, to create a posterior predictive distribution of adjudicated events. The methods are based on the construction of flexible Bayesian joint models combined with a Bayesian additive regression trees to directly address the ICD-9 misclassification. We assessed the performance of our approach by simulation study and applied to ARIC data.