Outcome Identification in Electronic Health Records using Predictions from an Enriched Dirichlet Process Mixture

Project Title Outcome Identification in Electronic Health Records using Predictions from an Enriched Dirichlet Process Mixture
Date
Wednesday, June 6, 2018
Location
Description

This manuscript proposes a novel semiparametric model for the joint distribution of a continuous longitudinal outcome and the baseline covariates using an enriched Dirichlet process (EDP) prior. The authors use their model to predict laboratory values indicative of diabetes for each individual and assess incidence of suspected diabetes from the predicted dataset. This model also serves as a functional clustering algorithm in which subjects are clustered into groups with similar longitudinal trajectories of the outcome over time.

Authors

Bret Zeldow, James Flory, Alisa Stephens-Shields, Marsha Raebel, Jason Roy

Related Links