Electronic Health Record Phenotyping with Internally Assessable Performance (PhIAP) using Anchor-Positive and Unlabeled Patients

TL;DR

This paper introduces a novel semi-automated EHR phenotyping method that accurately models disease status using anchor-positive and unlabeled data, eliminating the need for extensive manual labeling.

Contribution

It develops a maximum likelihood approach leveraging anchor-positive and unlabeled data for accurate phenotyping without validation sets, including new statistical methods for prevalence and performance estimation.

Findings

Achieved high discrimination with an AUC of 0.99 in real data

Generated accurate prevalence and performance estimates in simulations

Demonstrated robustness to minor model misfit

Abstract

Building phenotype models using electronic health record (EHR) data conventionally requires manually labeled cases and controls. Assigning labels is labor intensive and, for some phenotypes, identifying gold-standard controls is prohibitive. To facilitate comprehensive clinical decision support and research, we sought to develop an accurate EHR phenotyping approach that assesses its performance without a validation set. Our framework relies on specifying a random subset of cases, potentially using an anchor variable that has excellent positive predictive value and sensitivity that is independent of predictors. We developed a novel maximum likelihood approach that efficiently leverages data from anchor-positive and unlabeled patients to develop logistic regression phenotyping models. Additionally, we described novel statistical methods for estimating phenotyping prevalence and assessing model calibration and predictive performance measures. Theoretical and simulation studies indicated our method generates accurate predicted probabilities, leading to excellent discrimination and calibration, and consistent estimates of phenotype prevalence and anchor sensitivity. The method appeared robust to minor lack-of-fit and the proposed calibration assessment detected major lack-of-fit. We applied our method to EHR data to develop a preliminary model for identifying patients with primary aldosteronism, which achieved an AUC of 0.99 and PPV of 0.8. We developed novel statistical methods for accurate model development and validation with minimal manual labeling, facilitating development of scalable, transferable, semi-automated case labeling and practice-specific models. Our EHR phenotyping approach decreases labor-intensive manual phenotyping and annotation, which should enable broader model development and dissemination for EHR clinical decision support and research.