Overcoming data challenges to measure whole-person health in electronic health records

2025-02-07

AI Summary

Electronic health record (EHR) data frequently suffer from missingness and measurement error, undermining robust estimation of the All-cause Longevity Index (ALI). To address this, we propose a statistically efficient and robust semiparametric maximum likelihood framework that innovatively integrates residual-guided targeted sampling validation with a clinician-informed data verification protocol—thereby jointly improving data quality and enabling principled imputation of missing values. Evaluated on 1,000 real-world EHR records, our method achieves high-accuracy ALI modeling, significantly reduces validation error rates, and successfully recovers key missing observations. Further analysis reveals a statistically significant positive association between elevated ALI and age-adjusted probability of healthcare utilization. This work establishes a generalizable methodological paradigm for whole-person health quantification using EHR data, bridging statistical rigor, clinical domain knowledge, and practical scalability.

Technology Category

• Humans and AI: Human-in-the-loop Machine Learning
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: State Estimation

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

Abstract

The allostatic load index (ALI) is a composite measure of whole-person health. Data from electronic health records (EHR) present a huge opportunity to operationalize the ALI in the learning health system, except they are prone to missingness and errors. Validation of EHR data (e.g., through chart reviews) can provide better-quality data, but realistically, only a subset of patients' data can be validated, and most protocols do not recover missing data. Using a representative sample of 1000 patients from the EHR at an extensive learning health system (100 of whom could be validated), we propose methods to design, conduct, and analyze statistically efficient and robust studies of the ALI and healthcare utilization. With semiparametric maximum likelihood estimation, we robustly incorporate all available data into statistical models. Using targeted design strategies, we examine ways to select the most informative patients for validation. Incorporating clinical expertise, we devise a novel validation protocol to promote the quality and completeness of EHR data. Validating the EHR data uncovered relatively low error rates and recovered some missing data. Through simulation studies based on preliminary data, residual sampling was identified as the most informative strategy for completing our validation study. Statistical models of partially validated data indicated higher odds of engaging in the healthcare system were associated with worse whole-person health (i.e., higher ALI), adjusting for age. Targeted validation with an enriched protocol allowed us to ensure the quality and promote the completeness of the EHR. Findings from our validation study were incorporated into analyses as we operationalize the ALI as a whole-person health measure intended to predict healthcare utilization in the academic learning health system.

Problem

• Measure whole-person health using EHR data with missingness issues
• Develop methods for efficient validation and data recovery in EHR
• Link allostatic load index to healthcare utilization statistically

Innovation

• Semiparametric maximum likelihood estimation for robust modeling
• Targeted design strategies for informative patient selection
• Novel validation protocol enhancing EHR data quality