PyPheWAS Explorer: a visualization tool for exploratory analysis of phenome-disease associations. Issue 1 (3rd April 2023)

• Record Type: Journal Article
• Authors: Kerley, Cailey I; Nguyen, Tin Q; Ramadass, Karthik; Cutting, Laurie E; Landman, Bennett A; Berger, Matthew
• Is Part Of: JAMIA open. Volume 6:Issue 1(2023)
• Publication Date: 2023-04-03
• Subjects: electronic health records -- PheWAS -- ICD codes -- interactive visualization; Medical informatics -- Periodicals; 610.285
• DOI: 10.1093/jamiaopen/ooad018
• Languages: English
• ISSNs: 2574-2531

Abstract

Abstract: Objective: To enable interactive visualization of phenome-wide association studies (PheWAS) on electronic health records (EHR). Materials and Methods: Current PheWAS technologies require familiarity with command-line interfaces and lack end-to-end data visualizations. pyPheWAS Explorer allows users to examine group variables, test assumptions, design PheWAS models, and evaluate results in a streamlined graphical interface. Results: A cohort of attention deficit hyperactivity disorder (ADHD) subjects and matched non-ADHD controls is examined. pyPheWAS Explorer is used to build a PheWAS model including sex and deprivation index as covariates, and the Explorer's result visualization for this model reveals known ADHD comorbidities. Discussion: pyPheWAS Explorer may be used to rapidly investigate potentially novel EHR associations. Broader applications include deployment for clinical experts and preliminary exploration tools for institutional EHR repositories. Conclusion: pyPheWAS Explorer provides a seamless graphical interface for designing, executing, and analyzing PheWAS experiments, emphasizing exploratory analysis of regression types and covariate selection. Lay Summary: Electronic health record (EHR) data are a powerful resource that may be used to identify real-world patterns in disease progression. The phenome-wide association study (PheWAS) is an EHR analysis method, which extracts meaningful phenotypes from EHR data and looks for associations between those phenotypes and a genetic variant or medical condition of interest. Though several PheWAS tools exist, most run solely in a command-line or programming environment, making verification of model inputs and outputs challenging. We present pyPheWAS Explorer, a graphical interface, for interactively designing PheWAS experiments. The Explorer increases model transparency by providing visualizations of all demographic variables alongside the PheWAS model results. We demonstrate the utility of pyPheWAS Explorer in a case study of attention deficit hyperactivity disorder patients compared to matched controls.