Deep Phenotyping of Obesity: Electronic Health Record-Based Temporal Modeling Study.

Background: Obesity affects approximately 40% of adults and 15%-20% of children and adolescents in the United States, and poses significant economic and psychosocial burdens. Currently, patient responses to any single antiobesity medication (AOM) vary significantly, making obesity deep phenotyping and associated precision medicine important targets of investigation.

Objective: This study aimed to evaluate the potential of electronic health records (EHR) as a primary data source for obesity deep phenotyping. We conducted an in-depth analysis of the data elements and quality available from obesity patients prior to pharmacotherapy and applied a multimodal longitudinal deep autoencoder to investigate the feasibility, data requirements, clustering patterns, and challenges associated with EHR-based obesity deep phenotyping.

Methods: We analyzed 53,688 pre-AOM periods from 32,969 patients with obesity or overweight who underwent medium- to long-term AOM treatment. A total of 92 laboratory and vital measurements, along with 79 ICD (International Classification of Diseases)-derived clinical classifications software (CCS) codes recorded within one year prior to AOM treatment, were used to train a gated recurrent unit with decay-based longitudinal autoencoder (GRU-D-AE) to generate dense embeddings for each pre-AOM record. Principal component analysis and Gaussian mixture modeling (GMM) were applied to identify clusters.

Results: Our analysis identified at least 9 clusters, with 5 exhibiting distinct and explainable clinical relevance. Certain clusters show characteristics overlapping with phenotypes from traditional phenotyping strategy. Results from multiple training folds demonstrated stable clustering patterns in 2D space and reproducible clinical significance. However, challenges persist regarding the stability of missing data imputation across folds, maintaining consistency in input features, and effectively visualizing complex diseases in low-dimensional spaces.

Conclusions: In this proof-of-concept study, we demonstrated longitudinal EHR as a valuable resource for deep phenotyping the pre-AOM period at per patient visit level. Our analysis revealed the presence of clusters with distinct clinical significance, which could have implications in AOM treatment options. Further research using larger, independent cohorts is necessary to validate the reproducibility and clinical relevance of these clusters, uncover more detailed substructures and corresponding AOM treatment responses.