Research

Mixed

Electronic health record (EHR) data collected prior to anti-obesity medication (AOM) initiation can be used to identify distinct obesity subtypes (clusters) with specific clinical comorbidities, which may inform precision medicine strategies.

Current obesity treatment often relies on BMI, which fails to predict how individuals will respond to medications. This research suggests that using detailed electronic health records (labs, vitals, diagnoses) before starting treatment can identify distinct obesity subtypes with specific health profiles. This 'deep phenotyping' approach could help doctors choose more effective, personalized treatments, moving away from a one-size-fits-all model.

ModerateSupportsMEDIUM confidence
Our analysis identified at least nine distinct clusters before AOM initiation. Five clusters show clear clinical relevance independent of traditional obesity diagnoses... These observations highlight the method's potential to uncover unique patient groups, marking an important first step in digital phenotyping.
Xiaoyang Ruan et al. · medRxiv · 2024

Why this rating

It is a proof-of-concept study using retrospective EHR data; while the cohort is large, it lacks prospective validation of treatment response by cluster.

Source

Deep phenotyping obesity using EHR data: Promise, Challenges, and Future Directions

Xiaoyang Ruan et al. · medRxiv · 2024

DOI 10.1101/2024.12.06.24318608

preprint · n=32969Cited 1×
Read the paper
DOI resolved against Crossref · corpus check 2026-06-10

This is one finding among thousands. Every one is graded and traced to its source, so you can see what the evidence actually supports. Browse the research →