OpenResearchAlpha

Biology Methods and Protocols · 13 Nov 2026

Large-scale data extraction from clinical notes reveals the lean-mass fraction of weight-loss in patients treated with GLP-1 medicines

Karthik Murugadoss, A J Venkatakrishnan, Venky Soundararajanh-index 19

0
Citations
no database records one yet
0
Citations in 2026
so far
19
Leading author's h-index
Venky Soundararajan, in QAI's scholar index
0
References
works it cites, from open citation data

Citations by database

Each database indexes a different set of journals, preprints and books, so they are shown side by side rather than blended.

  • OpenCitations0
  • Crossref0

Citations per year

The current year is still counting.

  • 2026 so far0

Abstract

Abstract Body-composition measurements are often recorded in the free text of electronic health record (EHR) notes, limiting large-scale assessment of the composition of weight change. We evaluated a large language model (LLM)-based pipeline for extracting and harmonizing these measurements and characterizing the lean-mass proportion of weight change. Among 670,422 adults initiating semaglutide or tirzepatide, the pipeline yielded 158,573 harmonized lean body mass (LBM) measurements for 29,154 patients; 7,965 had baseline and follow-up measurements. Manual review of a sample of 53 notes found correct values and units in all 32 notes with extracted LBM values and correct dates in 93.8%, with no missed values in 21 screened negatives. Repeat extraction showed 95%–97% agreement for values, units, and dates. Across a wider clinical-note corpus, analyses of 1,907 weight-loss-associated medications, procedures, and conditions distinguished relatively lean-sparing loss with bariatric surgery (lean-mass proportion, 0.24), semaglutide (0.27), and tirzepatide (0.26) from lean-depleting loss with catabolic illness (0.70–0.74). Analyses of 427 weight-gain-associated entities distinguished fat-predominant from lean- or fluid-predominant gain. Matched comparisons generally placed incretin therapies between lifestyle counseling and bariatric surgery in weight and LBM loss. Comparing tirzepatide with semaglutide, the covariate-adjusted 12-month difference in LBM change was −1.9 percentage points (95% CI, −3.6 to − 0.3), attenuating to − 0.1 (95% CI, −1.6 to 1.4) after adjustment for concurrent weight change. Among 465 matched pairs, the 12-month lean-mass proportion of weight lost did not differ significantly (0.24 vs 0.22; difference, 0.02; 95% CI, −0.04 to 0.09). These observational findings support scalable assessment of body composition from routine EHR notes and suggest that tirzepatide’s greater LBM loss accompanies greater weight loss.

What the data shows

  • No database records a citation yet, as is usual for a paper this new.
  • Venky Soundararajan has the highest h-index among the authors (19).

Graph

This paper in the middle, its authors and their most-cited papers below, the papers it cites to the left and the papers citing it to the right. The timeline lays every paper out by year.

Citing paper shares an authorAuthor without a profileSize shows citations, or h-index for authors

Select a node for its details. Drag to pan, scroll to zoom, drag a node to move it.

Start with

Authors (3)

Each author's standing in QAI's scholar index: the works their ORCID iD is attached to, and for anyone whose ORCID record names a lab OpenResearch follows, their arXiv preprints matched by name and a shared co-author. Names are as printed on the paper.

ProfileMost-cited paper

Cited by 0 papers

Who cites this paper, from open citation data, with Crossref's record of each; the 100 newest when there are more.

0 shown
No citing papers for this filter.

References (0)

What it cites, from open citation data, with Crossref's record of each.

No references in the open citation data yet.
Large-scale data extraction from clinical notes reveals the lean-mass fraction of weight-loss in patients treated with GLP-1 medicines - QAI OpenResearch