Deep learning–based CT-derived vertebral bone mineral density and metformin therapy: a longitudinal study in the Multi-Ethnic Study of Atherosclerosis
Skeletal Radiology · 2026-10 · 55 (10) · 2527-2537
DOI: 10.1007/s00256-026-05263-7 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Skeletal Radiology, online erschienen am 31.05.2026. Verfasst von Sara Momtazmanesh und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology and Radiologic Science, Johns Hopkins University, Baltimore, MD, USA. Hauptthemen laut MEDLINE: Atherosclerosis, Bone Density, Deep Learning, Hypoglycemic Agents. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NHLBI NIH HHS, U.S. Environmental Protection Agency, NCATS NIH HHS.
Abstract (Originalsprache)
OBJECTIVE: Evidence on metformin's skeletal effects remains conflicting. We emulated a target trial to evaluate associations between metformin therapy and deep learning-based CT-derived vertebral bone mineral density (vBMD). We also assessed variation across prespecified subgroups. MATERIALS AND METHODS: Within the Multi-Ethnic Study of Atherosclerosis (MESA), incident metformin users (Exams 4 and 5) were compared with propensity score-matched controls. Noncontrast chest CT scans from Exams 5 and 6 were processed using a previously validated deep learning-based vertebral segmentation and calibration pipeline to quantify trabecular vBMD from T1 to T10. Median imaging follow-up was 6.4 years. Linear mixed-effects models estimated annualized Fracture Risk Assessment Tool (FRAX) absolute vBMD change, applying inverse probability of censoring weights. Prespecified subgroup analyses examined demographic, metabolic, and inflammatory modifiers. RESULTS: Among 238 trial entries (86 metformin, 152 controls), metformin was not associated with overall vBMD change (time × treatment interaction β, 0.27 mg/cm3 per year; 95%CI, -0.07 to 0.61; p = 0.12). Substudy-specific and per-protocol estimates were consistent. Favorable associations were observed in women, body mass index (BMI) < 30 kg/m2, ASCVD risk < 0.2, hs-CRP < 2 mg/L, never-smokers, and nondrinkers. Significant effect modification was found for gender, hs-CRP, and smoking status, with borderline trends for BMI. CONCLUSIONS: Metformin use was not associated with overall CT-derived vBMD change. Subgroup analyses indicate heterogeneity of association across demographic, metabolic, and inflammatory profiles, with more favorable associations among women and participants with healthier risk profiles. Findings support metformin's skeletal safety and warrant future context-specific trials.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Radiology and Radiologic Science, Johns Hopkins University, Baltimore, MD, USA.
- Department of Radiology, University of Pennsylvania, Philadelphia, PA, USA.
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran.
- Wake Forest University School of Medicine, Winston-Salem, NC, USA.
- Department of Radiology, Madison School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA.
- Department of Medicine, Columbia University Medical Center, New York, NY, USA.
Förderung
- NHLBI NIH HHS
- U.S. Environmental Protection Agency
- NCATS NIH HHS
- NIAMS NIH HHS
- National Heart, Lung, and Blood Institute
- National Center for Advancing Translational Sciences
- National Institute of Arthritis and Musculoskeletal and Skin Diseases
Zitieren
APA
Momtazmanesh, S., Hathaway, Q. A., Jannatdoust, P., Ghotbi, E., Bancks, M. P., Bluemke, D. A., Barr, R. G., Smith, B. M., Post, W. S., Budoff, M. J., Lima, J. A. C., & Demehri, S. (2026). Deep learning–based CT-derived vertebral bone mineral density and metformin therapy: a longitudinal study in the Multi-Ethnic Study of Atherosclerosis. Skeletal Radiology, 55(10), 2527-2537. https://doi.org/10.1007/s00256-026-05263-7
Vancouver
Momtazmanesh S, Hathaway QA, Jannatdoust P, Ghotbi E, Bancks MP, Bluemke DA, et al. Deep learning–based CT-derived vertebral bone mineral density and metformin therapy: a longitudinal study in the Multi-Ethnic Study of Atherosclerosis. Skeletal Radiology. 2026;55(10):2527-2537. doi:10.1007/s00256-026-05263-7
BibTeX
@article{Momtazmanesh2026,
author = {Momtazmanesh, Sara and Hathaway, Quincy A and Jannatdoust, Payam and Ghotbi, Elena and Bancks, Michael P and Bluemke, David A and Barr, R Graham and Smith, Benjamin M and Post, Wendy S and Budoff, Matthew J and Lima, João A C and Demehri, Shadpour},
title = {Deep learning–based CT-derived vertebral bone mineral density and metformin therapy: a longitudinal study in the Multi-Ethnic Study of Atherosclerosis},
journal = {Skeletal Radiology},
year = {2026},
volume = {55},
number = {10},
pages = {2527--2537},
doi = {10.1007/s00256-026-05263-7}
}
EUVIMED