EUVIMEDEUVIMED entdecken
VergleichsstudieKohortenstudie

AI-derived bone mineral density from standard radiographs compared with DXA for fracture prediction in a 10-year real-world cohort study

Tzu-Hao Tseng, Tseng Ti Huang, Jing En Huang, Shi-Chien Tzeng, Yu-Chen Wang, Pei-Chen Tsao, Chih-Chien Hung, Chia-Che Lee, Jui-Yo Hsu, Hung-Kuan Yen, Chih-Hsing Wu, Chung-Yi Li und 2 weitere

Osteoporosis International · 2026

DOI: 10.1007/s00198-026-08100-8 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Osteoporosis International, 2026. Verfasst von Tzu-Hao Tseng und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Orthopaedic Surgery, National Taiwan University Hospital, Taipei City, Taiwan. Hauptthemen laut MEDLINE: Bone Density, Osteoporotic Fractures, Artificial Intelligence, Osteoporosis. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: National Science and Technology Council, National Taiwan University Hospital Yunlin Branch, National Health Research Institutes.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

AI-derived bone mineral density from routine radiographs showed strong agreement with DXA and comparable ability to predict incident fractures. This opportunistic approach may support osteoporosis screening and early identification of high-risk individuals without reliance on dedicated DXA examinations. INTRODUCTION: Osteoporosis is a major cause of fragility fractures, yet limited access to DXA leads to underdiagnosis and delayed treatment. Recent advances in artificial intelligence enable extraction of bone structural information from routine radiographs, providing a potential tool for opportunistic osteoporosis screening. Whether AI-derived BMD can approximate DXA and predict real-world fracture risk remains unclear. METHODS: Adults aged ≥ 20 years who underwent both lumbar DXA and radiographic examinations (lumbosacral or kidney-ureter-bladder) within six months between January 2014 and December 2024 were retrospectively analyzed. Lumbar BMD was estimated using DeepXray Spina and compared with DXA using Pearson correlation, intraclass correlation coefficient (ICC), and Bland-Altman analysis. Diagnostic performance for osteoporosis (T-score ≤ - 2.5) and fracture prediction was evaluated using receiver operating characteristic (ROC) analysis, Cohen's κ, and logistic regression. RESULTS: Among 540 participants (73.9% female; mean age 57.0 years; mean follow-up 6.4 years), AI- and DXA-derived BMD showed strong agreement (r = 0.943; ICC = 0.934). For osteoporosis diagnosis, AI-derived T-scores achieved an AUC of 0.959, κ = 0.74, and 90% accuracy. AI- and DXA-derived BMD showed comparable performance for predicting vertebral (AUC 0.704 vs. 0.678) and hip fractures (0.716 vs. 0.678). For all-site fractures, AI-derived BMD showed a modestly higher AUC than DXA-derived BMD (AUC, 0.699 vs 0.677; P = 0.042). Lower AI-derived BMD was independently associated with higher fracture risk. CONCLUSIONS: AI-derived BMD from routine radiographs closely correlates with DXA and demonstrates comparable fracture prediction. This approach may support opportunistic osteoporosis screening without reliance on DXA.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Bone DensityOsteoporotic FracturesArtificial IntelligenceOsteoporosisHumansFemaleAbsorptiometry, PhotonMiddle AgedMaleAgedLumbar VertebraeRetrospective StudiesRisk AssessmentAdultRadiographyMass Screening

Stichwörter der Autor:innen

Artificial intelligenceBone mineral densityDXAFracture riskOsteoporosis

Autor:innen und Institutionen

  • Department of Orthopaedic Surgery, National Taiwan University Hospital, Taipei City, Taiwan.
  • Department of Medical Education, National Taiwan University Hospital, Taipei City, Taiwan.
  • Department of Medical Imaging, National Taiwan University Hospital Yun-Lin Branch, Douliu, Taiwan.
  • Department of Orthopedics, National Taiwan University Hospital Yun-Lin Branch, No.579, Sec. 2, Yunlin Rd., Douliu City, Yunlin County, 640, Taiwan.
  • Program for Precision Health and Intelligent Medicine, Graduate School of Advanced Technology, National Taiwan University, Taipei, Taiwan.
  • Department of Family Medicine, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan.

Förderung

  • National Science and Technology Council
  • National Taiwan University Hospital Yunlin Branch
  • National Health Research Institutes
  • National Health Research Institutes (NHRI) / National Taiwan University Hospital Yunlin Branch

Zitieren

APA

Tseng, T. H., Huang, T. T., Huang, J. E., Tzeng, S. C., Wang, Y. C., Tsao, P. C., Hung, C. C., Lee, C. C., Hsu, J. Y., Yen, H. K., Wu, C. H., Li, C. Y., Wang, C. Y., & Fu, S. H. (2026). AI-derived bone mineral density from standard radiographs compared with DXA for fracture prediction in a 10-year real-world cohort study. Osteoporosis International. https://doi.org/10.1007/s00198-026-08100-8

Vancouver

Tseng TH, Huang TT, Huang JE, Tzeng SC, Wang YC, Tsao PC, et al. AI-derived bone mineral density from standard radiographs compared with DXA for fracture prediction in a 10-year real-world cohort study. Osteoporosis International. 2026. doi:10.1007/s00198-026-08100-8

BibTeX
@article{Tseng2026,
  author = {Tseng, Tzu-Hao and Huang, Tseng Ti and Huang, Jing En and Tzeng, Shi-Chien and Wang, Yu-Chen and Tsao, Pei-Chen and Hung, Chih-Chien and Lee, Chia-Che and Hsu, Jui-Yo and Yen, Hung-Kuan and Wu, Chih-Hsing and Li, Chung-Yi and Wang, Chen-Yu and Fu, Shau-Huai},
  title = {AI-derived bone mineral density from standard radiographs compared with DXA for fracture prediction in a 10-year real-world cohort study},
  journal = {Osteoporosis International},
  year = {2026},
  doi = {10.1007/s00198-026-08100-8}
}
Kostenlos starten →