Academic Journal
Real-World Validation of an AI-Based Opportunistic Osteoporosis Risk Stratification Tool Using Chest Radiographs in a Male-Predominant Cohort.
| Τίτλος: | Real-World Validation of an AI-Based Opportunistic Osteoporosis Risk Stratification Tool Using Chest Radiographs in a Male-Predominant Cohort. |
|---|---|
| Συγγραφείς: | Tu KC; Department of Orthopaedics, Taichung Veterans General Hospital, Taichung 40705, Taiwan.; Doctoral Program in Tissue Engineering and Regenerative Medicine, National Chung Hsing University, Taichung 402202, Taiwan., Wu SC; Department of Orthopaedics, Taichung Veterans General Hospital, Taichung 40705, Taiwan., Shih HT; Department of Orthopaedics, Taichung Veterans General Hospital, Taichung 40705, Taiwan.; Department of Industrial Engineering and Enterprise Information, Tunghai University, Taichung 407224, Taiwan., Lee CH; Department of Orthopaedics, Taichung Veterans General Hospital, Taichung 40705, Taiwan., Chen KH; Department of Orthopaedics, Taichung Veterans General Hospital, Taichung 40705, Taiwan.; Department of Post-Baccalaureate Medicine, College of Medicine, National Chung Hsing University, Taichung 402202, Taiwan.; Department of Computer Science and Information Engineering, Providence University, Taichung 43301, Taiwan., Hsu CH; Doctoral Program in Tissue Engineering and Regenerative Medicine, National Chung Hsing University, Taichung 402202, Taiwan.; Institute of Biomedical Engineering and Nanomedicine, National Health Research Institutes, Zhunan, Miaoli County 35053, Taiwan.; Institute of NanoEngineering and MicroSystems, National Tsing Hua University, Hsinchu 30013, Taiwan. |
| Πηγή: | Healthcare (Basel, Switzerland) [Healthcare (Basel)] 2026 Sep 28; Vol. 14 (19). Date of Electronic Publication: 2026 Sep 28. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: MDPI AG Country of Publication: Switzerland NLM ID: 101666525 Publication Model: Electronic Cited Medium: Print ISSN: 2227-9032 (Print) Linking ISSN: 22279032 NLM ISO Abbreviation: Healthcare (Basel) Subsets: PubMed not MEDLINE |
| Imprint Name(s): | Original Publication: Basel, Switzerland : MDPI AG, [2013]- |
| Περίληψη: | Background: Osteoporosis is a major public health concern and a leading cause of fragility fractures, yet screening with dual-energy X-ray absorptiometry (DXA) remains limited by accessibility and utilization. Opportunistic artificial intelligence (AI)-based analysis of routinely acquired chest radiographs (CXRs) may facilitate osteoporosis risk stratification. This study aimed to independently validate a regulatory-approved deep learning model (VeriOsteo™ OP) in a real-world, male-predominant cohort. Methods: We retrospectively analyzed 2336 patients who underwent both CXR and DXA at a medical center in 2023, including 1688 males (72.3%) and 648 females (27.7%). Osteoporosis was defined as a DXA T-score ≤ -2.5. AI performance was evaluated using sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and area under the receiver operating characteristic curve (AUC), with sex-specific subgroup analyses. Results: The AI model achieved an accuracy of 76.97%, sensitivity of 69.67%, specificity of 84.64%, PPV of 82.66%, and NPV of 72.65%. The overall AUC was 0.854 (95% CI, 0.839-0.868). The AUC was 0.825 (95% CI, 0.794-0.854) in males and 0.849 (95% CI, 0.831-0.866) in females. PPV was lower in males than in females (60.00% vs. 83.39%), while other performance measures were broadly comparable. The optimal AI cutoff also differed between males (≤-1.9) and females (≤-2.5). Conclusions: The AI model demonstrated good discrimination for opportunistic osteoporosis risk stratification using CXRs in a real-world cohort. Its moderate sensitivity and lower PPV among males highlight potential sex-related differences in AI-assisted osteoporosis assessment. The model may be most appropriately used as an adjunctive risk-stratification and DXA-prioritization tool to identify individuals who may benefit from subsequent DXA evaluation rather than a standalone diagnostic test. |
| References: | Neth J Med. 2001 Feb;58(2):62-70. (PMID: 11166447) Osteoporos Int. 2024 Oct;35(10):1681-1692. (PMID: 38985200) Osteoporos Int. 2022 Oct;33(10):2049-2102. (PMID: 35478046) Sci Rep. 2021 Aug 3;11(1):15709. (PMID: 34344965) J Bone Miner Res. 2023 Jun;38(6):887-895. (PMID: 37038364) Biomedicines. 2022 Sep 19;10(9):. (PMID: 36140424) Front Med (Lausanne). 2025 Mar 26;12:1499670. (PMID: 40206487) Eur J Rheumatol. 2017 Mar;4(1):46-56. (PMID: 28293453) Diagnostics (Basel). 2024 Jun 07;14(12):. (PMID: 38928624) Bone. 2020 Nov;140:115561. (PMID: 32730939) Med Clin North Am. 2020 Sep;104(5):873-884. (PMID: 32773051) J Bone Miner Res. 2022 Feb;37(2):369-377. (PMID: 34812546) Bone. 2017 Nov;104:39-43. (PMID: 28041872) J Clin Densitom. 2017 Jul - Sep;20(3):322-333. (PMID: 28739081) J Bone Miner Res. 2021 May;36(5):833-851. (PMID: 33751686) Med Eng Phys. 2022 Oct;108:103887. (PMID: 36195368) BMC Musculoskelet Disord. 2017 Jan 26;18(1):46. (PMID: 28125982) Sci Rep. 2021 Oct 7;11(1):19997. (PMID: 34620976) Curr Rheumatol Rep. 2018 Oct 13;20(12):74. (PMID: 30317448) |
| Contributed Indexing: | Keywords: artificial intelligence; bone mineral density; chest radiograph; opportunistic screening; osteoporosis |
| Entry Date(s): | Date Created: 20261016 Date Completed: 20261016 Latest Revision: 20261020 |
| Update Code: | 20261020 |
| PubMed Central ID: | PMC13664794 |
| DOI: | 10.3390/healthcare14193200 |
| PMID: | 42881638 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 2227-9032 |
|---|---|
| DOI: | 10.3390/healthcare14193200 |