Academic Journal
In silico augmentation strategies for enhanced machine learning performance in fracture recognition.
| Τίτλος: | In silico augmentation strategies for enhanced machine learning performance in fracture recognition. |
|---|---|
| Συγγραφείς: | Xu M; Department of Orthopaedic Surgery, Suzhou TCM Hospital, Nanjing University of Chinese Medicine, Suzhou city, 215009, Jiangsu Province, China., Wang Z; Department of Orthopaedic Surgery, Suzhou TCM Hospital, Nanjing University of Chinese Medicine, Suzhou city, 215009, Jiangsu Province, China., Liu G; Department of Orthopaedic Surgery, Suzhou TCM Hospital, Nanjing University of Chinese Medicine, Suzhou city, 215009, Jiangsu Province, China., Wu C; Department of Orthopaedic Surgery, Suzhou TCM Hospital, Nanjing University of Chinese Medicine, Suzhou city, 215009, Jiangsu Province, China., Jiang H; Department of Orthopaedic Surgery, Suzhou TCM Hospital, Nanjing University of Chinese Medicine, Suzhou city, 215009, Jiangsu Province, China., Meng X; Department of Orthopaedic Surgery, Suzhou TCM Hospital, Nanjing University of Chinese Medicine, Suzhou city, 215009, Jiangsu Province, China. xuming1231231@hotmail.com. |
| Πηγή: | Scientific reports [Sci Rep] 2026 May 21; Vol. 16 (1). Date of Electronic Publication: 2026 May 21. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: London : Nature Publishing Group, copyright 2011- |
| Ιατρικοί όροι (MeSH): | Fractures, Bone*/diagnosis , Machine Learning* , Computer Simulation*, Humans ; Classification Algorithms ; Boosting Machine Learning Algorithms ; Prediction Algorithms ; Random Forest ; Predictive Learning Models ; Logistic Models ; Bone Density ; Support Vector Machine ; Retrospective Studies |
| Περίληψη: | This study presents a machine learning framework for fracture risk prediction and in silico validation of synthetic biomedical data. A retrospective dataset comprising 169 patient records with clinically relevant variables, including age, sex, weight, height, medication status, and bone mineral density (BMD), was analyzed. Multiple classification models, including Logistic Regression, Random Forest, Gradient Boosting, Support Vector Machine, and ensemble voting classifiers, were evaluated using 5-fold stratified cross-validation. Synthetic data fidelity was assessed through statistical distribution alignment, correlation preservation, and predictive transferability between real and synthetic domains. Among the evaluated models, the Voting Hard ensemble achieved the highest classification performance with an accuracy of 85.8% and F1-score of 0.822, while Logistic Regression demonstrated the highest discriminative capability (AUC = 0.88). Synthetic data showed strong agreement with real data in marginal feature distributions but weaker preservation of inter-feature correlations. The findings demonstrate the potential of ensemble machine learning methods for fracture risk prediction while highlighting the importance of rigorous validation when utilizing synthetic biomedical datasets. This framework provides a foundation for future development of privacy-preserving and clinically relevant synthetic data applications in biomedical machine learning. (© 2026. The Author(s).) |
| Competing Interests: | Declarations. Competing interests: The authors declare no competing interests. Ethical Considerations: No human participants or animals were involved in this study. |
| References: | BMJ Open. 2023 Dec 9;13(12):e071430. (PMID: 38070927) Neurospine. 2023 Dec;20(4):1112-1123. (PMID: 38171281) Bone Rep. 2024 Sep 12;22:101805. (PMID: 39328352) Sci Rep. 2025 Mar 21;15(1):9828. (PMID: 40119100) Sci Rep. 2024 Nov 18;14(1):28428. (PMID: 39558102) Sci Rep. 2024 Jan 30;14(1):2487. (PMID: 38291130) J Bone Miner Res. 2024 May 2;39(4):462-472. (PMID: 38477741) Sci Data. 2023 Aug 5;10(1):521. (PMID: 37543626) Diagnostics (Basel). 2024 Aug 27;14(17):. (PMID: 39272664) Comput Methods Programs Biomed. 2022 Nov;226:107141. (PMID: 36162246) Front Med (Lausanne). 2025 Jul 03;12:1616923. (PMID: 40678140) Heliyon. 2023 Jul 11;9(7):e18186. (PMID: 37501989) J Orthop Surg Res. 2023 Dec 12;18(1):956. (PMID: 38087332) Korean J Fam Med. 2024 May;45(3):144-148. (PMID: 38282437) Sci Rep. 2023 Nov 16;13(1):20077. (PMID: 37973984) SICOT J. 2023;9:21. (PMID: 37409882) Sci Rep. 2024 Dec 19;14(1):30560. (PMID: 39702597) Osteoporos Int. 2025 May;36(5):811-821. (PMID: 40053072) BMC Med Imaging. 2025 Aug 5;25(1):316. (PMID: 40764539) |
| Contributed Indexing: | Keywords: Bone mineral density; Ensemble learning; Fracture risk prediction; Machine learning; Predictive modeling; Synthetic biomedical data |
| Entry Date(s): | Date Created: 20260521 Date Completed: 20260824 Latest Revision: 20260827 |
| Update Code: | 20260827 |
| PubMed Central ID: | PMC13503791 |
| DOI: | 10.1038/s41598-026-53126-x |
| PMID: | 42168545 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 2045-2322 |
|---|---|
| DOI: | 10.1038/s41598-026-53126-x |