Skip to content
DraconiticResearch
Search Sources API
185,139 studies31 sourcesUpdated 18 min ago
Peer-reviewedCC BY-NC-NDBMC surgery

Unsupervised machine learning for clinical risk subtyping and re-fracture risk analysis in osteoporotic vertebral compression fractures.

  • Yongjie Wang1
  • Xinwei Zhang1
  • Libin Cui1
  • Qian Lu1
  • Ziqian Ma1
  • Yan Zhang1
  • Xin Yuan2
  • Xueming Chen3
  • Liang Liu4
4 affiliations
  1. 1Department of Orthopedics Surgery, Beijing Luhe Hospital, Capital Medical University, Xinhua South Road No. 82, Tongzhou District, Beijing, 101149, China.
  2. 2Department of Orthopedics Surgery, Beijing Luhe Hospital, Capital Medical University, Xinhua South Road No. 82, Tongzhou District, Beijing, 101149, China. [email protected].
  3. 3Department of Orthopedics Surgery, Beijing Luhe Hospital, Capital Medical University, Xinhua South Road No. 82, Tongzhou District, Beijing, 101149, China. [email protected].
  4. 4Department of Orthopedics Surgery, Beijing Luhe Hospital, Capital Medical University, Xinhua South Road No. 82, Tongzhou District, Beijing, 101149, China. [email protected].
Read full textPDFDOICite

Abstract

Objective

To investigate the application of unsupervised machine learning analyzing re-fracture risks in osteoporotic vertebral compression fractures.Methods

A cohort of 867 patients (658 females and 209 males) with 1,255 fracture cases was analyzed. Fractures predominantly occurred at vertebrae T12, L1, and L2. Patients were categorized into once-fracture (n = 730) and multi-fracture (n = 137) groups. Bone mineral density (BMD) was measured, and t-SNE was used for dimensionality reduction. K-means clustering was applied for clustering fracture cases into four risk clusters based on patient-level clinical characteristics and regional fracture distribution (Clusters A: male-predominant low-risk, Cluster B: female low-risk, Cluster C: female high-risk, thoracolumbar, and Cluster D: female high-risk, mid-thoracic).Results

Multi-fracture patients had a median re-fracture interval of 10 months and significantly lower BMD compared to once-fracture patients. Cluster A fractures were exclusive to males with a re-fracture probability of 19.31%. Female fractures were categorized into Clusters B, C, and D, with re-fracture probabilities of 19.00%, 36.71%, and 32.77%, respectively. Cluster B fractures in females showed a significantly lower re-fracture risk compared to Clusters C and D. Significant differences in age, height, weight, and fracture location were observed among subtypes.Conclusion

The study highlights the potential of unsupervised machine learning for identifying exploratory, potentially clinically relevant risk phenotypes in OVCF patients, which may inform future risk-stratified follow-up strategies.Significance

The findings underscore the potential of unsupervised machine learning in identifying exploratory data-driven subtypes of spinal fractures and may inform risk stratification, thereby warranting further investigation.

Related

  1. Effects of percutaneous kyphoplasty with concomitant postural reduction in the treatment of acute osteoporotic vertebral compression fractures
    Yulin Chen, Peng Yang, Ankejiang Anniwaer +4
    Frontiers in medicinePeer-reviewedCC BYFull textGeneral medicineEurope PMC
  2. Correlation Between Paravertebral Muscles Degeneration and Spinopelvic Parameters in Patients With Osteoporotic Vertebral Compression Fractures.
    De-Chao Miao, Bao-Yue Zhang, Tong Tong +2
    Medical science monitor : international medical journal of experimental and clinical researchPeer-reviewedCC BY-NC-NDFull textSurgery & anaesthesiaEurope PMC
  3. Comparison of Two Puncture Approaches in Robot-Assisted Percutaneous Kyphoplasty for Upper Thoracic Osteoporotic Vertebral Compression Fractures.
    Yongtao Yang, Wei Chen, Rujie Qin +1
    Radiology research and practicePeer-reviewedCC BYFull textSurgery & anaesthesiaEurope PMC
  4. Extensive vertebral compression fractures as the initial manifestation of childhood B-cell acute lymphoblastic leukemia despite limited peripheral blood abnormalities: a case report
    Danmei Zou, Tong Zhou, Yilan Chen +2
    Frontiers in PediatricsPeer-reviewedCC BY 4.0Full textEpidemiology & public healthPMCEurope PMC
  5. Procedural Complications and Implant Cutout of the SpineJack®-System in Thoracolumbar Vertebral Fractures: A Retrospective Analysis of 204 Implants from a Level-1 Trauma Center
    Julian Scherer, Magdalena Karner, Georg Osterhoff +2
    Global Spine JournalPeer-reviewedCC BY-NC-NDFull textSurgery & anaesthesiaEurope PMC

Cite

BibTeXRIS
BibTeX
@article{wang2026unsupervised,
  title = {{Unsupervised machine learning for clinical risk subtyping and re-fracture risk analysis in osteoporotic vertebral compression fractures.}},
  author = {Yongjie Wang and Xinwei Zhang and Libin Cui and Qian Lu and Ziqian Ma and Yan Zhang and Xin Yuan and Xueming Chen and Liang Liu},
  journal = {BMC surgery},
  year = {2026},
  month = aug,
  doi = {10.1186/s12893-026-04007-7},
  url = {https://europepmc.org/article/MED/42958247},
  note = {CC BY-NC-ND},
}
RIS
TY  - JOUR
TI  - Unsupervised machine learning for clinical risk subtyping and re-fracture risk analysis in osteoporotic vertebral compression fractures.
AU  - Yongjie Wang
AU  - Xinwei Zhang
AU  - Libin Cui
AU  - Qian Lu
AU  - Ziqian Ma
AU  - Yan Zhang
AU  - Xin Yuan
AU  - Xueming Chen
AU  - Liang Liu
PY  - 2026
DA  - 2026/08/04
JO  - BMC surgery
DO  - 10.1186/s12893-026-04007-7
UR  - https://europepmc.org/article/MED/42958247
AB  - Objective  To investigate the application of unsupervised machine learning analyzing re-fracture risks in osteoporotic vertebral compression fractures.Methods  A cohort of 867 patients (658 females and 209 males) with 1,255 fracture cases was analyzed. Fractures predominantly occurred at vertebrae T12, L1, and L2. Patients were categorized into once-fracture (n = 730) and multi-fracture (n = 137) groups. Bone mineral density (BMD) was measured, and t-SNE was used for dimensionality reduction. K-means clustering was applied for clustering fracture cases into four risk clusters based on patient-level clinical characteristics and regional fracture distribution (Clusters A: male-predominant low-risk, Cluster B: female low-risk, Cluster C: female high-risk, thoracolumbar, and Cluster D: female high-risk, mid-thoracic).Results  Multi-fracture patients had a median re-fracture interval of 10 months and significantly lower BMD compared to once-fracture patients. Cluster A fractures were exclusive to males with a re-fracture probability of 19.31%. Female fractures were categorized into Clusters B, C, and D, with re-fracture probabilities of 19.00%, 36.71%, and 32.77%, respectively. Cluster B fractures in females showed a significantly lower re-fracture risk compared to Clusters C and D. Significant differences in age, height, weight, and fracture location were observed among subtypes.Conclusion  The study highlights the potential of unsupervised machine learning for identifying exploratory, potentially clinically relevant risk phenotypes in OVCF patients, which may inform future risk-stratified follow-up strategies.Significance  The findings underscore the potential of unsupervised machine learning in identifying exploratory data-driven subtypes of spinal fractures and may inform risk stratification, thereby warranting further investigation.
SN  - 1471-2482
ER  -