Advanced imaging and AI for detecting and staging osteoporosis and osteoarthritis
A Comprehensive Evaluation of Musculoskeletal Aging and Degenerative Pathologies Using Multi-modal Clinical Imaging and Quantitative Analysis.
This project will see if an AI system can use routine X‑rays, CT, and MRI to accurately diagnose and stage osteoporosis and osteoarthritis in adults.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 2000 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | Peking University People's Hospital Academic / other |
| Drugs / interventions | chemotherapy |
| Locations | 1 site (Beijing) |
| Trial ID | NCT07474571 on ClinicalTrials.gov |
What this trial studies
This observational project develops and validates a multimodal AI platform that combines X‑ray, CT, MRI, clinical laboratory markers, and patient history to detect and stage osteoporosis and osteoarthritis. A retrospective cohort of about 1,500 patients from Peking University People's Hospital (2005–2025) will be used for model development, and at least 500 prospectively recruited adults will provide external validation beginning December 2025. The AI will quantify bone mineral density and microarchitecture for osteoporosis and identify radiographic markers such as joint space narrowing and osteophytes for osteoarthritis to produce standardized staging. The work is non‑interventional and aims to reduce inter‑observer variability and improve objectivity in imaging-based musculoskeletal assessment.
Who should consider this trial
Good fit: Ideal candidates are adults (18–90) who have completed relevant clinical imaging (X‑ray, CT, or MRI) of bone or joint sites and have no implants or major skeletal deformities.
Not a fit: Patients with prior pathological fractures, active bone malignancy, recent chemotherapy or radiotherapy, or a history of long‑term steroid use are excluded and unlikely to benefit from the model's outputs.
Why it matters
Potential benefit: If successful, the platform could provide faster, more objective, and more consistent diagnoses and staging of osteoporosis and osteoarthritis, helping clinicians make better treatment and fracture‑risk decisions.
How similar studies have performed: Similar AI methods have shown promising results for automated bone density measurement and radiographic OA grading in earlier studies, but the combination of multimodal imaging and large prospective validation remains relatively novel.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Age: Adults aged at least 18 years. * Gender: No gender restrictions; both male and female participants are eligible. * Imaging Data: Participants must have completed relevant clinical imaging scans of skeletal sites, including but not limited to X-ray, CT (plain scan), or MRI (plain scan). * Anatomical Integrity: The skeletal structure of the target area must be free from congenital or acquired deformities. * Absence of Implants: No internal fixation materials or orthopedic implants in the skeletal areas being assessed. Exclusion Criteria: * Pathological History: Patients with a history of prior pathological fractures. * Malignancy: Patients seeking treatment or diagnosed with bone tumors or other systemic malignancies. * Medication History: Patients with a history of long-term steroid use, which may significantly affect bone density and joint structure. * Recent Treatment: Patients who have undergone radiotherapy or chemotherapy within the past six months. * Data Quality: Patients whose imaging data is of insufficient quality for AI analysis or lacks clear clinical diagnostic "gold standard" references (e.g., missing DXA results for osteoporosis staging).
Where this trial is running
Beijing
- Beijing, China (Recruiting)
Study contacts
- Study coordinator: Yuhui Kou, M.D
- Email: yuhuikou@bjmu.edu.cn
- Phone: 13146213332
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.