Skip to content

Propective clinical validation study of a deep learning model for opportunistic osteoporosis screening based on non-contrast CT scans

Propective clinical validation study of a deep learning model for opportunistic osteoporosis screening based on non-contrast CT scans

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2600129120
Enrollment
Unknown
Registered
2026-07-31
Start date
2026-08-01
Completion date
Unknown
Last updated
2026-08-03

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Osteoporosis

Interventions

Gold Standard:The diagnosis of osteoporosis was based on the DXA-based diagnostic criteria established by the World Health Organization (WHO) in 1994.
Index test:DeepBMD model (an AI screening model for osteoporosis based on non-contrast CT).

Sponsors

Union Hospital, Tongji Medical College, Huazhong University of Science and Technology
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to No maximum

Inclusion criteria

Inclusion criteria: Study Group 1: (1) Underwent a plain chest CT scan using the hospital’s Philips IQon spectral CT scanner, with images of acceptable quality and free from severe artefacts; (2) Identified by the DeepBMD model as a high-risk individual for osteoporosis screening; (3) Valid contact details are recorded in the PACS system; the patient is cognitively sound and able to cooperate with telephone follow-ups and on-site examinations; (4) The patient voluntarily participates in the study, is able to sign a written informed consent form on site, and agrees to undergo DXA testing. Study Group 2: Patients who underwent plain chest and abdominal CT scans and DXA examinations at our hospital during the same period from April to June 2026.

Exclusion criteria

Exclusion criteria: 1. Severe spinal deformity, postoperative spinal internal fixation, malignant bone metastasis, or severe osteolytic lesions that may interfere with measurements; 2. A confirmed diagnosis of osteoporosis with ongoing standardized treatment; 3.Inability to be contacted, explicit refusal of follow-up, or inability to visit the hospital for informed consent signing and DXA examination.

Design outcomes

Primary

MeasureTime frame
Diagnostic performance of the DeepBMD model;

Secondary

MeasureTime frame
Computational success rate of DeepBMD;Patient recall rate;

Countries

China

Contacts

Public ContactYang Fan

Union Hospital, Tongji Medical College, Huazhong University of Science and Technology

fyang@vip.163.com+86 13871266365

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Aug 10, 2026