Skip to content

Multicenter Deep Learning for Multi-Abnormality Screening on Hip Radiographs: Development, External Validation, and Assisted Reader Study

Research on Deep Learning-Based Imaging Diagnosis of Hip Diseases and Postoperative Gait Assessment

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2500108943
Enrollment
Unknown
Registered
2025-09-09
Start date
2025-04-01
Completion date
Unknown
Last updated
2025-09-15

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

Conditions

Normal hip, hip osteoarthritis, osteonecrosis of the femoral head, femoral neck fracture, intertrochanteric fracture, developmental dysplasia of the hip, total hip arthroplasty, and metallic internal fixation.

Interventions

Gold Standard:All images were independently annotated by two senior orthopedic surgeons. If their assessments differed, a third senior surgeon performed a final review, and a consensus diagnosis was r
Index test:1. Hip Disease Diagnostic Model: A model based on deep learning algorithms for the automated detection and classification of hip diseases (e.g., osteoarthritis, osteonecrosis, developmental

Sponsors

The Second Hospital of Jilin University?
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to No maximum

Inclusion criteria

Inclusion criteria: 1. Availability of hip radiographs or CT scans. 2. Availability of recorded gait videos following joint replacement surgery. 3. Age = 18 years. 4. Scan coverage extending from the anterior superior iliac spine to the upper third of the femur.

Exclusion criteria

Exclusion criteria: 1. Immature skeletal development or open epiphyses. 2. Prior surgery that compromises the bony architecture of the hip. 3. Malposition of the pelvis resulting in partial or complete obscuration of the joint structures.? 4. Poor quality of imaging or gait videos.

Design outcomes

Primary

MeasureTime frame
Accuracy;Area under the curve;

Secondary

MeasureTime frame
Specificity;Recall;Precision;Negative predictive value;F1 score;

Countries

China

Contacts

Public ContactYanguo Qin

The Second Hospital of Jilin University

qinyg@jlu.edu.cn+86 178 6507 9359

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 4, 2026