Hip Subsidence
| Purpose | Measure subsidence in the hip following total hip arthroplasty |
| Tag(s) | #THA |
| Panel | Musculoskeletal |
| Define-AI ID | 18050004 |
| Originator | Munib Sana |
| Panel Chair | Jay Patti |
| Panel Reviewers | Musculoskeletal Panel |
| License | |
| Status | Published |
Clinical Implementation
Value Proposition
There are roughly 400,000 total hip arthroplasties (THAs) performed annually. Every patient has annual follow-up exams, which can add up to about 100 reads per day for an MSK radiologist who works with arthroplasty surgeons. Aseptic loosening and adverse local tissue reaction (ALTR) complicate a significant number of THAs and necessitate revision arthroplasty. These are indolent processes that, if not detected early, can lead to osteolysis or extensive tissue necrosis. Findings are not readily apparent on x-ray and require comparison with multiple prior exams to see progression of abnormality over time. AI meeting this use case would help to reduce false negative rate, patient risk, and medical legal risk for the radiologists. High-risk patients could be screened for elevated serum cobalt levels and sent to MRI for further evaluation. Delay in diagnosis could delay treatment for years.Narrative(s)
A 65-year-old patient presents for annual follow-up THA x-ray. An algorithm evaluates the image and may also compare this exam with multiple prior exams. The algorithm detects if osteolysis is present to assist the radiologists in the interpretation of the patient’s THA status.Workflow Description
The current image and accessible, prior hip x-rays are analyzed by the engine. Between the current image and images at least five years old or initial post-op film (if THA was performed less than five years ago), the engine can detect osteolysis. The images are returned to the radiologist at the time of interpretation.Considerations for Dataset Development
Procedures(s): X-ray, hip
View(s): {AP, frog-leg lateral, cross-table lateral}
Sex at Birth: {Male, female}
Osteolysis Location: {Gruen zone 1, Gruen zone 7, Gruen zone 8, Gruen zone 14}
Interval Between Imaging (years): [0,20]
Comorbidities: {Calcar resorption, osteoporosis, subsidence, lucency}
Technical Specifications
Inputs
DICOM Study
| Procedure | XRAY, Hip |
| Views | AP, frog-leg lateral, cross-table lateral |
| Data Type | DICOM |
| Modality | XRAY |
| Body Region | Pelvis |
| Anatomic Focus | Hip |
Primary Outputs
Hip Subsidence
| RadElement ID | |
| Definition | Measure the amount of subsidence. Alert if subsidence is greater than or equal to 10 mm. |
| Data Type | Numeric |
| Value Set | [0,30] |
| Units | mm |
Secondary Outputs
Total Hip Arthoplasty Status
| RadElement ID | RDE213 |
| Definition | Status of the total hip arthroplasty |
| Data Type | Categorical |
| Value Set | 0–Unknown 1–Present 2–Absent |
| Units | N/A |
Related Datasets
No known related public datasets at this time, please us alert us if you know of any.