Periprosthetic Hip Fracture

Purpose

Detect periprosthetic hip fracture

Tag(s)

 

Panel

 Musculoskeletal

TOUCH-AI ID

 TAI-05180009

Originator

 Munib Sana

Panel Chair

 Jay Patti

Panel Reviewers

 Musculoskeletal Panel

License

 Creative Commons 4.0

Status  Public Commenting

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 exams per day for a musculoskeletal radiologist who works with arthroplasty surgeons. Aseptic loosening and adverse local tissue reaction complicate a significant number of THAs and necessitate revision arthroplasty. These are indolent processes that, if not detected early, can lead to osteolysis and/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 the 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 compares this exam with multiple prior exams. The algorithm categorizes the THA as stable or abnormal. The radiologist is informed of this categorization at the time of interpretation.

Workflow Description

The current image and prior hip x-rays are analyzed by an AI engine. The engine then detects periprosthetic fracture.

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

Periprosthetic Fracture

RadElement ID

RDE248

Definition

Detect if periprosthetic fracture is present.

Data Type

Categorical

Value Set

0–Unknown

1–Fracture present

2–Fracture absent

Units

N/A

Secondary Outputs

Total Hip Arthoplasty Status

RadElement ID

RDE249

Definition

Status of the total hip arthroplasty

Data Type

Categorical

Value Set

0–Unknown

1–Normal

2–Abnormal

Units

N/A

Public Commenting


Use cases are meant to be a primary vehicle for distributing clinical information to the developer community. They pinpoint precise scenarios within radiology workflows where potential automation could add noticeable value and establish standards for interpreting and passing corresponding common data elements. Implementing effective standards requires the perspective from all stakeholders. So to that end, we encourage your feedback on use cases.

To submit comments, please email DSIUseCases@acr.org with the use case title(s) and relevant comments by January 1, 2019. If more convenient, you may also download this use case and comment directly on the PDF. Just attach the PDF copy on the email.