Radial Head Dislocation

Purpose	Detect radial head dislocation
Tag(s)
Panel	Musculoskeletal
Define-AI ID	18050011
Originator	Munib Sana
Panel Chair	Jay Patti
Panel Reviewers	Musculoskeletal Panel
License	Creative Commons 4.0
Status	Published

Clinical Implementation

Value Proposition

Injury is common, but easily missed by nonspecialists and in a busy emergency room (ER) setting. Many cases have a joint effusion and no fracture and are reported as such. AI would help to reduce the false negative rate, patient risk, and medical-legal risk for the radiologists.

Narrative(s)

A 9-year-old patient presents with trauma and/or elbow pain. An x-ray is taken in the ER. An algorithm evaluates radiocapitellar alignment and categorizes it as normal, abnormal, or indeterminate. The radiologist is informed of this categorization at the time of interpretation.

Workflow Description

Images are obtained from the modality and sent to PACS and the AI engine. The lateral x-ray image is analyzed by the AI. AI categorizes the radiocapitellar alignment as normal, abnormal, or indeterminate. The algorithm’s interpretation of the radiocapitellar line on the lateral view is accessible, should the radiologist want to display it. A message is sent to PACS from the engine with the classification information.

Considerations for Dataset Development

Procedures(s): X-ray, Elbow

View(s): Lateral

Sex at Birth: {Male, Female}

Age: [0,18]

Comorbidities: Cerebral Palsy

Other: Congenital radial head dislocations

Technical Specifications

Inputs

DICOM Study

Procedure	XRAY, Elbow
Views	Lateral
Data Type	DICOM
Modality	XRAY
Body Region	Upper Extremity
Anatomic Focus	Elbow

Primary Outputs