Pediatric Elbow
| Purpose | To assist radiologists in the interpretation of pediatric elbow radiographs |
| Tag(s) |
|
| Panel | Musculoskeletal |
| Define-AI ID | 18050008 |
| Originator | Jay Patti |
| Panel Chair | Jay Patti |
| Panel Reviewers | Musculoskeletal Panel |
| License | |
| Status | Published |
Clinical Implementation
Value Proposition
When interpreting pediatric elbow radiographs, the appearance of the osseous structures can vary significantly based on the patient’s age. Normal development dictates an ordered mineralization of the apophyses of the elbow, which depends on patient age. Fractures of the elbow bones can mimic normal apophyses. Knowing the order of expected mineralization and age of the patient can help prevent diagnostic error. An AI algorithm could refine the currently known expected age of mineralization and warn radiologists when pathology mimics a normal developmental appearance in the setting of a discordant patient age. The classic mnemonic device that is used to remember the order of ossification is CRITOE, which stands for Capitellum, Radial head, Internal epicondyle, Trochlea, Olecranon, External epicondyle. In normal development, these apophyses ossify at roughly ages 2, 4, 5, 9, and 11, respectively.Narrative(s)
A pediatric (<15 years old) patient presents for elbow radiography after trauma. There is a fracture of the lateral humeral epiphyseal apophysis that mimics normal development in a patient 3 years older than the patient’s true age. This could present a diagnostic challenge or potential area for diagnostic oversight resulting in medical error.Workflow Description
The radiograph is processed by the algorithm, which is tuned to identify the elbow apophyses and correlate them with patient age. The engine would send a message to PACS with the coordinates of each normal apophysis, which are then highlighted with a subtle green tint. Any apophyses that are inconsistent with the patient’s age are highlighted in yellow, which alerts the radiologist to examine these suspicious areas more closely.Considerations for Dataset Development
Procedures(s): X-ray, Elbow
View(s): {AP, Lateral, Oblique}
Sex at Birth: {Male, Female}
Age (years): [0,15]
Data source: {pediatric facilities, general facilities}
Differential Diagnoses: Apophysis injury
Elbow: {Left, Right}
Fractures: supracondylar fractures
Other: {Casting, bracing material}
Technical Specifications
Inputs
DICOM Study
| Procedure | XRAY, Elbow |
| Views | AP, Lateral, Oblique |
| Data Type | DICOM |
| Modality | XRAY |
| Body Region | Upper Extremity |
| Anatomic Focus | Elbow |
Primary Outputs
Abnormal Apophyses
| RadElement ID | RDED246 |
| Definition | Detect and count abnormal apophyses |
| Data Type | Numeric |
| Value Set | [0,6] |
| Units | Apophyses |
Secondary Outputs
Age
| RadElement ID | RDE247 |
| Definition | Patient age in years |
| Data Type | Numeric |
| Value Set |
|
| Units | Years |
Future Development Ideas
Segment capitellum, radial head, internal epicondyle, trochlea, olecranon, and external epicondyle as well as highlight the abnormal apophyses.Related Datasets
No known related public datasets at this time, please us alert us if you know of any.