Artificial intelligence to identify fractures on pediatric and young adult upper extremity radiographs

Background Pediatric fractures are challenging to identify given the different response of the pediatric skeleton to injury compared to adults, and most artificial intelligence (AI) fracture detection work has focused on adults. Objective Develop and transparently share an AI model capable of detect...

Full description

Saved in:
Bibliographic Details
Published in:Pediatric radiology 2023-11, Vol.53 (12), p.2386-2397
Main Authors: Zech, John R., Jaramillo, Diego, Altosaar, Jaan, Popkin, Charles A., Wong, Tony T.
Format: Article
Language:English
Subjects:
Accuracy
Adults
Algorithms
Artificial intelligence
Artificial neural networks
Clavicle
Elbow
Elbow (anatomy)
Fingers
Fractures
Humerus
Image classification
Imaging
Medicine
Medicine & Public Health
Model testing
Natural language processing
Neural networks
Neuroradiology
Nuclear Medicine
Object recognition
Oncology
Original Article
Pediatrics
Radiographs
Radiography
Radiology
Ultrasound
Wrist
Young adults
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Background Pediatric fractures are challenging to identify given the different response of the pediatric skeleton to injury compared to adults, and most artificial intelligence (AI) fracture detection work has focused on adults. Objective Develop and transparently share an AI model capable of detecting a range of pediatric upper extremity fractures. Materials and methods In total, 58,846 upper extremity radiographs (finger/hand, wrist/forearm, elbow, humerus, shoulder/clavicle) from 14,873 pediatric and young adult patients were divided into train ( n  = 12,232 patients), tune ( n  = 1,307), internal test ( n  = 819), and external test ( n  = 515) splits. Fracture was determined by manual inspection of all test radiographs and the subset of train/tune radiographs whose reports were classified fracture-positive by a rule-based natural language processing (NLP) algorithm. We trained an object detection model (Faster Region-based Convolutional Neural Network [R-CNN]; “strongly-supervised”) and an image classification model (EfficientNetV2-Small; “weakly-supervised”) to detect fractures using train/tune data and evaluate on test data. AI fracture detection accuracy was compared with accuracy of on-call residents on cases they preliminarily interpreted overnight. Results A strongly-supervised fracture detection AI model achieved overall test area under the receiver operating characteristic curve (AUC) of 0.96 (95% CI 0.95–0.97), accuracy 89.7% (95% CI 88.0–91.3%), sensitivity 90.8% (95% CI 88.5–93.1%), and specificity 88.7% (95% CI 86.4–91.0%), and outperformed a weakly-supervised model (AUC 0.93, 95% CI 0.92–0.94, P  
ISSN:1432-1998
0301-0449
1432-1998
DOI:10.1007/s00247-023-05754-y