Evidence map›Paper›PMID 37740031›Full record

ArticlePediatric radiology2023

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

John R Zech, Diego Jaramillo, Jaan Altosaar, Charles A Popkin, Tony T Wong

Abstract read
PubMed Publisher
In one paragraph

Article in Pediatric radiology, 2023. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 26 papers, 6 of them syntheses that pooled it.

0numbers the graph read from it
0cells of the map it votes in
26citing papers in PubMed, 6 pooled it
1.5field-weighted citation impact, top 13% of its field
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

26 citing papers in PubMed, 6 syntheses or guidelines pooled it, 40 citations in OpenAlex.

  1. Pooled it
  2. Pooled it
  3. Pooled it
  4. Impact of deep learning on pediatric elbow fracture detection: a systematic review and meta-analysis.European journal of trauma and emergency surgery : official publication of the European Trauma Society · 2025
    Pooled it
  5. Pooled it
  6. Pooled it
  7. Review
  8. Article
  9. Article
  10. Article
  11. Article
  12. Article
  13. Article
  14. Advances in Artificial Intelligence for Wrist Joint Injury Diagnosis.International journal of medical sciences · 2026
    Review
  15. Review
  16. Article
  17. Article
  18. Review
  19. Article
  20. Article
4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

5 authors at 2 institutions in 1 country.

John R ZechDepartment of Radiology, Columbia University Irving Medical Center, 622 W. 168th St., New York, NY, 10032, USA. jrzech@gmail.com.ORCID http://orcid.org/0000-0003-1317-8951
Diego JaramilloDepartment of Radiology, Columbia University Irving Medical Center, 622 W. 168th St., New York, NY, 10032, USA.
Jaan AltosaarOne Fact Foundation, Brooklyn, NY, USA.
Charles A PopkinDepartment of Orthopedic Surgery, Columbia University Irving Medical Center, New York, NY, USA.
Tony T WongDepartment of Radiology, Columbia University Irving Medical Center, 622 W. 168th St., New York, NY, 10032, USA.
Columbia University Irving Medical Center · USACT Foundation · US

Funding

RSNA Research and Education Foundation RR2216
6 · The paper itself

Abstract

backgroundPediatric 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.

objectiveDevelop and transparently share an AI model capable of detecting a range of pediatric upper extremity fractures. MATERIALS AND

methodsIn 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.

resultsA 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 < 0.0001). AI accuracy on cases preliminary interpreted overnight was higher than resident accuracy (AI 89.4% vs. 85.1%, 95% CI 87.3-91.5% vs. 82.7-87.5%, P = 0.01).

conclusionAn object detection AI model identified pediatric upper extremity fractures with high accuracy.

Indexed as

Artificial IntelligenceFractures, BoneChildElbowHumansNeural Networks, ComputerRadiographyRetrospective StudiesYoung AdultArtificial intelligenceBone, ChildConvolutional neural networkFracturesHumansMusculoskeletal system*/diagnostic imagingRadiographyUpper extremity

Identifiers

PMID37740031
OpenAlexW4386946116

What OpenQuestion holds

Textmetadata
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.