INTRODUCTION: In this study, we aimed to compare the performance of a convolutional neural network (CNN)-based deep learning model that was trained on a dataset of normal and abnormal paediatric elbow radiographs with that of paediatric emergency department (ED) physicians on a binomial classification task. METHODS: A total of 1,314 paediatric elbow lateral radiographs (patient mean age 8.2 years) were retrospectively retrieved and classified based on annotation as normal or abnormal (with pathology). They were then randomly partitioned to a development set (993 images); first and second tuning (validation) sets (109 and 100 images, respectively); and a test set (112 images). An artificial intelligence (AI) model was trained on the development set using the EfficientNet B1 network architecture. Its performance on the test set was compared to that of five physicians (inter-rater agreement: fair). Performance of the AI model and the physician group was tested using McNemar test. RESULTS: The accuracy of the AI model on the test set was 80.4% (95% confidence interval [CI] 71.8%-87.3%), and the area under the receiver operating characteristic curve (AUROC) was 0.872 (95% CI 0.831-0.947). The performance of the AI model vs. the physician group on the test set was: sensitivity 79.0% (95% CI: 68.4%-89.5%) vs. 64.9% (95% CI: 52.5%-77.3%; P = 0.088); and specificity 81.8% (95% CI: 71.6%-92.0%) vs. 87.3% (95% CI: 78.5%-96.1%; P = 0.439). CONCLUSION The AI model showed good AUROC values and higher sensitivity, with the P-value at nominal significance when compared to the clinician group.
Humans ; Deep Learning ; Child ; Retrospective Studies ; Male ; Female ; Radiography/methods* ; ROC Curve ; Elbow/diagnostic imaging* ; Neural Networks, Computer ; Child, Preschool ; Elbow Joint/diagnostic imaging* ; Emergency Service, Hospital ; Adolescent ; Infant ; Artificial Intelligence

The Singapore Health Services cluster (SingHealth) radiology film archives are a valuable repository of local radiological cases dating back to the 1950s. Some of the cases in the archives are of historical medical interest, i.e. cerebral angiography in the workup of patients with hemiplegia. Other cases are of historical social interest, being conditions seen during earlier stages of Singapore's development, i.e. bound feet. The archives form a unique portal into the development of local radiology as well as the national development of Singapore. A selection from the archives is published in commemoration of the International Day of Radiology in 2020, as well as the 200th anniversary of the Singapore General Hospital in 2021. This pictorial essay comprises gastroenterology, musculoskeletal and obstetrics and gynaecology cases from the archives.

The Singapore Health Services cluster (SingHealth) radiology film archives are a valuable repository of local radiological cases dating back to the 1950s. Some of the cases in the archives are of historical medical interest, i.e. cerebral angiography in the workup of patients with hemiplegia. Other cases are of historical social interest, being conditions seen during earlier stages of Singapore's development, i.e. bound feet. The archives form a unique portal into the development of local radiology as well as the national development of Singapore. A selection from the archives is published in 2020 in commemoration of the 20th anniversary of the formation of SingHealth, the 55th National Day of Singapore, and the 125th anniversary of the International Day of Radiology. This pictorial essay comprises cardiovascular, respiratory and neurological cases from the archives.