Artificial intelligence-assisted diagnosis of congenital heart disease and associated pulmonary arterial hypertension from chest radiographs: A multi-reader multi-case study

Objectives: To explore the possibility of automatic diagnosis of congenital heart disease (CHD) and pulmonary arterial hypertension associated with CHD (PAH-CHD) from chest radiographs using artificial intelligence (AI) technology and to evaluate whether AI assistance could improve clinical diagnostic accuracy. Materials and Methods: A total of 3255 frontal preoperative chest radiographs (1174 CHD of any type and 2081 non-CHD) were retrospectively obtained. In this study, we adopted ResNet18 pretrained with the ImageNet database to establish diagnostic models. Radiologists diagnosed CHD/PAH-CHD from 330/165 chest radiographs twice: the first time, 50% of the images were accompanied by AI-based classification; after a month, the remaining 50% were accompanied by AI-based classification. Diagnostic results were compared between the radiologists and AI models, and between radiologists with and without AI assistance. Results: The AI model achieved an average area under the receiver operating characteristic curve (AUC) of 0.948 (sensitivity: 0.970, specificity: 0.982) for CHD diagnoses and an AUC of 0.778 (sensitivity: 0.632, specificity: 0.925) for identifying PAH-CHD. In the 330 balanced (165 CHD and 165 non-CHD) testing set, AI achieved higher AUCs than all 5 radiologists in the identification of CHD (0.670-0.858) and PAH-CHD (0.610-0.688). With AI assistance, the mean +/- standard error AUC of radiologists was significantly improved for CHD (Delta AUC + 0.096, 95 % CI: 0.001-0.190; P = 0.048) and PAH-CHD (Delta AUC + 0.066, 95 % CI: 0.010-0.122; P = 0.031) diagnosis. Conclusion: Chest radiograph-based AI models can detect CHD and PAH-CHD automatically. AI assistance improved radiologists' diagnostic accuracy, which may facilitate a timely initial diagnosis of CHD and PAH-CHD.