Key result
Chest x-ray AI outperforms human observers in predicting PAH risk in children with VSD.
Why the study?
Early risk assessment of PAH in CHD patients is crucial for timely treatment, prompting evaluation of AI applied to CXRs to identify PAH risk in VSD.
Does a deep learning artificial intelligence algorithm applied to standard chest x-rays improve the prediction of pulmonary arterial hypertension in children with ventricular septal defects compared to human observers?
Cohort (n=831)
Does a deep learning artificial intelligence algorithm applied to standard chest x-rays improve the prediction of pulmonary arterial hypertension in children with ventricular septal defects compared to human observers?
Effect estimate: AUC
Absolute Event Rate: 0.81% vs 0.65%
A deep learning model applied to standard chest x-rays can effectively identify the risk of pulmonary arterial hypertension in children with ventricular septal defects, significantly outperforming human observers.
Should not yet change PAH screening in pediatric VSD; leaves open need for prospective validation of AI chest x-ray models.
Objective: Early risk assessment of pulmonary arterial hypertension (PAH) in patients with congenital heart disease (CHD) is crucial to ensure timely treatment. We hypothesize that applying artificial intelligence (AI) to chest x-rays (CXRs) could identify the future risk of PAH in patients with ventricular septal defect (VSD). Methods: A total of 831 VSD patients (161 PAH-VSD, 670 nonPAH-VSD) was retrospectively included. A residual neural networks (ResNet) was trained for classify VSD patients with different outcomes based on chest radiographs. The endpoint of this study was the occurrence of PAH in VSD children before or after surgery. Results: In the validation set, the AI algorithm achieved an area under the curve (AUC) of 0.82. In an independent test set, the AI algorithm significantly outperformed human observers in terms of AUC (0.81 vs. 0.65). Class Activation Mapping (CAM) images demonstrated the model's attention focused on the pulmonary artery segment. Conclusion: The preliminary findings of this study suggest that the application of artificial intelligence to chest x-rays in VSD patients can effectively identify the risk of PAH.
No takes yet. Share an insight, caveat, or question.
Li et al. (2024) conducted a cohort in Ventricular septal defect (n=831). Artificial intelligence (ResNet) algorithm vs. Human observers was evaluated on Occurrence of PAH in VSD children before or after surgery (AUC). An AI algorithm applied to chest x-rays significantly outperformed human observers in predicting the risk of pulmonary arterial hypertension in children with VSD (AUC 0.81 vs 0.65).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: