Leveraging artificial intelligence for predicting spontaneous closure of perimembranous ventricular septal defect in children: a multicentre, retrospective study in China.

Background: Perimembranous ventricular septal defect (PMVSD) is a prevalent congenital heart disease, presenting challenges in predicting spontaneous closure, which is crucial for therapeutic decisions. Existing models mainly rely on structured echocardiographic parameters or restricted data. This study introduces an artificial intelligence (AI)-based model, which uses natural language processing (NLP) and machine learning with the aim of improving spontaneous closure predictability in PMVSD.

Methods: We did a multicentre, retrospective analysis using data from 29 142 PMVSD patients across six tertiary centres in China from May, 2004, to September, 2022, for training (70%) and validation (30%; dataset 1, 27 269 patients), and from September, 2001, to December, 2009 for testing (dataset 2, 1873 patients). NLP extracted structured data from echocardiography reports and medical records, which were used to develop machine learning models. Models were evaluated for spontaneous closure occurrence and timing by use of area under the receiver operating characteristic curve (AUC), decision curve analysis, and calibration index.

Findings: Spontaneous closure occurred in 3520 patients (12·1%) at a median of 31 months (IQR 16-56). Eleven NLP-derived predictors, identified via least absolute shrinkage and selection operator, highlighted the importance of defect morphology and patient age. The random survival forest algorithm, selected for its superior concordance indexes, showed excellent predictive performance with validation set AUCs (95% CI) of 0·95 (0·94-0·96) for 1-year and 3-year predictions, and 0·95 (0·95-0·96) for 5-year predictions; testing set AUCs were 0·95 (0·94-0·97) for 1-year predictions, 0·97 (0·96-0·98) for 3-year predictions, and 0·98 (0·97-0·99) for 5-year predictions. The model showed high clinical utility through decision curve analysis, calibration, and risk stratification, maintaining consistent accuracy across centres and subgroups.

Interpretation: This AI-based model for predicting spontaneous closure in PMVSD patients represents a substantial advancement, potentially improving patient management, reducing risks of delayed or inappropriate treatment, and enhancing clinical outcomes.

Funding: National Natural Science Foundation of China, Shanghai Municipal Hospital Clinical Technology Project, Shanghai Municipal Health Commission, and Clinical Research Unit of XinHua Hospital.