OP02.02: Multimodal nomogram for the prenatal risk assessment of hypoplastic left heart syndrome using self‐supervised learning

Early detection of HLHS is crucial for prenatal consultation and early clinical management. This retrospective study aims to develop and validate a multimodal nomogram for the prenatal risk assessment of hypoplastic left heart syndrome (HLHS) and to explore significant risk factors for HLHS. This retrospective study enrolled 161 normal pregnancies and 52 pregnancies diagnosed with HLHS at the Maternal and Child Health Hospital of Hubei Province in China from September 2019 to September 2023. Experienced sonographers selected and delineated standard four-chamber cardiac views. A Resnet-like variational autoencoder was used to extract features from four-chamber views in a self-supervised learning strategy. These features were then converted into an image score. The proposed multimodal nomogram was developed using univariate and multivariate logistic regression analysis, incorporating demographics and morphological characteristics of the fetus heart. We constructed an expert model comprising three sonographers with varying years of clinical experience and a clinical regression model. The study identified several significant risk factors for assessing the risk of HLHS. A multimodal nomogram was constructed based on these factors, achieving an accuracy of 0.905 and an AUC of 0.991. The performance of the nomogram was better than that of the traditional logistic regression model and comparable to that of the expert model. Additionally, the multimodal nomogram outperforms sonographers with 3-year and 6-year experience, and performs only slightly worse than the sonographer with 10-year experience. When combined with the heat-map generated from RVAE, the nomogram can serve as an easy-to-use tool to help clinicians better understand the process of computer-aided diagnosis. The proposed multimodal nomogram demonstrates its superiority, effectiveness and interpretability in prenatal risk assessment of HLHS. It could assist in better individual diagnosis and treatment during pregnancy.