Deep-learning model for prenatal congenital heart disease screening generalizes to community setting and outperforms clinical detection

Computer-aided assessment for enlarged fetal heart with deep learning model

Enlarged fetal heart conditions may indicate congenital heart diseases or other complications, making early detection through prenatal ultrasound essential. However, manual assessments by sonographers are often subjective, time-consuming, and inconsistent. This paper proposes a deep learning approach using the You Only Look Once (YOLO) architecture to automate fetal heart enlargement assessment. Using a set of ultrasound videos, YOLOv8 with a CBAM module demonstrated superior performance compared to YOLOv11 with self-attention. Incorporating the ResNeXtBlock-a residual network with cardinality-additionally enhanced accuracy and prediction consistency. The model exhibits strong capability in detecting fetal heart enlargement, offering a reliable computer-aided tool for sonographers during prenatal screenings. Further validation is required to confirm its clinical applicability. By improving early and accurate detection, this approach has the potential to enhance prenatal care, facilitate timely interventions, and contribute to better neonatal health outcomes.

Indications for fetal echocardiography: consensus and controversies among evidence-based national and international guidelines

OBJECTIVE

Fetal echocardiography (FE) is an indication-driven examination for pregnant women with a fetus at high risk for congenital heart disease (CHD). Several familial, maternal and fetal factors are reported to increase the risk of CHD. The aim of this study was to highlight the existing differences in recommended indications for FE among recently published guidelines and consensuses of experts.

METHODS

Guidelines and expert consensuses published from January 2008 to October 2023 were identified through a systematic literature search. FE guidelines and consensus statements were excluded if not written in the English language and if indications for FE were not reported. All familial, maternal and fetal risk factors for CHD reported in the consensuses and guidelines were listed and comparisons were made between documents. The agreement or disagreement for each risk factor between guidelines and consensuses was classified as: complete agreement (all analyzed documents reported the same indication); partial agreement (all documents considered a risk factor as an indication, but with inconsistency in its definition); or complete disagreement (inconsistency between documents for the considered risk factor as an indication).

RESULTS

Six guidelines and expert consensuses that met the inclusion criteria were identified. Overall, a total of 17 risk factors were identified as an indication for FE. Complete agreement was reached for 3/17 (17.6%) risk factors, all of which are fetal risk factors (suspected CHD at the anomaly scan, presence of major fetal extracardiac abnormality and non-immune hydrops fetalis). Partial agreement was recorded for 8/17 (47.1%) risk factors (family history of CHD, increased nuchal translucency, multiple gestation, maternal diabetes mellitus, maternal phenylketonuria, maternal infection, maternal autoimmune disease and autoantibody positivity, and teratogen exposure). Complete disagreement was recorded for 6/17 (35.3%) risk factors (inherited genetic disease associated with CHD, fetal genetic anomaly, suspected abnormality of heart rate or rhythm, first-trimester sonographic markers of CHD, abnormality of umbilical cord and venous system, and use of assisted reproductive technology).

CONCLUSIONS

Areas of controversy regarding which CHD risk factors warrant FE were greater in quantity than were the areas of consensus. An internationally standardized agreement would be valuable for physicians and guideline developers. For many risk factors, further evidence is needed to justify their use as an indication for FE. © 2025 International Society of Ultrasound in Obstetrics and Gynecology.

Artificial Intelligence-Assisted Echocardiographic Image-Analysis for the Diagnosis of Fetal Congenital Heart Disease: A Systematic Review and Meta-Analysis

Background

To assess the precision of artificial intelligence (AI) in aiding the diagnostic process of congenital heart disease (CHD).

Methods

PubMed, Embase, Cochrane, and Web of Science databases were searched for clinical studies published in English up to March 2024. Studies using AI-assisted ultrasound for diagnosing CHD were included. To evaluate the quality of the studies included in the analysis, the Quality Assessment Tool for Diagnostic Accuracy Studies-2 scale was employed. The overall accuracy of AI-assisted imaging in the diagnosis of CHD was determined using Stata15.0 software. Subgroup analyses were conducted based on region and model architecture.

Results

The analysis encompassed a total of 7 studies, yielding 19 datasets. The combined sensitivity was 0.93 (95% confidence interval (CI): 0.88-0.96), and the specificity was 0.93 (95% CI: 0.88-0.96). The positive likelihood ratio was calculated as 13.0 (95% CI: 7.7-21.9), and the negative likelihood ratio was 0.08 (95% CI: 0.04-0.13). The diagnostic odds ratio was 171 (95% CI: 62-472). The summary receiver operating characteristic (SROC) curve analysis revealed an area under the curve of 0.98 (95% CI: 0.96-0.99). Subgroup analysis found that the ResNet and DenNet architecture models had better diagnostic performance than other models.

Conclusions

AI demonstrates considerable value in aiding the diagnostic process of CHD. However, further prospective studies are required to establish its utility in real-world clinical practice.

The PROSPERO registration

CRD42024540525, https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=540525.

The Artificial Intelligence-Enhanced Echocardiographic Detection of Congenital Heart Defects in the Fetus: A Mini-Review

Artificial intelligence (AI) is rapidly gaining attention in radiology and cardiology for accurately diagnosing structural heart disease. In this review paper, we first outline the technical background of AI and echocardiography and then present an array of clinical applications, including image quality control, cardiac function measurements, defect detection, and classifications. Collectively, we answer how integrating AI technologies and echocardiography can help improve the detection of congenital heart defects. Particularly, the superior sensitivity of AI-based congenital heart defect (CHD) detection in the fetus (>90%) allows it to be potentially translated into the clinical workflow as an effective screening tool in an obstetric setting. However, the current AI technologies still have many limitations, and more technological developments are required to enable these AI technologies to reach their full potential. Also, integrating diagnostic AI technologies into the clinical workflow should resolve ethical concerns. Otherwise, deploying diagnostic AI may not address low-resource populations' healthcare access disadvantages. Instead, it will further exacerbate the access disparities. We envision that, through the combination of tele-echocardiography and AI, low-resource medical facilities may gain access to the effective detection of CHD at the prenatal stage.

Artificial Intelligence and Machine Learning: An Updated Systematic Review of Their Role in Obstetrics and Midwifery

Artificial intelligence (AI) and machine learning (ML) are rapidly evolving technologies with significant implications in obstetrics and midwifery. This systematic review aims to evaluate the latest advancements in AI and ML applications in obstetrics and midwifery. A search was conducted in three electronic databases (PubMed, Scopus, and Web of Science) for studies published between January 1, 2022, and February 20, 2025, using keywords related to AI, ML, obstetrics, and midwifery. The review adhered to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines for updated systematic reviews. Studies were selected based on their focus on AI/ML applications in obstetrics and midwifery, while non-English publications and review studies were excluded. The review included 64 studies, highlighting significant advancements in AI and ML applications across various domains in obstetrics and midwifery. Findings indicate that AI and ML models and systems achieved high accuracy in areas, such as assisted reproduction, diagnosis (e.g., 3D/4D ultrasound and MRI), pregnancy risk assessment (e.g., preeclampsia, gestational diabetes, preterm birth), fetal monitoring, mode of birth, and perinatal outcomes (e.g., mortality rates, postpartum hemorrhage, hypertensive disorders, neonatal respiratory distress). AI and ML have significant potential in transforming obstetric and midwifery care. The great number of studies reporting significant improvements suggests that the widespread adoption of AI and ML in these fields is imminent. Interdisciplinary collaboration between clinicians, data scientists, and policymakers will be crucial in shaping the future of maternal and neonatal healthcare.

Artificial Intelligence in Fetal and Pediatric Echocardiography

Echocardiography is the main modality in diagnosing acquired and congenital heart disease (CHD) in fetal and pediatric patients. However, operator variability, complex image interpretation, and lack of experienced sonographers and cardiologists in certain regions are the main limitations existing in fetal and pediatric echocardiography. Advances in artificial intelligence (AI), including machine learning (ML) and deep learning (DL), offer significant potential to overcome these challenges by automating image acquisition, image segmentation, CHD detection, and measurements. Despite these promising advancements, challenges such as small number of datasets, algorithm transparency, physician comfort with AI, and accessibility must be addressed to fully integrate AI into practice. This review highlights AI's current applications, challenges, and future directions in fetal and pediatric echocardiography.

The Holy Grail of obstetric ultrasound: can artificial intelligence detect hard-to-identify fetal cardiac anomalies?

Linked article: This Editorial comments on articles by Day et al. and Taksøe‐Vester et al.

Precision Medicine in Congenital Heart Disease, Rheumatic Heart Disease, and Kawasaki Disease of Children: An Overview of Literature

Congenital heart disease and common acquired heart diseases like Kawasaki disease and rheumatic heart disease are prevalent cardiovascular conditions in children worldwide. Despite the availability of treatment options, they continue to be significant contributors to morbidity and mortality. Advancements in early diagnosis, improvements in treatment approaches, and overcoming resistance to available treatments are crucial to reduce morbidity. Researchers have turned to precision medicine to tackle these challenges. We aimed to analyze the existing literature concerning the utilization of precision medicine in congenital heart disease, rheumatic heart disease, and Kawasaki disease. The emphasis is placed on comprehending the key themes explored in these studies and evaluating the present state of their clinical integration. The central theme of most studies revolves around the examination of genetic factors. Despite promising research outcomes, limitations in these studies indicate that the clinical implementation of precision medicine in these conditions remains a distant prospect, necessitating additional exploration and attention to confounding factors.

Advances in the Application of Artificial Intelligence in Fetal Echocardiography

Congenital heart disease is a severe health risk for newborns. Early detection of abnormalities in fetal cardiac structure and function during pregnancy can help patients seek timely diagnostic and therapeutic advice, and early intervention planning can significantly improve fetal survival rates. Echocardiography is one of the most accessible and widely used diagnostic tools in the diagnosis of fetal congenital heart disease. However, traditional fetal echocardiography has limitations due to fetal, maternal, and ultrasound equipment factors and is highly dependent on the skill level of the operator. Artificial intelligence (AI) technology, with its rapid development utilizing advanced computer algorithms, has great potential to empower sonographers in time-saving and accurate diagnosis and to bridge the skill gap in different regions. In recent years, AI-assisted fetal echocardiography has been successfully applied to a wide range of ultrasound diagnoses. This review systematically reviews the applications of AI in the field of fetal echocardiography over the years in terms of image processing, biometrics, and disease diagnosis and provides an outlook for future research.