Related Experiment Video
Updated: Oct 26, 2025
Fetal Mouse Cardiovascular Imaging Using a High-frequency Ultrasound 30/45MHZ System
Published on: May 5, 2018
Diagnostic Accuracy of Machine Learning Models to Identify Congenital Heart Disease: A Meta-Analysis
Zahra Hoodbhoy1, Uswa Jiwani1, Saima Sattar1
1Department of Pediatrics and Child Health at the Aga Khan University, Karachi, Pakistan.
Insights
Machine learning models, particularly neural networks, show high accuracy in diagnosing congenital heart disease (CHD). This technology offers a promising solution for accurate CHD detection, even with limited trained healthcare professionals.
Area of Science:
- Medical Informatics
- Cardiology
- Artificial Intelligence
Background:
- Shortage of trained professionals for congenital heart disease (CHD) diagnosis.
- Increasing development and application of machine learning (ML) models in healthcare.
Purpose of the Study:
- To estimate the diagnostic accuracy of ML models for detecting CHD.
- To synthesize evidence on ML's performance in CHD diagnosis.
Main Methods:
- Comprehensive literature search across major databases (PubMed, CINAHL, Wiley Cochrane Library, Web of Science).
- Inclusion of studies reporting ML diagnostic ability for CHD against a reference standard.
- Risk of bias assessment using QUADAS-2 and HSROC curve generation for meta-analysis.
Main Results:
- 16 studies with 1217 participants were included.
- Neural networks demonstrated high diagnostic accuracy: 90.9% sensitivity and 92.7% specificity.
- Significant risks of bias were noted in patient selection, index test, and flow/timing across studies.
Conclusions:
- ML models, especially neural networks, show potential for accurate CHD diagnosis.
- ML can aid in CHD detection where trained personnel are scarce.
- Heterogeneity in training data and diagnostic criteria presents a key limitation.
Abstract:
Background: With the dearth of trained care providers to diagnose congenital heart disease (CHD) and a surge in machine learning (ML) models, this review aims to estimate the diagnostic accuracy of such models for detecting CHD. Methods: A comprehensive literature search in the PubMed, CINAHL, Wiley Cochrane Library, and Web of Science databases was performed. Studies that reported the diagnostic ability of ML for the detection of CHD compared to the reference standard were included. Risk of bias assessment was performed using Quality Assessment for Diagnostic Accuracy Studies-2 tool. The sensitivity and specificity results from the studies were used to generate the hierarchical Summary ROC (HSROC) curve. Results: We included 16 studies (1217 participants) that used ML algorithm to diagnose CHD. Neural networks were used in seven studies with overall sensitivity of 90.9% (95% CI 85.2-94.5%) and specificity was 92.7% (95% CI 86.4-96.2%). Other ML models included ensemble methods, deep learning and clustering techniques but did not have sufficient number of studies for a meta-analysis. Majority (n=11, 69%) of studies had a high risk of patient selection bias, unclear bias on index test (n=9, 56%) and flow and timing (n=12, 75%) while low risk of bias was reported for the reference standard (n=10, 62%). Conclusion: ML models such as neural networks have the potential to diagnose CHD accurately without the need for trained personnel. The heterogeneity of the diagnostic modalities used to train these models and the heterogeneity of the CHD diagnoses included between the studies is a major limitation.
