Prenatal diagnosis of hypoplastic left heart syndrome on ultrasound using artificial intelligence: How does performance compare to a current screening programme?

Abstract

BackgroundArtificial intelligence (AI) has the potential to improve prenatal detection of congenital heart disease. We analysed the performance of the current national screening programme in detecting hypoplastic left heart syndrome (HLHS) to compare with our own AI model.MethodsCurrent screening programme performance was calculated from local and national sources. AI models were trained using four‐chamber ultrasound views of the fetal heart, using a ResNet classifier.ResultsEstimated current fetal screening programme sensitivity and specificity for HLHS were 94.3% and 99.985%, respectively. Depending on calibration, AI models to detect HLHS were either highly sensitive (sensitivity 100%, specificity 94.0%) or highly specific (sensitivity 93.3%, specificity 100%). Our analysis suggests that our highly sensitive model would generate 45,134 screen positive results for a gain of 14 additional HLHS cases. Our highly specific model would be associated with two fewer detected HLHS cases, and 118 fewer false positives.ConclusionIf used independently, our AI model performance is slightly worse than the performance level of the current screening programme in detecting HLHS, and this performance is likely to deteriorate further when used prospectively. This demonstrates that collaboration between humans and AI will be key for effective future clinical use.

Artificial Intelligence to Assist in the Screening Fetal Anomaly Ultrasound Scan (PROMETHEUS): A Randomised Controlled Trial

“…Previous work has also explored the use of AI to directly detect anomalies such as CHD on ultrasound images. 24,[27][28][29] The addition of such models to our current AI tool may further improve overall scan performance, but this does not come without risk, and needs to be carefully assessed. However, such model ensembles may be a powerful way of improving detection of fetuses with congenital malformations, and will be the focus of our future work.…”

“…As we have previously demonstrated, specificity is extremely important when considering the introduction of AI to screening programmes, to avoid overwhelming downstream specialist services with false positive referrals. 24 The fact that specificity remains robustly high in the AI- assisted group offers reassurance that AI tools may prevent this issue, potentially reducing false positive referrals for CHD.…”

The bright future of fetal cardiology

“…4 These data suggest that the threshold for referral for fetal echocardiography should be lower. The use of artificial intelligence (AI) to increase prenatal detection of FCHD has generated excitement, but it is not yet ready for "prime time," at least in resource-rich settings, as illustrated by the work of Day et al 5 In the context of the United Kingdom's highly sensitive and specific program for prenatal detection of hypoplastic left heart syndrome (HLHS) (94.3% and 99.98%, respectively), AI did not add value. The authors wisely underscore the need for ongoing "collaboration between humans and AI.…”