An ensemble of neural networks provides expert-level prenatal detection of complex congenital heart disease
Top Cited Papers
- 14 May 2021
- journal article
- research article
- Published by Springer Science and Business Media LLC in Nature Medicine
- Vol. 27 (5), 882-891
- https://doi.org/10.1038/s41591-021-01342-5
Abstract
Congenital heart disease (CHD) is the most common birth defect. Fetal screening ultrasound provides five views of the heart that together can detect 90% of complex CHD, but in practice, sensitivity is as low as 30%. Here, using 107,823 images from 1,326 retrospective echocardiograms and screening ultrasounds from 18- to 24-week fetuses, we trained an ensemble of neural networks to identify recommended cardiac views and distinguish between normal hearts and complex CHD. We also used segmentation models to calculate standard fetal cardiothoracic measurements. In an internal test set of 4,108 fetal surveys (0.9% CHD, >4.4 million images), the model achieved an area under the curve (AUC) of 0.99, 95% sensitivity (95% confidence interval (CI), 84–99%), 96% specificity (95% CI, 95–97%) and 100% negative predictive value in distinguishing normal from abnormal hearts. Model sensitivity was comparable to that of clinicians and remained robust on outside-hospital and lower-quality images. The model’s decisions were based on clinically relevant features. Cardiac measurements correlated with reported measures for normal and abnormal hearts. Applied to guideline-recommended imaging, ensemble learning models could significantly improve detection of fetal CHD, a critical and global diagnostic challenge.Keywords
Funding Information
- U.S. Department of Health & Human Services | National Institutes of Health (R01HL150394)
- U.S. Department of Defense (W81XWH-19-1-0294)
- American Heart Association (17IGMV33870001)
This publication has 49 references indexed in Scilit:
- Diagnosis and Treatment of Fetal Cardiac DiseaseJournal of the American College of Cardiology, 2014
- Relation of Prenatal Diagnosis With One-Year Survival Rate for Infants With Congenital Heart DiseaseThe American Journal of Cardiology, 2014
- A Population-Based Study of the Association of Prenatal Diagnosis With Survival Rate for Infants With Congenital Heart DefectsThe American Journal of Cardiology, 2013
- Distal Pectoralis Major TearsJournal of Ultrasound in Medicine, 2013
- Diagnosis of congenital heart disease in an era of universal prenatal ultrasound screening in southwest OhioCardiology in the Young, 2013
- AIUM Practice Guideline for the Performance of Fetal EchocardiographyJournal of Ultrasound in Medicine, 2013
- ISUOG Practice Guidelines (updated): sonographic screening examination of the fetal heartUltrasound in Obstetrics & Gynecology, 2013
- Prenatal Detection of Congenital Heart DiseaseThe Journal of Pediatrics, 2009
- Evaluation of fetal cardiac contractility by two-dimensional ultrasonographyPrenatal Diagnosis, 2004
- Examination of the fetal heart by five short‐axis views: a proposed screening method for comprehensive cardiac evaluationUltrasound in Obstetrics & Gynecology, 2001