Abstract
There is a growing body of literature supporting the utilization of machine learning (ML) to improve diagnosis and prognosis tools of cardiovascular disease. The current study was to investigate the impact that the ML framework may have on the sensitivity of predicting the presence or absence of congenital heart disease (CHD) using fetal echocardiography. A comprehensive fetal echocardiogram including 2D cardiac chamber quantification, valvar assessments, assessment of great vessel morphology, and Doppler-derived blood flow interrogation was recorded. The postnatal echocardiogram was used to ascertain the diagnosis of CHD. A random forest (RF) algorithm with a nested tenfold cross-validation was used to train models for assessing the presence of CHD. The study population was derived from a database of 3910 singleton fetuses with maternal age of 28.8 ± 5.2 years and gestational age at the time of fetal echocardiography of 22.0 weeks (IQR 21–24). The proportion of CHD was 14.1% for the studied cohort confirmed by post-natal echocardiograms. Our proposed RF-based framework provided a sensitivity of 0.85, a specificity of 0.88, a positive predictive value of 0.55 and a negative predictive value of 0.97 to detect the CHD with the mean of mean ROC curves of 0.94 and the mean of mean PR curves of 0.84. Additionally, six first features, including cardiac axis, peak velocity of blood flow across the pulmonic valve, cardiothoracic ratio, pulmonary valvar annulus diameter, right ventricular end-diastolic diameter, and aortic valvar annulus diameter, are essential features that play crucial roles in adding more predictive values to the model in detecting patients with CHD. ML using RF can provide increased sensitivity in prenatal CHD screening with very good performance. The incorporation of ML algorithms into fetal echocardiography may further standardize the assessment for CHD.
Similar content being viewed by others
Data availability
Requests for data access can be sent to the corresponding author at lekimtuyen09@gmail.com or vien.truong@thechristhospital.com.
References
Hoffman JI, Kaplan S (2002) The incidence of congenital heart disease. J Am Coll Cardiol 39(12):1890–1900
Zhang YF, Zeng XL, Zhao EF, Lu HW (2015) Diagnostic value of fetal echocardiography for congenital heart disease: a systematic review and meta-analysis. Medicine (Baltimore) 94(42):e1759
Ailes EC, Gilboa SM, Honein MA, Oster ME (2015) Estimated number of infants detected and missed by critical congenital heart defect screening. Pediatrics 135(6):1000–1008
Donofrio MT, Moon-Grady AJ, Hornberger LK, Copel JA, Sklansky MS, Abuhamad A et al (2014) Diagnosis and treatment of fetal cardiac disease: a scientific statement from the American Heart Association. Circulation 129(21):2183–2242
Motwani M, Dey D, Berman DS, Germano G, Achenbach S, Al-Mallah MH et al (2017) Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis. Eur Heart J 38(7):500–507
Al’Aref SJ, Maliakal G, Singh G, van Rosendael AR, Ma X, Xu Z et al (2020) Machine learning of clinical variables and coronary artery calcium scoring for the prediction of obstructive coronary artery disease on coronary computed tomography angiography: analysis from the CONFIRM registry. Eur Heart J 41(3):359–367
Ruijsink B, Puyol-Anton E, Oksuz I, Sinclair M, Bai W, Schnabel JA et al (2020) Fully automated, quality-controlled cardiac analysis from CMR: validation and large-scale application to characterize cardiac function. JACC Cardiovasc Imaging 13(3):684–695
Zhang J, Gajjala S, Agrawal P, Tison GH, Hallock LA, Beussink-Nelson L et al (2018) Fully automated echocardiogram interpretation in clinical practice. Circulation 138(16):1623–1635
Rychik J, Ayres N, Cuneo B, Gotteiner N, Hornberger L, Spevak PJ et al (2004) American Society of Echocardiography guidelines and standards for performance of the fetal echocardiogram. J Am Soc Echocardiogr 17(7):803–810
Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140
Breiman L (2001) Random forests. Mach Learn 45(1):5–32
Oppo K, Leen E, Angerson WJ, Cooke TG, McArdle CS (1998) Doppler perfusion index: an interobserver and intraobserver reproducibility study. Radiology 208(2):453–457
Chang RK, Gurvitz M, Rodriguez S (2008) Missed diagnosis of critical congenital heart disease. Arch Pediatr Adolesc Med 162(10):969–974
Kuehl KS, Loffredo CA, Ferencz C (1999) Failure to diagnose congenital heart disease in infancy. Pediatrics 103(4 Pt 1):743–747
Mahle WT, Clancy RR, McGaurn SP, Goin JE, Clark BJ (2001) Impact of prenatal diagnosis on survival and early neurologic morbidity in neonates with the hypoplastic left heart syndrome. Pediatrics 107(6):1277–1282
Bartlett JM, Wypij D, Bellinger DC, Rappaport LA, Heffner LJ, Jonas RA et al (2004) Effect of prenatal diagnosis on outcomes in D-transposition of the great arteries. Pediatrics 113(4):e335–e340
Brown KL, Ridout DA, Hoskote A, Verhulst L, Ricci M, Bull C (2006) Delayed diagnosis of congenital heart disease worsens preoperative condition and outcome of surgery in neonates. Heart (Br Card Soc) 92(9):1298–1302
Liu H, Zhou J, Feng QL, Gu HT, Wan G, Zhang HM et al (2015) Fetal echocardiography for congenital heart disease diagnosis: a meta-analysis, power analysis and missing data analysis. Eur J Prev Cardiol 22(12):1531–1547
van Nisselrooij AEL, Teunissen AKK, Clur SA, Rozendaal L, Pajkrt E, Linskens IH et al (2020) Why are congenital heart defects being missed? Ultrasound Obstet Gynecol 55(6):747–757
Sengupta PP, Huang YM, Bansal M, Ashrafi A, Fisher M, Shameer K et al (2016) Cognitive machine-learning algorithm for cardiac imaging: a pilot study for differentiating constrictive pericarditis from restrictive cardiomyopathy. Circ Cardiovasc Imaging. 2016;9(6):e004330.
Narula S, Shameer K, Salem Omar AM, Dudley JT, Sengupta PP (2016) Machine-learning algorithms to automate morphological and functional assessments in 2D echocardiography. J Am Coll Cardiol 68(21):2287–2295
Arnaout R, Curran L, Chinn E, Zhao Y, MooŽ Grady AJ (2018) Deep-learning models improve on community-level diagnosis for common congenital heart disease lesions. ArXiv. 2018;abs/1809.06993.
Funding
The authors received no financial support for this study.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declared no potential conflicts of interest of this study.
Ethical approval
The study was approved by the hospital’s Institutional Review Board.
Informed consent
Informed consent was obtained from their parents/guardians. Assent was also obtained from children ages 7 and older.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Truong, V.T., Nguyen, B.P., Nguyen-Vo, TH. et al. Application of machine learning in screening for congenital heart diseases using fetal echocardiography. Int J Cardiovasc Imaging 38, 1007–1015 (2022). https://doi.org/10.1007/s10554-022-02566-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10554-022-02566-3