Prenatal detection of critical cardiac outflow tract anomalies remains suboptimal despite revised obstetrical imaging guidelines

Sun, Heather Y.; Proudfoot, James; McCandless, Rachel T.

doi:10.1111/chd.12648

Cited by 55 publications

(43 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Education of obstetrical sonographers and practitioners who perform fetal anatomic screening is vital to increase referrals and prenatal detection of critical outflow tract anomalies. 28 In the present study, differently from international studies, the cardiac malformation diagnosis in most cases was obtained in the third trimester, which was possibly a reflex of the health conditions in our region, where echography is performed later on, as well as the pregnancy diagnosis, also making it difficult the access to tertiary services.…”

Section: Discussionmentioning

confidence: 55%

Accuracy of Prenatal Diagnosis of Congenital Cardiac Malformations

Pinheiro

Varisco

Silva³

et al. 2018

Rev Bras Ginecol Obstet

View full text Add to dashboard Cite

Objective To evaluate the accuracy of the diagnosis of fetal heart diseases obtained through ultrasound examinations performed during the prenatal period compared with the postnatal evaluation. Methods A retrospective cohort study with 96 pregnant women who were attended at the Echocardiography Service and whose deliveries occurred at the Complexo Hospitalar Santa Casa de Porto Alegre, in the state of Rio Grande do Sul, Brazil. Risk factor assessment plus sensitivity and specificity analysis were used, comparing the accuracy of the screening for congenital heart disease by means of obstetrical ultrasound and morphological evaluation and fetal echocardiography, considering p < 0.05 as significant. The present study was approved by the Research Ethics Committee of the Institution. Results The analysis of risk factors shows that 31.3% of the fetuses with congenital heart disease could be identified by anamnesis. The antepartum echocardiography demonstrated a sensitivity of 97.7%, a specificity of 88.9%, and accuracy of 93% in the diagnosis of congenital heart disease. A sensitivity of 29.3% was found for the obstetric ultrasound, of 54.3% for the morphological ultrasound, and of 97.7% for the fetal echocardiography. The fetal echocardiography detected fetal heart disease in 67.7% of the cases, the morphological ultrasound in 16.7%, and the obstetric ultrasound in 11.5% of the cases. Conclusion There is a high proportion of congenital heart disease in pregnancies with no risk factors for this outcome. Faced with the disappointing results of obstetric ultrasound for the detection of congenital heart diseases and the current unfeasibility of universal screening of congenital heart diseases through fetal echocardiography, the importance of the fetal morphological ultrasound and its performance by qualified professionals is reinforced for a more appropriate management of these pregnancies.

show abstract

Section: Discussionmentioning

confidence: 55%

Accuracy of Prenatal Diagnosis of Congenital Cardiac Malformations

Pinheiro

Varisco

Silva³

et al. 2018

Rev Bras Ginecol Obstet

View full text Add to dashboard Cite

show abstract

“…11 Despite these revised guidelines stressing the importance of outflow tract imaging, prenatal diagnosis of outflow tract anomalies remains low and suboptimal. 11 Many cases of CHD occur in otherwise low-risk pregnancies, relying primarily on the screening anatomic ultrasound to detect abnormalities. 11 Without surgical correction, survival beyond the first year of life is uncommon.…”

Section: Discussionmentioning

confidence: 99%

“…11 Many cases of CHD occur in otherwise low-risk pregnancies, relying primarily on the screening anatomic ultrasound to detect abnormalities. 11…”

Section: Discussionmentioning

confidence: 99%

The Use of Sonography in a Mother and Fetus With Concordant Truncus Arteriosus

Fyock

Downs

2019

Journal of Diagnostic Medical Sonography

View full text Add to dashboard Cite

Reported pregnancies in women with repaired truncus arteriosus are rare. As a result of improved surgical techniques, more women with conotruncal defects are now reaching reproductive age. Multifactorial inheritance rather than single gene mutation is the causative agent of most congenital heart disease. The environment can play an important and varied role in direct transmission, particularly in incidences where genes predispose a defect. This may be one of the first reported cases discussing a pregnant mother with repaired truncus arteriosus and her fetus, prenatally diagnosed with a concordant truncal defect.

show abstract

“…Two reasons for this gap between possible and commonplace CHD detection are (i) inadequate expertise in interpretation and/or (ii) inadequate acquisition of diagnostic-quality images 16,17 .…”

Section: Introductionmentioning

confidence: 99%

Expert-level prenatal detection of complex congenital heart disease from screening ultrasound using deep learning

Arnaout

Curran

Zhao

et al. 2020

Preprint

View full text Add to dashboard Cite

Congenital heart disease (CHD) is the most common birth defect. Fetal survey ultrasound is recommended worldwide, including five views of the heart that together could detect 90% of complex CHD. In practice, however, sensitivity is as low as 30%. We hypothesized poor detection results from challenges in acquiring and interpreting diagnostic-quality cardiac views, and that deep learning could improve complex CHD detection. Using 107,823 images from 1,326 retrospective echocardiograms and surveys from 18-24 week fetuses, we trained an ensemble of neural networks to (i) identify recommended cardiac views and (ii) distinguish between normal hearts and complex CHD. Finally, (iii) we used segmentation models to calculate standard fetal cardiothoracic measurements. In a test set of 4,108 fetal surveys (0.9% CHD, >4.4 million images, about 400 times the size of the training dataset) the model achieved an AUC of 0.99, 95% sensitivity (95%CI, 84-99), 96% specificity (95%CI, 95-97), and 100% NPV in distinguishing normal from abnormal hearts. Sensitivity was comparable to clinicians' task-for-task and remained robust on external 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 guidelines-recommended imaging, ensemble learning models could significantly improve detection of fetal CHD and expand telehealth options for prenatal care at a time when the COVID-19 pandemic has further limited patient access to trained providers. This is the first use of deep learning to approximately double standard clinical performance on a critical and global diagnostic challenge.

show abstract

Prenatal detection of critical cardiac outflow tract anomalies remains suboptimal despite revised obstetrical imaging guidelines

Cited by 55 publications

References 39 publications

Accuracy of Prenatal Diagnosis of Congenital Cardiac Malformations

Accuracy of Prenatal Diagnosis of Congenital Cardiac Malformations

The Use of Sonography in a Mother and Fetus With Concordant Truncus Arteriosus

Expert-level prenatal detection of complex congenital heart disease from screening ultrasound using deep learning

Contact Info

Product

Resources

About