The significance of an integrated management mode of prenatal diagnosis-postnatal treatment for critical congenital heart disease in newborns

Applications of artificial intelligence-powered prenatal diagnosis for congenital heart disease

Artificial intelligence (AI) has made significant progress in the medical field in the last decade. The AI-powered analysis methods of medical images and clinical records can now match the abilities of clinical physicians. Due to the challenges posed by the unique group of fetuses and the dynamic organ of the heart, research into the application of AI in the prenatal diagnosis of congenital heart disease (CHD) is particularly active. In this review, we discuss the clinical questions and research methods involved in using AI to address prenatal diagnosis of CHD, including imaging, genetic diagnosis, and risk prediction. Representative examples are provided for each method discussed. Finally, we discuss the current limitations of AI in prenatal diagnosis of CHD, namely Volatility, Insufficiency and Independence (VII), and propose possible solutions.

Improving the Quality of Fetal Heart Ultrasound Imaging With Multihead Enhanced Self-Attention and Contrastive Learning

Fetal congenital heart disease (FCHD) is a common, serious birth defect affecting ∼1% of newborns annually. Fetal echocardiography is the most effective and important technique for prenatal FCHD diagnosis. The prerequisites for accurate ultrasound FCHD diagnosis are accurate view recognition and high-quality diagnostic view extraction. However, these manual clinical procedures have drawbacks such as, varying technical capabilities and inefficiency. Therefore, the automatic identification of high-quality multiview fetal heart scan images is highly desirable to improve prenatal diagnosis efficiency and accuracy of FCHD. Here, we present a framework for multiview fetal heart ultrasound image recognition and quality assessment that comprises two parts: a multiview classification and localization network (MCLN) and an improved contrastive learning network (ICLN). In the MCLN, a multihead enhanced self-attention mechanism is applied to construct the classification network and identify six accurate and interpretable views of the fetal heart. In the ICLN, anatomical structure standardization and image clarity are considered. With contrastive learning, the absolute loss, feature relative loss and predicted value relative loss are combined to achieve favorable quality assessment results. Experiments show that the MCLN outperforms other state-of-the-art networks by 1.52-13.61% when determining the F1 score in six standard view recognition tasks, and the ICLN is comparable to the performance of expert cardiologists in the quality assessment of fetal heart ultrasound images, reaching 97% on a test set within 2 points for the four-chamber view task. Thus, our architecture offers great potential in helping cardiologists improve quality control for fetal echocardiographic images in clinical practice.

Current status and challenges in prenatal and neonatal screening, diagnosis, and management of congenital heart disease in China

Congenital heart disease (CHD), a wide spectrum of diseases with varied outcomes, is the most common congenital malformation worldwide. In this Series of three papers, we describe the burden of CHD in China; the development of screening, diagnosis, treatment, and follow-up strategies; and challenges associated with the disease. We also propose solutions and recommendations for policies and actions to improve the outcomes of CHD. In the first paper in this Series, we focus on prenatal and neonatal screening, diagnosis, and management of CHD. Based on advanced international knowledge, the Chinese Government has developed a network system comprising prenatal screening, diagnosis of CHD subtypes, specialist consultation appointments, and treatment centres for CHD. A new professional discipline, fetal cardiology, has been formed and rapidly developed. Consequently, the overall coverage of prenatal and neonatal screening and the accuracy of CHD diagnoses have gradually improved, and the neonatal CHD mortality rate has decreased substantially. However, China still faces several challenges in the prevention and treatment of CHD, such as insufficient diagnostic capabilities and unqualified consultation services in some regions and rural areas. TRANSLATION: For the Chinese translation of the abstract see Supplementary Materials section.

The implications of an integrated management model of prenatal diagnosis/postnatal treatment for premature infants with critical congenital heart disease-a case-control study

Background

The high death rate and medical costs of critical congenital heart disease (CCHD) in preterm infants has resulted in significant burdens on both countries and individuals. It is unclear how this affects the mortality of the integrated management model of prenatal diagnosis/postnatal treatment. This study explored the effects of the delivery classification scale for fetal heart and postnatal infants' CCHD on prenatal and postnatal integrated treatment strategies to improve the effectiveness of disease management in CCHD.

Methods

This study was a case-control study, which retrospectively analyzed the clinical data of 79 preterm infants (<37 weeks) who underwent prenatal diagnosis and postpartum treatment in Guangdong Provincial People' s Hospital (China) from June 2017 to June 2019. According to the diagnostic and exclusion criteria, the subjects were divided into prenatal and postpartum diagnostic groups. The clinical characteristics and survival outcomes of patients were collected and compared. The delivery classification scale was used for risk stratification and patient management.

Results

Among the 79 patients included in this study, 48 (60.76%) were diagnosed prenatally, and 31 (39.24%) were diagnosed postpartum. The prenatal diagnosis group was born slightly earlier during the gestation period [35.00 (33.29-35.86) vs. 35.57 (34.14-36.71) weeks, P<0.05], and their mothers were older (33.23±5.22 vs. 30.43±6.37 years, P<0.05). The difference in the admission age between the groups was statistically significant [0 (0-5.5) vs. 7 (5-16) days, P<0.001]. The median survival time of the prenatal diagnosis group was higher than the postnatal diagnosis group [48 months (95% CI: 40.78-57.29) vs. 39 months (95% CI: 34.41-44.32), P<0.05]. The 3-year survival rates of the classes I, II, and III were 92.31% (12/13), 59.09% (13/22), and 38.46% (5/13), respectively. The survival of class I as denoted in the delivery classification scale was better than classes II or III (class I vs. II, P<0.05; class I vs. III, P<0.05). Unexpectedly, the hospitalisation costs were lower and total in-hospital days were shorter in the postnatal diagnosis group.

Conclusions

The results indicated that the integrated management of a prenatal diagnosis/postnatal treatment approach in premature infants may be effective. Furthermore, the delivery classification scale has a particular prognostic value for CCHD. The authors anticipate that their management model will be able to contribute to the shift from a reactive monodisciplinary system to a proactive, multidisciplinary and dynamic management paradigm in premature infants with CCHD in the near future.

Impact of prenatally diagnosed congenital heart defects on outcomes and management

Fetal echocardiogram aids in prenatal identification of neonates at high risk for congenital heart defects (CHD). Prenatal detection rates for CHD have increased with improved ultrasound technology, the use of the early fetal echocardiography, and standardization of the performance of the fetal echocardiogram. Accurate prenatal detection of CHD, particularly complex CHD, is an important contributor to improved survival rates for patients with CHD. Early detection allows for families to choose whether or not to continue with pregnancy, referral to pediatric cardiology specialists for patient education, and delivery planning. Better psychosocial supports are needed for families with CHD.