Current status of screening, diagnosis, and treatment of neonatal congenital heart disease in China

The combination of deep learning and pseudo-MS image improves the applicability of metabolomics to congenital heart defect prenatal screening

To investigate the metabolic alterations in maternal individuals with fetal congenital heart disease (FCHD), establish the FCHD diagnostic models, and assess the performance of these models, we recruited two batches of pregnant women. By metabolomics analysis using Ultra High-performance Liquid Chromatography-Mass/Mass (UPLC-MS/MS), a total of 36 significantly altered metabolites (VIP >1.0) were identified between FCHD and non-FCHD groups. Two logistic regression models and four support vector machine (SVM) models exhibited strong performance and clinical utility in the training set (area under the curve (AUC) = 1.00). The convolutional neural network (CNN) model also demonstrated commendable performance and clinical utility (AUC = 0.89 in the training set). Notably, in the validation set, the performance of the CNN model (AUC = 0.66, precision = 0.714) exhibited better robustness than the six models above (AUC≤0.50). In conclusion, the CNN model based on pseudo-MS images holds promise for real-world and clinical applications due to its better repeatability.

Trend of Mortality Due to Congenital Anomalies in Children Younger Than 5 Years in Eastern China, 2012-2021: Surveillance Data Analysis

BACKGROUND

As one of the leading causes of child mortality, deaths due to congenital anomalies (CAs) have been a prominent obstacle to meet Sustainable Development Goal 3.2.

OBJECTIVE

We conducted this study to understand the death burden and trend of under-5 CA mortality (CAMR) in Zhejiang, one of the provinces with the best medical services and public health foundations in Eastern China.

METHODS

We used data retrieved from the under-5 mortality surveillance system in Zhejiang from 2012 to 2021. CAMR by sex, residence, and age group for each year was calculated and standardized according to 2020 National Population Census sex- and residence-specific live birth data in China. Poisson regression models were used to estimate the annual average change rate (AACR) of CAMR and to obtain the rate ratio between subgroups after adjusting for sex, residence, and age group when appropriate.

RESULTS

From 2012 to 2021, a total of 1753 children died from CAs, and the standardized CAMR declined from 121.2 to 62.6 per 100,000 live births with an AACR of -9% (95% CI -10.7% to -7.2%; P<.001). The declining trend was also observed in female and male children, urban and rural children, and neonates and older infants, and the AACRs were -9.7%, -8.5%, -8.5%, -9.2%, -12%, and -6.3%, respectively (all P<.001). However, no significant reduction was observed in children aged 1-4 years (P=.22). Generally, the CAMR rate ratios for male versus female children, rural versus urban children, older infants versus neonates, and older children versus neonates were 1.18 (95% CI 1.08-1.30; P<.001), 1.20 (95% CI 1.08-1.32; P=.001), 0.66 (95% CI 0.59-0.73; P<.001), and 0.20 (95% CI 0.17-0.24; P<.001), respectively. Among all broad CA groups, circulatory system malformations, mainly deaths caused by congenital heart diseases, accounted for 49.4% (866/1753) of deaths and ranked first across all years, although it declined yearly with an AACR of -9.8% (P<.001). Deaths due to chromosomal abnormalities tended to grow in recent years, although the AACR was not significant (P=.90).

CONCLUSIONS

CAMR reduced annually, with cardiovascular malformations ranking first across all years in Zhejiang, China. Future research and practices should focus more on the prevention, early detection, long-term management of CAs and comprehensive support for families with children with CAs to improve their survival chances.

Clinical characteristics and outcomes of patients who underwent neonatal cardiac surgery: ten years of experience in a tertiary surgery center

OBJECTIVE

To evaluate the outcomes after neonatal cardiac surgery at our institute, and identify factors associated with operative mortality.

METHODS

We examined 224 neonates who underwent cardiac surgery at a single institution from 2013 to 2022. Relevant data, such as demographic information, operative details, and postoperative records, were gathered from medical and surgical records. Our primary focus was on the operative mortality.

RESULTS

Median age and weight at surgery were 12 (7-20) days and 3.4 (3.0-3.8) kg, respectively. Overall mortality was 14.3% (32/224). Mortality rates showed improvement over time (2013-2017 vs. 2018-2022), with rates decreasing from 21.9% to 10.6% (p = 0.023). ECMO use, extubation failure, lactate > 4.8 mmol/l and VIS > 15.5 on 24 h after operation were significantly associated with operative mortality, according to multivariate logistic regression analysis. Patients admitted to the cardiac intensive care unit (CICU) before surgery and those with prenatal diagnosis showed lower operative mortality. Median follow-up time of 192 hospital survivors was 28.0 (11.0-62.3) months. 10 patients experienced late deaths, and 7 patients required reinterventions after neonatal cardiac surgery. Risk factors for composite end-point of death and reintervention on multivariable analysis were: surgical period (HR = 0.230, 95% CI 0.081-0.654; p = 0.006), prolonged ventilation (HR = 4.792, 95% CI 1.296-16.177; p = 0.018) and STAT categories 3-5 (HR = 5.936, 95% CI 1.672-21.069; p = 0.006).

CONCLUSIONS

Our institution has observed improved surgical outcomes in neonatal cardiac surgery over the past five years with low mortality, but late death and reintervention remain necessary in some patients. The location and prenatal diagnosis prior to surgery may affect the outcomes of neonates undergoing congenital heart disease operations.

Risk factors and incidence of postoperative delirium after cardiac surgery in children: a systematic review and meta-analysis

Delirium, a form of acute cerebral dysfunction, is a common complication of postoperative cardiac surgery in children. It is strongly associated with adverse outcomes, including prolonged hospitalization, increased mortality, and cognitive dysfunction. This study aimed to identify risk factors and incidence of delirium after cardiac surgery in children to facilitate early identification of delirium risk and provide a reference for the implementation of effective prevention and management. A systematic literature search was conducted in PubMed, Web of Science, Embase, Cochrane Library, Scopus, CNKI, Sinomed, and Wanfang for studies published in English or Chinese from the inception of each database to November 2023. The PRISMA guidelines were followed in all phases of this systematic review. The Risk of Bias Assessment for Nonrandomized Studies tool was used to assess methodological quality. A total of twelve studies were included in the analysis, with four studies classified as overall low risk of bias, seven studies as moderate risk of bias, and one study as high risk of bias. The studies reported 39 possible predictors of delirium, categorized into four broad groups: intrinsic and parent-related factors, disease-related factors, surgery and treatment-related factors, and clinical scores and laboratory parameters. By conducting qualitative synthesis and quantitative meta-analysis, we identified two definite factors, four possible factors, and 32 unclear factors related to delirium. Definite risk factors included age and mechanical ventilation duration. Possible factors included developmental delay, cyanotic heart disease, cardiopulmonary bypass time, and pain score. With only a few high-quality studies currently available, well-designed and more extensive prospective studies are still needed to investigate the risk factors affecting delirium and explore delirium prevention strategies in high-risk children.

Machine learning prediction model of major adverse outcomes after pediatric congenital heart surgery-a retrospective cohort study

BACKGROUND

Major adverse postoperative outcomes (APOs) can greatly affect mortality, hospital stay, care management and planning, and quality of life. This study aimed to evaluate the performance of five machine learning (ML) algorithms for predicting four major APOs after pediatric congenital heart surgery and their clinically meaningful model interpretations.

METHODS

Between August 2014 and December 2021, 23,000 consecutive pediatric patients receiving congenital heart surgery were enrolled. Based on the split date of 1 January 2019, we selected 13,927 participants for the training cohort, and 9,073 participants for the testing cohort. Four predefined major APOs including low cardiac output syndrome (LCOS), pneumonia, renal failure, and deep venous thrombosis (DVT) were investigated. 39 clinical and laboratory features were inputted in five ML models: light gradient boosting machine (LightGBM), logistic regression (LR), support vector machine, random forest, and CatBoost. The performance and interpretations of ML models were evaluated using the area under the receiver operating characteristic curve (AUC) and Shapley Additive Explanations (SHAP).

RESULTS

In the training cohort, CatBoost algorithms outperformed others with the mean AUCs of 0.908 for LCOS and 0.957 for renal failure, while LightGBM and LR achieved the best mean AUCs of 0.886 for pneumonia and 0.942 for DVT, respectively. In the testing cohort, the best-performing ML model for each major APOs with the following mean AUCs: LCOS (LightGBM), 0.893 (95% confidence interval (CI), 0.884-0.895); pneumonia (LR), 0.929 (95% CI, 0.926-0.931); renal failure (LightGBM), 0.963 (95% CI, 0.947-0.979), and DVT (LightGBM), 0.970 (95% CI, 0.953-0.982). The performance of ML models using only clinical variables was slightly lower than those using combined data, with the mean AUCs of 0.873 for LCOS, 0.894 for pneumonia, 0.953 for renal failure, and 0.933 for DVT. The SHAP showed that mechanical ventilation time was the most important contributor of four major APOs.

CONCLUSIONS

In pediatric congenital heart surgery, the established ML model can accurately predict the risk of four major APOs, providing reliable interpretations for high-risk contributor identification and informed clinical decisions making.

Association of Maternal Folate Intake and Offspring MTHFD1 and MTHFD2 Genes with Congenital Heart Disease

Existing evidence supported that congenital heart defect (CHD) was associated with a combination of environmental and genetic factors. Based on this, this study aimed at assessing the association of maternal folic acid supplementation (FAS), genetic variations in offspring methylenetetrahydrofolate dehydrogenase (MTHFD)1 and MTHFD2 genes, and their interactions with CHD and its subtypes. A hospital-based case-control study, including 620 cases with CHD and 620 healthy children, was conducted. This study showed that the absence of FAS was significantly associated with an increased risk of total CHD and its subtypes, such as atrial septal defect (ASD). FAS during the first and second trimesters was associated with a significantly higher risk of CHD in offspring compared to FAS during the three months prior to conception. The polymorphisms of offspring MTHFD1 and MTHFD2 genes at rs2236222, rs11849530, and rs828858 were significantly associated with the risk of CHD. Additionally, a significantly positive interaction between maternal FAS and genetic variation at rs828858 was observed for the risk of CHD. These findings suggested that pregnant women should carefully consider the timing of FAS, and individuals with higher genetic risk may benefit from targeted folic acid supplementation as a preventive measure against CHD.

Current treatment outcomes of congenital heart disease and future perspectives

China has the largest number of individuals with congenital heart disease (CHD) in the world and a heavy burden of CHD. Therefore, understanding current CHD treatment outcomes and patterns in China will contribute to global progress in CHD treatment and be a valuable experience. Generally, CHD treatment in China has satisfactory outcomes owing to the joint efforts by all relevant stakeholders across the country. However, efforts are needed to overcome the remaining challenges: management of mitral valve disease and paediatric end-stage heart failure needs to be improved; cohesive paediatric cardiology teams should be established and collaboration between hospitals enhanced; CHD-related medical resources need to be more accessible and equitable; and nationwide CHD databases should be enhanced. In the second paper of this Series, we aim to systematically summarise the current CHD treatment outcomes in China, discuss potential solutions, and provide future perspectives.

Artificial Intelligence in Pediatric Cardiology: A Scoping Review

The evolution of AI and data science has aided in mechanizing several aspects of medical care requiring critical thinking: diagnosis, risk stratification, and management, thus mitigating the burden of physicians and reducing the likelihood of human error. AI modalities have expanded feet to the specialty of pediatric cardiology as well. We conducted a scoping review searching the Scopus, Embase, and PubMed databases covering the recent literature between 2002-2022. We found that the use of neural networks and machine learning has significantly improved the diagnostic value of cardiac magnetic resonance imaging, echocardiograms, computer tomography scans, and electrocardiographs, thus augmenting the clinicians' diagnostic accuracy of pediatric heart diseases. The use of AI-based prediction algorithms in pediatric cardiac surgeries improves postoperative outcomes and prognosis to a great extent. Risk stratification and the prediction of treatment outcomes are feasible using the key clinical findings of each CHD with appropriate computational algorithms. Notably, AI can revolutionize prenatal prediction as well as the diagnosis of CHD using the EMR (electronic medical records) data on maternal risk factors. The use of AI in the diagnostics, risk stratification, and management of CHD in the near future is a promising possibility with current advancements in machine learning and neural networks. However, the challenges posed by the dearth of appropriate algorithms and their nascent nature, limited physician training, fear of over-mechanization, and apprehension of missing the 'human touch' limit the acceptability. Still, AI proposes to aid the clinician tomorrow with precision cardiology, paving a way for extremely efficient human-error-free health care.

Effect of preoperative pulse oximeter oxygen saturation on postoperative prolonged mechanical ventilation in patients with tetralogy of Fallot

Background

As an easily accessible and intervened clinical indicator, preoperative pulse oximeter oxygen saturation (SpO₂) is an important factor affecting the prognosis of patients with tetralogy of Fallot (TOF). However, whether SpO₂ is associated with postoperative mechanical ventilation (MV) time remains unknown. Therefore, this study aimed to investigate the impact of preoperative SpO₂ on postoperative prolonged mechanical ventilation (PMV) in children with TOF.

Materials and methods

The study included children younger than 18 years who underwent corrective operations for TOF between January 2016 and December 2018 in Fuwai Hospital, China. Univariate and multivariate logistic regression analyses were used to evaluate the influence of preoperative SpO₂ on postoperative PMV. After identifying SpO₂ as an independent risk factor for PMV, patients were further divided into two groups according to the cutoff value of SpO₂, and propensity score matching (PSM) analysis was used to eliminate the effect of confounding factors. The logistic regression was used to compare the outcomes between the two groups after PSM.

Results

A total of 617 patients were finally enrolled in this study. By the univariable and multivariate logistic analysis, four independent risk factors for PMV were determined, namely, SpO₂, surgical technique, aortic cross-clamp time, and intraoperative minimum temperature. According to the outcomes of 219 paired patients after PSM, the incidence of PMV was significantly higher in patients with lower preoperative SpO₂ (P = 0.022). Also, there was significant increase in mechanical ventilation time (P = 0.019), length of intensive care unit stay (P = 0.044), postoperative hospital stay (P = 0.006), hospital stay (P = 0.039), and hospitalization cost (P = 0.019) at the lower preoperative SpO₂ level.

Conclusion

Low preoperative SpO₂ represents an independent risk factor of postoperative PMV in children with TOF.

Risk factors for postoperative delirium in children with congenital heart disease: a prospective nested case-control study

OBJECTIVES

To study the risk factors for postoperative delirium (POD) in children with congenital heart disease.

METHODS

A prospective nested case-control study was performed on children with congenital heart disease who underwent surgery in Fuwai Hospital, Chinese Academy of Medical Sciences, from December 2020 to June 2021. The clinical data were compared between the POD group (n=114) and non-POD group (n=102). A multivariate unconditional logistic regression analysis was used to investigate the risk factors for POD in children with congenital heart disease.

RESULTS

The multivariate logistic regression analysis showed that age (OR=0.951, P<0.001), gender (OR=2.127, P=0.049), number of invasive catheters per day (OR=1.490, P=0.017), degree of postoperative pain (OR=5.856, P<0.001), and preoperative parental anxiety level (OR=1.025, P=0.010) were independent risk factors for POD in children with congenital heart disease.

CONCLUSIONS

The risk of POD increases in children with congenital heart disease who are younger, male, have higher number of invasive catheters per day, higher degree of postoperative pain, or higher preoperative parental anxiety level.

Maternal exposure to life events during pregnancy and congenital heart disease in offspring: a case-control study in a Chinese population

Background

Previous studies have suggested that maternal stress could increase the risk of some adverse pregnancy outcomes, but evidence on congenital heart disease (CHD) is limited. We aimed to explore the association between maternal exposure to life events during pregnancy and CHD in offspring.

Methods

The data was based on an unmatched case-control study about CHD conducted in Shaanxi province of China from 2014 to 2016. We included 2280 subjects, 699 in the case group and 1581 in the control group. The cases were infants or fetuses diagnosed with CHD, and the controls were infants without any birth defects. The life events were assessed by the Life Events Scale for Pregnant Women, and were divided into positive and negative events for synchronous analysis. A directed acyclic graph was drawn to screen the confounders. Logistic regression was employed to estimate the odds ratio and 95% confidence interval for the effects of life events on CHD.

Results

After controlling for the potential confounders, the pregnant women experiencing the positive events during pregnancy had lower risk of CHD in offspring than those without positive events (OR = 0.38, 95%CI: 0.30 ~ 0.48). The risk of CHD in offspring could increase by 62% among the pregnant women experiencing the negative events compared to those without (OR = 1.62, 95%CI: 1.29 ~ 2.03). Both effects showed a certain dose-response association. Besides, the positive events could weaken the risk impact of negative events on CHD.

Conclusion

It may suggest that maternal exposure to negative life events could increase the risk of CHD in offspring, while experiencing positive events could play a potential protective role.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12884-021-04154-0.

Association analysis of maternal MTHFR gene polymorphisms and the occurrence of congenital heart disease in offspring

BACKGROUND

Although many studies showed that the risk of congenital heart disease (CHD) was closely related to genetic factors, the exact pathogenesis is still unknown. Our study aimed to comprehensively assess the association of single nucleotide polymorphisms (SNPs) of maternal MTHFR gene with risk of CHD and its three subtypes in offspring.

METHODS

A case-control study involving 569 mothers of CHD cases and 652 health controls was conducted. Thirteen SNPs were detected and analyzed.

RESULTS

Our study showed that genetic polymorphisms of maternal MTHFR gene at rs4846052 and rs1801131 were significantly associated with risk of CHD in the homozygote comparisons (TT vs. CC at rs4846052: OR = 7.62 [95%CI 2.95-19.65]; GG vs. TT at rs1801131: OR = 5.18 [95%CI 2.77-9.71]). And six haplotypes of G-C (involving rs4846048 and rs2274976), A-C (involving rs1801133 and rs4846052), G-T (involving rs1801133 and rs4846052), G-T-G (involving rs2066470, rs3737964 and rs535107), A-C-G (involving rs2066470, rs3737964 and rs535107) and G-C-G (involving rs2066470, rs3737964 and rs535107) were identified to be significantly associated with risk of CHD. Additionally, we observed that a two-locus model involving rs2066470 and rs1801131 as well as a three-locus model involving rs227497, rs1801133 and rs1801131 were significantly associated with risk of CHD in the gene-gene interaction analyses. For three subtypes including atrial septal defect, ventricular septal defect and patent ductus arteriosus, similar results were observed.

CONCLUSIONS

Our study indicated genetic polymorphisms of maternal MTHFR gene were significantly associated with risk of fetal CHD in the Chinese population. Additionally, there were significantly interactions among different SNPs on risk of CHD. However, how these SNPs affect the development of fetal heart remains unknown, and more studies in different ethnic populations and with a larger sample are required to confirm these findings.

Artificial intelligence-assisted auscultation in detecting congenital heart disease

Aims

Computer-assisted auscultation has become available to assist clinicians with physical examinations to detect congenital heart disease (CHD). However, its accuracy and effectiveness remain to be evaluated. This study seeks to evaluate the accuracy of auscultations of abnormal heart sounds of an artificial intelligence-assisted auscultation (AI-AA) platform we create.

Methods and results

Initially, 1397 patients with CHD were enrolled in the study. The samples of their heart sounds were recorded and uploaded to the platform using a digital stethoscope. By the platform, both remote auscultation by a team of experienced cardiologists from Shanghai Children's Medical Center and automatic auscultation of the heart sound samples were conducted. Samples of 35 patients were deemed unsuitable for the analysis; therefore, the remaining samples from 1362 patients (mean age-2.4 ± 3.1 years and 46% female) were analysed. Sensitivity, specificity, and accuracy were calculated for remote auscultation compared to experts' face-to-face auscultation and for artificial intelligence automatic auscultation compared to experts' face-to-face auscultation. Kappa coefficients were measured. Compared to face-to-face auscultation, remote auscultation detected abnormal heart sound with 98% sensitivity, 91% specificity, 97% accuracy, and kappa coefficient 0.87. AI-AA demonstrated 97% sensitivity, 89% specificity, 96% accuracy, and kappa coefficient 0.84.

Conclusions

The remote auscultations and automatic auscultations, using the AI-AA platform, reported high auscultation accuracy in detecting abnormal heart sound and showed excellent concordance to experts' face-to-face auscultation. Hence, the platform may provide a feasible way to screen and detect CHD.

Comparison of fetal echocardiogram with fetal cardiac autopsy findings in fetuses with congenital heart disease

Objective: Although studies have compared fetal echo results with autopsy findings, investigations that compared multiple categories of congenital heart disease (CHD) are lacking. This study, therefore, aimed to compare fetal echocardiographic diagnoses with cardiac autopsy findings and evaluate the diagnostic accuracy of fetal echocardiography (FE).Methods: One hundred seventy-one specimens from fetuses diagnosed with CHD were collected after termination of pregnancy, and fetal autopsies were performed. FE and autopsy diagnoses were compared and the degree of their correspondence was categorized as "complete agreement" (FE results were in accordance with autopsy findings), "minor discrepancies" (autopsies verified the main FE diagnoses but added and/or revised some minor information), or "discordance" (autopsy findings were different from the primary diagnoses of FE).Results: The "complete agreement" group accounted for 87.1% (149/171) of the total specimens. In 11.7% (20/171) of cases, autopsies disclosed new deformities and/or revised some echo results (minor discrepancies group). Minor abnormalities were frequently embodied in small septal defects and vascular malformations. A rare malformation of common pulmonary vein atresia was confirmed by autopsy in two fetuses, but both were misdiagnosed by FE (discordance group).Conclusions: Fetal echocardiographic diagnoses were mostly consistent with autopsy findings. The diagnostic discrepancies mainly consisted of rare cases and minor abnormalities missed or misdiagnosed by FE. Autopsies may help confirm, modify, or add information to prenatal echo results. They may also help sonographers have a better understanding of the anatomic structures of CHD, especially for rare lesions, which could further improve the diagnostic accuracy and integrity of FE.

Screening for congenital heart defects: diversified strategies in current China

Background

Congenital heart defects (CHD) is the most common type of birth defect and a leading cause of infant mortality in China. Detection of CHD during newborn is still challenging. The contradiction between the increasingly mature technology of diagnosis and treatment and the inability of early detection is the biggest current dilemma. A few pilot studies attempt to establish the universal screening for CHD in newborns; however, the rate of misdiagnosis is still high in most Chinese hospitals, especially in some undeveloped middle-western regions.

Data sources

Based on the recent publications on screening of congenital heart diseases in China. We reviewed the use of diversified screening strategies in current China.

Results

Prenatal diagnosis by fetal echocardiography and postnatal detection by pulse oximetry combined with clinical assessment are the useful methods for CHD screening in most areas. The altitude should be taken into account when using pulse oximetry in the middle-western areas of China, where the incidence of CHD maybe higher. Echocardiography is suitable for CHD screening in almost all areas but it could add to financial burden in the developing regions. Genetic analysis could assist clinical doctors to perform more earlier screening and give better counseling regarding the outcome. Due to disparities in economic and medical resources, the screening system should be carried out from multiple perspectives according to the present economic development. Notably, follow-up is an important issue in the screening of CHD, especially for the asymptomatic babies who discharged home. Policies should be formulated to address the epidemiology of CHD in deprived areas to better allocate medical resources and to develop local training programmes to screen and diagnose CHD.

Conclusions

Diversified strategies are available in current China. The two-indicator method for CHD screening is recommended to be implemented in routine postnatal care. We can do more in screening for CHD in the future.