Screening For Congenital Heart Disease Research Articles

A “twelve-section ultrasonic screening and diagnosis method” and management system for screening and treating neonatal congenital heart disease at the grassroots level in Tang County, Hebei Province, China

BackgroundTo explore a method for screening and diagnosing neonatal congenital heart disease (CHD) applicable to grassroots level, evaluate the prevalence of CHD, and establish a hierarchical management system for CHD screening and treatment at the grassroots level.MethodsA total of 24,253 newborns born in Tang County between January 2016 and December 2020 were consecutively enrolled and screened by trained primary physicians via the “twelve-section ultrasonic screening and diagnosis method” (referred to as the “twelve-section method”). Specialized staff from the CHD Screening and Diagnosis Center of Hebei Children’s Hospital regularly visited the local area for definite diagnosis of CHD in newborns who screened positive. Newborns with CHD were managed according to the hierarchical management system.ResultsThe centre confirmed that, except for 2 newborns with patent ductus arteriosus missed in the diagnosis of ventricular septal defect combined with severe pulmonary hypertension, newborns with other isolated or concomitant simple CHDs were identified at the grassroots level. The sensitivity, specificity and diagnostic coincidence rate of the twelve-section method for screening complex CHD were 92%, 99.6% and 84%, respectively. A total of 301 children with CHD were identified. The overall CHD prevalence was 12.4‰. According to the hierarchical management system, 113 patients with simple CHD recovered spontaneously during local follow-up, 48 patients continued local follow-up, 106 patients were referred to the centre for surgery (including 17 patients with severe CHD and 89 patients with progressive CHD), 1 patient died without surgery, and 8 patients were lost to follow-up. Eighteen patients with complex CHD were directly referred to the centre for surgery, 3 patients died without surgery, and 4 patients were lost to follow-up. Most patients who received early intervention achieved satisfactory results. The mortality rate of CHD was approximately 28.86 per 100,000 children.ConclusionsThe “twelve-section method” is suitable for screening neonatal CHD at the grassroots level. The establishment of a hierarchical management system for CHD screening and treatment is conducive to the scientific management of CHD, which has important clinical and social significance for early detection, early intervention, reduction in mortality and improvement of the prognosis of complex and severe CHDs.

Enhancing Neonatal Care: The Vital Role of Pulse Oximetry in the Early Screening of Critical Congenital Heart Diseases and Respiratory Diseases in Rural Areas.

Background Pulse oximetry screening (POS) is acknowledged globally as a noninvasive method to detect critical congenital heart diseases (CCHDs) and respiratory illnesses. However, its value for early diagnosis and treatment remains unrecognized in many hospitals with limited resources around the world. This study aimed to evaluate POS's application in CCHDs, persistent pulmonary hypertension (PPHN), and respiratory distress syndrome (RDS) for early diagnosis and its influence on clinical procedures in rural areas. Methods This prospective observational study included all eligible newborn infants in the regional neonatal unit of a community healthcare center. Their peripheral oxygen saturation was assessed at <24 hours and >24 hours after birth, in the right upper limb and either lower limb. An oxygen saturation of <95% or >3% difference between pre-ductal and post-ductal circulations was considered abnormal. All neonates with abnormal oxygen saturations at >24 hours after birth were subjected to another POS test within two hours of the last test. If the oxygen saturation was still abnormal, it was considered a positive POS test. The POS results were classified as oxygen saturation abnormal (<90%), abnormal (90-94%), and normal (≥95%). All neonates with a positive POS test were referred for echocardiography. Results Overall, 440 infants had documented POS results. A total of 65 (14.77%) infants had a positive POS test result, out of which 39 (8.86%) cases were diagnosed on further evaluation. Four neonates had CCHD (positive predictive value (PPV) = 6.15%), 26 had RDS (PPV = 40%), and nine had PPHN (PPV = 13.85%). Without any further delay, the doctor directed them all to a more advanced facility. Conclusion Our research showed that, in large-scale clinical settings, the addition of pulse oximetry to routine cardiac auscultation could be a reliable and feasible method to screen newborns for CCHD, PPHN, and RDS early on. Our research underscores the importance of implementing routine POS to detect CCHD, RDS, and PPHN in clinical practice.

Is Pulse Oximetry a Reliable Method for Screening for Critical Congenital Heart Disease in Asymptomatic Neonates at 35 Weeks or More of Gestation?

Is Pulse Oximetry a Reliable Method for Screening for Critical Congenital Heart Disease in Asymptomatic Neonates at 35 Weeks or More of Gestation?

Universal Fetal Echocardiography for Pregestational Diabetes Mellitus: A Cost-Effectiveness Analysis.

To evaluate the cost effectiveness of universal fetal echocardiogram for patients with pregestational diabetes mellitus by first-trimester hemoglobin A1c (Hb A1c) level. We developed a cost-effectiveness model comparing two strategies of screening for critical fetal congenital heart disease among patients with diabetes: universal fetal echocardiogram and fetal echocardiogram only after abnormal findings on detailed anatomy ultrasonogram. We excluded ventricular septal defect, atrial septal defects, and bicuspid aortic valve from the definition of critical fetal congenital heart disease. Probabilities and costs were derived from the literature. We used individual models to evaluate different scenarios: first-trimester Hb A1c lower than 6.5%, Hb A1c 6.5-9.0%, and Hb A1c higher than 9.0%. Primary outcomes included fetal death, neonatal death, and false-positive and false-negative results. A cost-effectiveness threshold was set at $100,000 per quality-adjusted life-year. Univariable sensitivity analyses were performed to investigate the drivers of the model. Universal fetal echocardiogram is not cost effective except for when first-trimester Hb A1c level is higher than 9.0% (incremental cost-effectiveness ratio $638,100, $223,693, and $67,697 for Hb A1c lower than 6.5%, 6.5-9.0%, and higher than 9.0%, respectively). The models are sensitive to changes in the probability of congenital heart disease at a given Hb A1c level, as well as the cost of neonatal transfer to a higher level of care. Universal fetal echocardiogram became both cost saving and more effective when the probability of congenital heart disease reached 14.48% (15.4 times the baseline risk). In the Monte Carlo simulation, universal fetal echocardiogram is cost effective in 22.7%, 48.6%, and 62.3% of scenarios for each of the three models, respectively. For pregnant patients with first-trimester Hb A1c levels lower than 6.5%, universal fetal echocardiogram was not cost effective, whereas, for those with first-trimester Hb A1c levels higher than 9.0%, universal fetal echocardiogram was cost effective. For those with intermediate Hb A1c levels, universal fetal echocardiogram was cost effective in about 50% of cases; therefore, clinical judgment based on individual patient values, willingness to pay to detect congenital heart disease, and resource availability needs to be considered.

Research on bark-frequency spectral coefficients heart sound classification algorithm based on multiple window time-frequency reassignment

The multi-window time-frequency reassignment helps to improve the time-frequency resolution of bark-frequency spectral coefficient (BFSC) analysis of heart sounds. For this purpose, a new heart sound classification algorithm combining feature extraction based on multi-window time-frequency reassignment BFSC with deep learning was proposed in this paper. Firstly, the randomly intercepted heart sound segments are preprocessed with amplitude normalization, the heart sounds were framed and time-frequency rearrangement based on short-time Fourier transforms were computed using multiple orthogonal windows. A smooth spectrum estimate is calculated by arithmetic averaging each of the obtained independent spectra. Finally, the BFSC of reassignment spectrum is extracted as a feature by the Bark filter bank. In this paper, convolutional network and recurrent neural network are used as classifiers for model comparison and performance evaluation of the extracted features. Eventually, the multi-window time-frequency rearrangement improved BFSC method extracts more discriminative features, with a binary classification accuracy of 0.936, a sensitivity of 0.946, and a specificity of 0.922. These results present that the algorithm proposed in this paper does not need to segment the heart sounds and randomly intercepts the heart sound segments, which greatly simplifies the computational process and is expected to be used for screening of congenital heart disease.

Efficacy of atrioventricular valve regurgitation in the first trimester for the diagnosis of atrioventricular septal defect.

To investigate the efficacy of atrioventricular valve regurgitation (AVVR) for predicting atrioventricular septal defect (AVSD) in the first trimester. We performed a prospective observational study, screening for complicated congenital heart diseases and AVVR in fetuses at 11 to 13+6 weeks of gestation by advanced dynamic flow in four-chamber view and three-vessel-trachea view. 43 549 fetuses at 11 to 13+6 weeks of gestation were screened by echocardiography, of which 37 cases were diagnosed with AVSD, including complete AVSD (31 cases), intermediate AVSD (3 cases) and partial AVSD (1 cases), undiagnosed intermediate AVSD (2 cases), and misdiagnosed case (2 cases). AVVR was observed in 34 cases (34/37) in the first trimester, 59. 46% (22/37) nuchal translucency greater than 95th percentile, 29. 73% (11/37) absence of nasal bone, 32. 43% (12/37) ductus venosus A wave inversion, and 40. 54% (15/37) had tricuspid regurgitation. The sensitivity of common AVVR in predicting AVSD is better than other ultrasonic indexes. AVVR can be used as an ultrasonic indicator to predict AVSD in the first trimester, which is beneficial to detect AVSD.

Newborn Pulse Oximetry Screening for Detecting Congenital Heart Disease: Experience at a Tertiary Care Center.

Congenital heart disease (CHD) remains the number one birth defect worldwide. Pulse oximetry screening (POS) is a widely used CHD screening modality effective in detecting critical lesions. This study is aimed at assessing the accuracy and cost-effectiveness of POS in a cohort of term well-babies admitted to a regular nursery in a tertiary care center. We reviewed the charts of term babies admitted to our regular nursery over a period of one year. The results of POS and the findings of echocardiography were collected. Similarly, we explored the records of our fetal echocardiography program to identify the fetuses screened for CHD during the same period. 900 term babies were born and admitted to newborn nursery at our center, and 69 fetuses were evaluated by our fetal cardiology team during the study period. None of our term babies had a positive POS at birth or 24 hours of age. However, 56 babies had a cardiac echo before hospital discharge due to suspicious findings on physical examination or a family history of CHD. A simple noncritical CHD was noted in 10 of them. Additionally, 53 babies underwent echocardiography within the first five years of life; a simple CHD was noted in 6 of them. In parallel, 21 of our fetuses were found to have CHD: 16 simple CHD and 5 critical CHD (CCHD). Despite its cost-effectiveness and efficacy in screening for CCHD, POS is suboptimal for detecting simple CHD. In the absence of a proper prenatal screening and fetal echocardiography program, POS remains a cost-effective modality for detecting CCHD.

SPReCHD: Four-Chamber Semantic Parsing Network for Recognizing Fetal Congenital Heart Disease in Medical Metaverse.

Echocardiography is essential for evaluating cardiac anatomy and function during early recognition and screening for congenital heart disease (CHD), a widespread and complex congenital malformation. However, fetal CHD recognition still faces many difficulties due to instinctive fetal movements, artifacts in ultrasound images, and distinctive fetal cardiac structures. These factors hinder capturing robust and discriminative representations from ultrasound images, resulting in CHD's low prenatal detection rate. Hence, we propose a multi-scale gated axial-transformer network (MSGATNet) to capture fetal four-chamber semantic information. Then, we propose a SPReCHD: four-chamber semantic parsing network for recognizing fetal CHD in the clinical treatment of the medical metaverse, integrating MSGATNet to segment and locate four-chamber arbitrary contours, further capturing distinguished representations for the fetal heart. Comprehensive experiments indicate that our SPReCHD is sufficient in recognizing fetal CHD, achieving a precision of 95.92%, a recall of 94%, an accuracy of 95%, and a F1 score of 94.95% on the test set, dramatically improving the fetal CHD's prenatal detection rate.

Deep-learning model for prenatal congenital heart disease screening generalizes to community setting and outperforms clinical detection.

Despite nearly universal prenatal ultrasound screening programs, congenital heart defects (CHD) are still missed, which may result in severe morbidity or even death. Deep machine learning (DL) can automate image recognition from ultrasound. The main aim of this study was to assess the performance of a previously developed DL model, trained on images from a tertiary center, using fetal ultrasound images obtained during the second-trimester standard anomaly scan in a low-risk population. A secondary aim was to compare initial screening diagnosis, which made use of live imaging at the point-of-care, with diagnosis by clinicians evaluating only stored images. All pregnancies with isolated severe CHD in the Northwestern region of The Netherlands between 2015 and 2016 with available stored images were evaluated, as well as a sample of normal fetuses' examinations from the same region and time period. We compared the accuracy of the initial clinical diagnosis (made in real time with access to live imaging) with that of the model (which had only stored imaging available) and with the performance of three blinded human experts who had access only to the stored images (like the model). We analyzed performance according to ultrasound study characteristics, such as duration and quality (scored independently by investigators), number of stored images and availability of screening views. A total of 42 normal fetuses and 66 cases of isolated CHD at birth were analyzed. Of the abnormal cases, 31 were missed and 35 were detected at the time of the clinical anatomy scan (sensitivity, 53%). Model sensitivity and specificity were 91% and 78%, respectively. Blinded human experts (n = 3) achieved mean ± SD sensitivity and specificity of 55 ± 10% (range, 47-67%) and 71 ± 13% (range, 57-83%), respectively. There was a statistically significant difference in model correctness according to expert-graded image quality (P = 0.03). The abnormal cases included 19 lesions that the model had not encountered during its training; the model's performance in these cases (16/19 correct) was not statistically significantly different from that for previously encountered lesions (P = 0.41). A previously trained DL algorithm had higher sensitivity than initial clinical assessment in detecting CHD in a cohort in which over 50% of CHD cases were initially missed clinically. Notably, the DL algorithm performed well on community-acquired images in a low-risk population, including lesions to which it had not been exposed previously. Furthermore, when both the model and blinded human experts had access to only stored images and not the full range of images available to a clinician during a live scan, the model outperformed the human experts. Together, these findings support the proposition that use of DL models can improve prenatal detection of CHD. © 2023 International Society of Ultrasound in Obstetrics and Gynecology.

A Coarse-Fine Collaborative Learning Model for Three Vessel Segmentation in Fetal Cardiac Ultrasound Images.

Congenital heart disease (CHD) is the most frequent birth defect and a leading cause of infant mortality, emphasizing the crucial need for its early diagnosis. Ultrasound is the primary imaging modality for prenatal CHD screening. As a complement to the four-chamber view, the three-vessel view (3VV) plays a vital role in detecting anomalies in the great vessels. However, the interpretation of fetal cardiac ultrasound images is subjective and relies heavily on operator experience, leading to variability in CHD detection rates, particularly in resource-constrained regions. In this study, we propose an automated method for segmenting the pulmonary artery, ascending aorta, and superior vena cava in the 3VV using a novel deep learning network named CoFi-Net. Our network incorporates a coarse-fine collaborative strategy with two parallel branches dedicated to simultaneous global localization and fine segmentation of the vessels. The coarse branch employs a partial decoder to leverage high-level semantic features, enabling global localization of objects and suppression of irrelevant structures. The fine branch utilizes attention-parameterized skip connections to improve feature representations and improve boundary information. The outputs of the two branches are fused to generate accurate vessel segmentations. Extensive experiments conducted on a collected dataset demonstrate the superiority of CoFi-Net compared to state-of-the-art segmentation models for 3VV segmentation, indicating its great potential for enhancing CHD diagnostic efficiency in clinical practice. Furthermore, CoFi-Net outperforms other deep learning models in breast lesion segmentation on a public breast ultrasound dataset, despite not being specifically designed for this task, demonstrating its potential and robustness for various segmentation tasks.

Development and Validation of a Deep-Learning Network for Detecting Congenital Heart Disease from Multi-View Multi-Modal Transthoracic Echocardiograms.

Early detection and treatment of congenital heart disease (CHD) can significantly improve the prognosis of children. However, inexperienced sonographers often face difficulties in recognizing CHD through transthoracic echocardiogram (TTE) images. In this study, 2-dimensional (2D) and Doppler TTEs of children collected from 2 clinical groups from Beijing Children's Hospital between 2018 and 2022 were analyzed, including views of apical 4 chamber, subxiphoid long-axis view of 2 atria, parasternal long-axis view of the left ventricle, parasternal short-axis view of aorta, and suprasternal long-axis view. A deep learning (DL) framework was developed to identify cardiac views, integrate information from various views and modalities, visualize the high-risk region, and predict the probability of the subject being normal or having an atrial septal defect (ASD) or a ventricular septaldefect (VSD). A total of 1,932 children (1,255 healthy controls, 292 ASDs, and 385 VSDs) were collected from 2 clinical groups. For view classification, the DL model reached a mean [SD] accuracy of 0.989 [0.001]. For CHD screening, the model using both 2D and Doppler TTEs with 5 views achieved a mean [SD] area under the receiver operating characteristic curve (AUC) of 0.996 [0.000] and an accuracy of 0.994 [0.002] for within-center evaluation while reaching a mean [SD] AUC of 0.990 [0.003] and an accuracy of 0.993 [0.001] for cross-center test set. For the classification of healthy, ASD, and VSD, the model reached the mean [SD] accuracy of 0.991 [0.002] and 0.986 [0.001] for within- and cross-center evaluation, respectively. The DL models aggregating TTEs with more modalities and scanning views attained superior performance to approximate that of experienced sonographers. The incorporation of multiple views and modalities of TTEs in the model enables accurate identification of children with CHD in a noninvasive manner, suggesting the potential to enhance CHD detection performance and simplify the screening process.

Prenatal screening for congenital heart disease: Which interest in a country with limited resources

Prenatal screening for congenital heart disease: Which interest in a country with limited resources

Characterization of genomic variants associated with congenital heart disease in patients from southwestern Colombian

Congenital heart diseases correspond to errors during embryogenesis, generating structural and functional malformations. Congenital heart diseases are the most prevalent congenital malformations and are responsible for the highest infant morbidity and mortality. Among these cases, 8 % can be attributed to variants in genes associated with cardiac development. To establish the population frequency of genomic variants that cause congenital heart disease, a review of the scope of prevalent genes was carried out, complete exome sequencing results of 320 patients without suspicion of congenital heart disease were used, the exome sequencing is a technique based on DNA extraction using a Qiagen kit, with massive sequencing of Nextera TM libraries using an Illumina platform with 100X coverage, alignment with reference genome GRCh38/hg19, and analysis with the CRAVAT program; clinical characterization, significance classification, and gene interaction networks were performed. The scope analysis allowed to determine that the genes NKX2-5, TBX20, GATA4, NOTCH1, PTPN11 are the most prevalent, the variants with the highest allelic frequency were c.63A > G (0.2844), c.39T > C (0.3406), c.1132A > G (0.0406), c.1669+9T > C (0.3531) and c.854-30T > C (0.0875) respectively; 4 variants were reclassified by in silico tools, in the NKX2-5 gene c.335-311_335-303del from benign to probably pathogenic, in the NOTCH1 gene c.2354-24C > T from benign to pathogenic, and in the PTPN11 gene c.2354-24C > T and c.854-30T > C from benign to pathogenic. 17 % of intronic variants and 4.8 % of missense variants were identified. This work contributes to knowledge about the frequency with which genomic variants associated with congenital heart disease are present in the population, generating a tool for early diagnosis, early treatment, thus reducing morbidity and mortality, with a view to future universal molecular neonatal screening of congenital heart disease.

Knowledge and perception on expanded newborn screening in Sri Lanka among pregnant women attending antenatal clinics in Teaching Hospital Mahamodara

Introduction: Unlike in developed countries, there is no established expanded newborn screening (eNBS) in resource-limited settings. In Sri Lanka, the Ministry of Health has adopted screening only for congenital hypothyroidism, critical congenital heart diseases and congenital deafness as a policy in all newborns. Hence, there is a requirement to assess the need for eNBS in Sri Lanka. This requires epidemiological studies of the inherited metabolic disorders (IMDs) before investment to ensure costeffectiveness of the programme and reflections on acceptance by beneficiaries.Objectives: To evaluate the pregnant women's knowledge, attitudes and willingness towards eNBS.Method: A descriptive cross-sectional study was conducted at the Mahamodara Maternity Hospital antenatal clinics, Galle, Southern Province, Sri Lanka. A convenient sample was obtained from the antenatal clinics. A pre-tested intervieweradministered questionnaire was used to assess basic socio-demographic details, knowledge and perception of eNBSResults: A total of 602 pregnant women took part in the study. The mean age was 29±5.7 years; 67% were in the 25-40-year age group; 37.2% were primigravida and 60% were in the third trimester. More than 50% of the study participants knew about the heel prick test done at birth. However, only 34.8% and 28% were aware of the screening for congenital hypothyroidism and congenital heart disease, respectively; 93.6% of mothers had not heard of the term IMD, and only seven were aware of the term eNBS. Nevertheless, more than 80% of participants were willing to screen their babies at birth for underlying IMDs, even if it is available on payment, as the current programme was free of charge to the family. Similarly, 96.2% were willing to screen their babies for incurable diseases.Conclusions: Though most women were aware of the heel prick test done at birth, only a suboptimal proportion of them was aware of the disease/s checked using the test. In addition, there was poor knowledge about the IMDs and eNBS. However, there were positive attitudes towards eNBS.

EE308 Cost-Utility Analysis of Universal Neonatal Screening for Critical Congenital Heart Disease Based on Pulse Oximetry in Spain

EE308 Cost-Utility Analysis of Universal Neonatal Screening for Critical Congenital Heart Disease Based on Pulse Oximetry in Spain

Anorectal malformations (ARM) and VACTERL association and severity of congenital heart diseases (CHD): Experience of 396 consecutive patients in a tertiary center

ObjectiveCongenital heart diseases (CHD) are the most frequently associated anomalies with anorectal malformations (ARM). Nevertheless, many specific aspects of CHD in ARM patients have yet to be studied. The aims of this study were to evaluate the prevalence and distribution of CHD in neonates-infants with ARM, and to explore whether the severity of ARM, and the presence of VACTERL association, had an impact on CHD rate, severity, and timing at first cardiac surgery. Study designAll consecutive newborn-infants with ARM managed in our tertiary center (January-1999; December-2021) were collected from a prospective database and retrospectively analyzed. Prevalence and distribution of CHD in ARM patients were assessed. Patients were divided into groups depending on ARM severity and presence of VACTERL association. Pairwise comparison for CHD prevalence, severity, and timing at first cardiac surgery was performed between groups. ResultsOf 396 ARM patients identified, those with severe ARM showed a higher number of overall CHD compared to patients with non-severe ARM (36.7 % vs. 25.2 %, p = 0.032). VACTERL + patients had a significantly higher prevalence of CHD (73.4 % vs. 16.4 %; p <0.001) and major CHD (51.7 % vs. 26.9 %; p = 0.008) when compared with VACTERL-patients. Furthermore, VACTERL + patients underwent first cardiac surgery at a significantly younger age than VACTERL-patients (5.2 ± 15.2 months vs. 11.9 ± 6.3, p = 0.039). ConclusionsPatients with severe ARM had a higher number of CHD compared to patients with non-severe ARM. VATERL + patients had significantly more CHD and more severe CHD than VACTERL-patients. Early screening for CHD is strongly recommended in all newborns diagnosed with ARM before surgery. Level of evidenceIII retrospective comparative study.

Identification of abnormal ventricular asymmetry in 2nd trimester fetal ultrasound using artificial intelligence

Abstract Introduction Prenatal ultrasound screening for congenital heart disease (CHD) suffers from poor detection yield (10%-56%)[1, 2], with a strong impact on neonatal morbidity and mortality. The need for expertise in fetal cardiology and the high volume of screening cases limit the current detection rates. Computer-assisted prenatal screening could support clinicians in improving diagnostic yield, including for abnormal ventricular asymmetry, which is often hard to discriminate from physiological asymmetry. Here we aim at evaluating a deep neural network (DNN) for detection of abnormal ventricular asymmetry, which can be linked to multiple types of CHD, including coarctation of the aorta, pulmonary or aortic valve stenosis, ventricular hypoplasia or univentricular heart. Purpose To determine if a novel DNN can identify cases of abnormal ventricular asymmetry in 2nd trimester fetal ultrasound videos. Methods We used as an endpoint the presence of any abnormality causing a significantly abnormal asymmetry of the ventricles as seen in the fetal ultrasound. Consecutive patients who had an echocardiography performed at one center were included retrospectively starting from 2022, January 1st. Inclusion criteria were single pregnancy between 18 and 25 weeks of gestation. To have a high number of positive patients, patients were included separately if they were expected to be positive (n=35) or negative (n=75) to the endpoint, based on their medical record. Each case was reviewed by one of two physicians expert in fetal echocardiography interpretation to confirm the presence or absence of the endpoint. For each patient, a single video showing an interpretable four chamber view was selected. Patients with no such video were excluded. The DNN takes as input fetal ultrasound videos, and predicts the absence or presence of the endpoint for each video. If its confidence is low, the DNN predicts an "inconclusive" output instead. The DNN has a ResNet-50 architecture[3] adapted to videos and was trained on data from patients not included in the evaluation. The detection performance of the DNN and the proportion of conclusive outputs were assessed. Results Overall, 37 positive and 66 negative ultrasound videos were included. The DNN achieved an AUC of 75.5%, a sensitivity of 71.4% (54.9-83.7, 95%CI) and a specificity of 64.4% (51.7-75.4, 95%CI) in identifying cases of abnormal ventricular asymmetry, after excluding inconclusive diagnosis. The DNN predicted a conclusive diagnosis in 91.3% of cases. Conclusion A DNN could accurately identify cases of abnormal ventricular asymmetry in fetal heart ultrasound videos. Importantly, this evaluation was performed in a population of patients who had an echocardiogram, and which therefore contains more abnormal cases compared to patients undergoing standard screening. This work lays the ground for diagnostic support to enable a more efficient, accurate, and scalable analysis of fetal heart ultrasounds.

Determinants of childbearing intentions among pregnant women with a suspected fetal congenital heart disease

BackgroundThe Saudi population is characterized by a high fertility rate, a conservative sociocultural context, and an ongoing societal and lifestyle transition. Yet, data regarding childbearing intentions and the associated factors is scarce. Furthermore, childbearing intention may be impacted by abnormal pregnancy events, such as the clinical suspicion or diagnosis of a fetal congenital disease and the negative experience that may result from it. ObjectivesThe present study explored childbearing intention and determined the sociodemographic and health-related factors discouraging from future pregnancies among women visiting the cardiology clinic for antenatal screening of congenital heart diseases (CHD). MethodsA one-year cross-sectional study involved 150 consecutive pregnant women aged between 18 and 47 years old, who presented for antenatal screening of CHD at the fetal echocardiography clinic for, of a teaching hospital in Jeddah, Saudi Arabia. An interview-based questionnaire was administered before the clinic visit and collected sociodemographic data, obstetrical history, risk factors of congenital diseases, mothers’ knowledge about fetal echocardiography and CHDs, and childbearing intention (the primary outcome). ResultsFetal echocardiography and CHD were correctly described by 60 % and 31.3 % of the participants respectively, while 40.7 % and 12 % recognized the association of congenital diseases with consanguinity and advanced maternal age respectively. Childbearing intentions showed 68.0 % of the participants declared desiring a future baby while the remaining 32.0 % declared having no further pregnancy expectations. Attitudes towards a hypothetical baby with CHD were positive in 97.3 % of the participants, and only 30 % declared that the fetal echocardiography results will impact their future childbearing decision. However, childbearing intention showed no significant association with knowledge or attitudes towards CHD. On the other hand, childbearing intention was independently associated with the number of children (OR=0.34; p<0.001), consanguinity with husband (OR=3.64; p = 0.010), and history of gestational diabetes (OR=0.28; p = 0.040). ConclusionFertility expectations among Saudi mothers are more likely to be impacted by the personal experience and judgment of own pregnancy fitness, while no significant impact of fetal risks and events. This demonstrates a certain level of autonomy balanced with deeply rooted religious ethics yet combined with a lack of awareness about fetal and maternal risks associated with advanced maternal age and consanguinity. We emphasize the unmet need of education and family planning.

Abstract 13368: Availability of PGE1 in Northern California Hospitals: Before and After Routine CCHD Screening

Introduction: Fetal echocardiogram and critical congenital heart disease (CCHD) screening has improved early detection of CCHD. CCHD screening has been recommended for all infants since 2011 and mandated in California since July 2013. In patients with suspected ductal dependent congenital heart disease, early intervention with prostaglandin E1 (PGE1) is the standard of care to reduce morbidity and mortality. Hypothesis: In 2004, we assessed the availability of PGE1 in Northern California hospitals that care for newborn infants and found that 32% of hospitals with obstetric services did not have the ability to institute PGE1 infusion. As California has adopted CCHD screening for all newborn infants prior to hospital discharge, our aim was to assess the percentage of hospitals that perform CCHD screening as well as reassess PGE1 availability. Our hypothesis was that CCHD screening would increase the availability of PGE1 at hospitals providing obstetric services. Methods: The initial study contacted 117 Northern California hospitals to determine PGE1 availability. We contacted the same hospitals, ending up with 106 hospitals due to closures and mergers. The newborn nursery and/or NICU for each of these hospitals was contacted to determine CCHD screening practices and availability of PGE1. Mileage to the nearest level IV NICU was used as a gross estimate of distance to a tertiary care center. Results: In 2004, 92 of 117 hospitals had obstetric service, and 30 (32.6%) of those did not have PGE1. In this study, 74 of the 106 provided obstetric services. All performed CCHD screening, but 15 (20.3%) did not have ability to provide PGE1 infusion. 8 of the 15 hospitals were more than 30 miles (range 1.5 - 192 miles) from the closest level IV NICU. Conclusions: All hospitals in Northern California providing obstetric service are performing CCHD screening. However, 20.3% of these hospitals still do not have the ability to administer PGE1 infusion. Of these, 53% were in suburban and rural areas of Northern California, with significant transportation distance to a tertiary care center. Delay in initiating PGE1 infusion in patients with ductal dependent CCHD may lead to morbidity or mortality, and increasing PGE1 availability is an opportunity to improve access to care.

Abstract 18657: Diagnostic Yield of Whole Genome Sequencing in Congenital Heart Disease: Data From the UK 100,000 Genomes Project

Congenital heart disease (CHD) is the most common birth defect affecting around 1% global live births. The aetiology of CHD is poorly understood: while a number genetic loci have already been identified, the majority of cases remain unexplained. Many CHD cases occur with additional abnormalities, or as part of a defined syndrome (eg. Noonan or CHARGE syndromes). The 100,000 Genomes Project conducted whole genome sequencing for patients with a range of rare diseases and cancers in partnership with the UK National Health Service. We analysed clinical and genetic data from the project in 2638 participants with CHD, including both primary CHD cases and secondary cases who have CHD as part of a syndromic presentation but were recruited under other disease categories. Both cohorts are primarily composed of patients with CHD accompanied by additional extra-cardiac abnormalities without a prior diagnosis of a defined syndrome. We found that families recruited as primary CHD cases were significantly less likely to have been classed as “solved cases” (indicating a pathogenic variant has been identified) than phenotypically similar secondary CHD cases (5.4% primary, 16.2% secondary; p = 6.78х -11 ). This is primarily due to differences in the gene lists used in analysis, with the majority of diagnoses in both groups due to genes not included in the CHD gene panel (83% primary and 97% secondary cases). Expanding standard CHD screening to include a wider range of syndromic CHD genes is likely to increase the diagnostic yield for the primary CHD cohort by more than two-fold. Copy number variants (CNVs) also contribute to CHD, especially in cases with additional abnormalities. CHD cases have a significantly higher burden of both deletions (p = 1.00х10 -5 ) and duplications (p = 0.009) than an ethnically-matched control cohort. However, only 7 of 2638 participants have CNVs in known CHD-causative regions such as the 22q11.2 or Williams-Beuren syndrome regions indicating novel CNVs are likely to contribute to a significant number of cases. Wider screening of syndromic CHD genes and novel copy number variants is likely significantly increase the diagnostic yield for CHD both within the 100,000 Genomes Project and in healthcare settings, and potentially yield novel CHD-associated loci.