Congenital heart disease diagnosed with echocardiogram in newborns with asymptomatic cardiac murmurs: a systematic review

Incidence and Antenatal Detection of Congenital Heart Malformations-Data from a Tertiary Obstetric Romanian Center

OBJECTIVES

Congenital heart defects (CHDs) are among the most frequent congenital defects, and they significantly burden the healthcare system due to their high mortality rate and high cost of care for survivors. We aimed to highlight the incidence of CHDs in a tertiary center in Western Romania.

METHODS

A retrospective study was carried out between 2018 and 2022 at the "Pius Brinzeu" Emergency County Hospital Timisoara. Relevant information about the mothers and the newborns were collected and statistically analyzed.

RESULTS

The incidence of CHDs from 2018 to 2022 in our center was 5.3%. Eleven types of malformations were diagnosed postnatally in 541 newborns, with 28.8% of cases having more than one type of CHD. The antenatal detection rate was 28%, with the highest rates for tetralogy of Fallot, hypoplastic left heart syndrome, or significant ventricular septal defects and the lowest for pulmonary stenosis. The lower antenatal detection rate was influenced mainly by incomplete or absent prenatal care.

CONCLUSIONS

The incidence of CHDs is clearly dependent of a multifactorial approach, and the results highlight this. With an incidence almost 50% lower than reported within the literature and a low rate of prenatal detections, CHDs could be a more of a burden to endure regarding medical treatment. Improvements in patients' education, prenatal care, and screening programs could improve diagnosis, decrease mortality, and optimize postnatal care.

Heart and great vessels segmentation in congenital heart disease via CNN and conditioned energy function postprocessing

PURPOSE

The segmentation of the heart and great vessels in CT images of congenital heart disease (CHD) is critical for the clinical assessment of cardiac anomalies and the diagnosis of CHD. However, the diverse types and abnormalities inherent in CHD present significant challenges to comprehensive heart segmentation.

METHODS

We proposed a novel two-stage segmentation approach, integrating a Convolutional Neural Network (CNN) with a postprocessing method with conditioned energy function for pulmonary and aorta. The initial stage employs a CNN enhanced by a gated self-attention mechanism for the segmentation of five primary heart structures and two major vessels. Subsequently, the second stage utilizes a conditioned energy function specifically tailored to refine the segmentation of the pulmonary artery and aorta, ensuring vascular continuity.

RESULTS

Our method was evaluated on a public dataset including 110 3D CT volumes, encompassing 16 CHD variants. Compared to prevailing segmentation techniques (U-Net, V-Net, Unetr, dynUnet), our approach demonstrated improvements of 1.02, 1.04, and 1.41% in Dice Coefficient (DSC), Intersection over Union (IOU), and the 95th percentile Hausdorff Distance (HD95), respectively, for heart structure segmentation. For the two great vessels, the enhancements were 1.05, 1.07, and 1.42% in these metrics.

CONCLUSION

The outcomes on the public dataset affirm the efficacy of our proposed segmentation method. Precise segmentation of the entire heart and great vessels can significantly aid in the diagnosis and treatment of CHD, underscoring the clinical relevance of our findings.

Conotruncal Heart Defects: A Narrative Review of Molecular Genetics, Genomics Research and Innovation

Congenital heart defects (CHDs) are most prevalent cardiac defects that occur at birth, leading to significant neonatal mortality and morbidity, especially in the developing nations. Among the CHDs, conotruncal heart defects (CTDs) are particularly noteworthy, comprising a significant portion of congenital cardiac anomalies. While advances in imaging and surgical techniques have improved the diagnosis, prognosis, and management of CTDs, their molecular genetics and genomic substrates remain incompletely understood. This expert review covers the recent advances from January 2016 onward and examines the complexities surrounding the genetic etiologies, prevalence, embryology, diagnosis, and clinical management of CTDs. We also emphasize the known copy number variants and single nucleotide variants associated with CTDs, along with the current planetary health research efforts aimed at CTDs in large cohort studies. In all, this comprehensive narrative review of molecular genetics and genomics research and innovation on CTDs draws from and highlights selected works from around the world and offers new ideas for advances in CTD diagnosis, precision medicine interventions, and accurate assessment of prognosis and recurrence risks.

Natural History of Secundum ASD in Preterm and Term Neonates: A Comparative Study

Atrial septal defects (ASDs) are common in neonates. Although past studies suggest ASDs  ≥ 3 mm in term neonates (TNs) are less likely to close, there is paucity of data regarding the natural history in preterm neonates (PNs), information that would inform surveillance. We sought to compare spontaneous closure rates and need for intervention for ASDs in TNs/near term (≥ 36 weeks) versus PNs (< 36 weeks). We included all TNs and PNs who underwent echocardiography at ≤ 1 month between 2010 and 2018 in our institution with an ASD ≥ 3 mm, without major congenital heart disease, and with repeat echocardiogram(s). Spontaneous resolution was defined as size diminution to < 3 mm or closure. We included 156 TNs (mean gestational age at birth 38.6 ± 1.4 weeks) and 156 PNs (29.6 ± 3.7 weeks) with a mean age at follow-up of 16 ± 19 and 15 ± 21 months, respectively (p = 0.76). Based on maximum color Doppler diameter, in TNs, ASD resolution occurred in 95% of small (3-5 mm), 87% of moderate (5.1-8 mm), and 60% of large (> 8 mm) defects; whereas, in PNs, resolution occurred in 79% of small, 76% of moderate, and 33% of large ASDs. There was a significant association between size and ASD resolution in TNs (p = 0.003), but not PNs (p = 0.17). Overall, ASD resolution rate was higher in TNs (89%) versus PNs (78%) (p = 0.009), and fewer TNs (1%) compared to PNs (7%) required ASD intervention (p = 0.02). Most ASDs identified in TNs and PNs spontaneously resolve. PNs, however, demonstrate lower ASD resolution and higher intervention rates within all size groups. These data should inform follow-up of affected neonates.

Congenital Heart Disease

More people are living with congenital heart disease (CHD) because many children now survive to adulthood with advances in medical and surgical treatments. Patients with CHD have ongoing complex health-care needs in the various life stages of infancy, childhood, adolescence, and adulthood. Primary care providers should collaborate with pediatric specialists to provide ongoing care for people living with CHD and to create smooth transitions of care.

Role of artificial intelligence in early detection of congenital heart diseases in neonates

In the domain of healthcare, most importantly pediatric healthcare, the role of artificial intelligence (AI) has significantly impacted the medical field. Congenital heart diseases represent a group of heart diseases that are known to be some of the most critical cardiac conditions present at birth. These heart diseases need a swift diagnosis as well as an intervention to ensure the wellbeing of newborns. Fortunately, with the help of AI, including the highly advanced algorithms, analytics and imaging involved, it provides us with a promising era for neonatal care. This article reviewed published data in PubMed, Science Direct, UpToDate, and Google Scholar between the years 2015-2023. To conclude The use of artificial intelligence in detecting congenital heart diseases has shown great promise in improving the accuracy and efficiency of diagnosis. Several studies have demonstrated the efficacy of AI-based approaches for diagnosing congenital heart diseases, with results indicating that the systems can achieve high levels of sensitivity and specificity. In addition, AI can help reduce the workload of healthcare professionals allowing them to focus on other critical aspects of patient care. Despite the potential benefits of using AI, in addition to detecting congenital heart disease, there are still some challenges to overcome, such as the need for large amounts of high-quality data and the requirement for careful validation of the algorithms. Nevertheless, with ongoing research and development, AI is likely to become an increasingly valuable tool for improving the diagnosis and treatment of congenital heart diseases.

The Burden of Neonatal Referrals on a Pediatric Cardiology Service: A Local Center Experience

BACKGROUND

Congenital heart disease (CHD) is a common occurrence in live births, with some exhibiting critical congenital heart disease; therefore, cardiology services should be available around the clock to ensure timely diagnosis and management. This study aims to describe the workload and the need for pediatric cardiac services in a maternity hospital for newborn referrals. Moreover, the study describes the indications for neonatal cardiology consultations.

METHODS

The prospective cohort study was conducted over four months, from January to April 2022, in the Prince Sultan Cardiac Center Al Qassim region of Saudi Arabia. Prince Sultan Cardiac Center's pediatric cardiology department provides cardiac services to the Maternity and Children Hospital Buraidah Al Qassim. Out of the total 2,606 live births during the study period, the cardiology team evaluated 352 neonates. Neonates less than 30 days of age who were born in the maternity hospital were enrolled in the study. The outborn babies referred from other centers as suspected congenital heart disease for whom a cardiac evaluation was done were excluded. In addition, babies assessed in the emergency room and born elsewhere were excluded. Only new consultations have been considered, excluding follow-up consultations.

STATISTICAL ANALYSIS

Data about patients' demographic, clinical and echocardiographic findings were recorded on Google Forms and converted to a Google spreadsheet. The Google spreadsheet's inbuilt statistical software was used for analysis. Categorical data were presented as percentages, and numerical data as median and range.

RESULTS

The cardiology team evaluated 352 neonates from 2,606 live births over four months, accounting for 13.5 per 100 live births. The median weight was 2.8 kilograms, with a 0.5-4.3 kilogram range. Males comprised 187 (53%), and females comprised 165 (47%). Moreover, full-term, preterm, and post-term accounted for 236 (67%), 113 (32%), and 3 (0.8%) of patients, respectively. The common indications for neonatal cardiac referral were respiratory distress 60 (17%), infants born to diabetic mothers 50 (14%), abnormal fetal echocardiogram 49 (13.9%), family history of abortion or neonatal death 31 (8.8%), and congenital anomalies 30 (8.5%). Systolic murmur was the commonest clinical finding that prompted cardiology referrals 82 (23.2%), followed by desaturation 38 (10.7%) and dysmorphic features 31 (8.8%). Among the congenital cardiac defects, an isolated atrial septal defect (ASD) was seen in 66 (18.5%), isolated patent ductus arteriosus in 50 (14.2%), and ventricular septal defect in 21 (5.9%). Moreover, 13 (4.4%) lesions were critical CHDs. Finally, 27 (7.6%) had a diagnosis of pulmonary hypertension.

CONCLUSION

Knowing the burden of neonatal cardiac assessment on pediatric cardiology services in any maternity center may help the healthcare authorities to allocate resources and optimize the delivery of cardiac services among the neonatal population. Properly allocating pediatric cardiologists to the needed centers may optimize neonatal cardiac services. Moreover, it may decide on the number of pediatric cardiologists that need to be trained each year to meet the requirements of neonatal cardiac services.

Automatic echocardiographic anomalies interpretation using a stacked residual-dense network model

Echocardiographic interpretation during the prenatal or postnatal period is important for diagnosing cardiac septal abnormalities. However, manual interpretation can be time consuming and subject to human error. Automatic segmentation of echocardiogram can support cardiologists in making an initial interpretation. However, such a process does not always provide straightforward information to make a complete interpretation. The segmentation process only identifies the region of cardiac septal abnormality, whereas complete interpretation should determine based on the position of defect. In this study, we proposed a stacked residual-dense network model to segment the entire region of cardiac and classifying their defect positions to generate automatic echocardiographic interpretation. We proposed the generalization model with incorporated two modalities: prenatal and postnatal echocardiography. To further evaluate the effectiveness of our model, its performance was verified by five cardiologists. We develop a pipeline process using 1345 echocardiograms for training data and 181 echocardiograms for unseen data from prospective patients acquired during standard clinical practice at Muhammad Hoesin General Hospital in Indonesia. As a result, the proposed model produced of 58.17% intersection over union (IoU), 75.75% dice similarity coefficient (DSC), and 76.36% mean average precision (mAP) for the validation data. Using unseen data, we achieved 42.39% IoU, 55.72% DSC, and 51.04% mAP. Further, the classification of defect positions using unseen data had approximately 92.27% accuracy, 94.33% specificity, and 92.05% sensitivity. Finally, our proposed model is validated with human expert with varying Kappa value. On average, these results hold promise of increasing suitability in clinical practice as a supporting diagnostic tool for establishing the diagnosis.

Determining the incidence of heart malformations in neonates: A novel and clinically approved solution

Background

Screening for critical congenital heart defects should be performed as early as possible and is essential for saving the lives of children and reducing the incidence of undetected adult congenital heart diseases. Heart malformations remain unrecognized at birth in more than 50% of neonates at maternity hospitals. Accurate screening for congenital heart malformations is possible using a certified and internationally patented digital intelligent phonocardiography machine. This study aimed to assess the actual incidence of heart defects in neonates. A pre-evaluation of the incidence of unrecognized severe and critical congenital heart defects at birth in our well-baby nursery was also performed.

Methods

We conducted the Neonates Cardiac Monitoring Research Project (ethics approval number: IR-IUMS-FMD. REC.1398.098) at the Shahid Akbarabadi Maternity Hospital. This study was a retrospective analysis of congenital heart malformations observed after screening 840 neonates. Using a double-blind format, 840 neonates from the well-baby nursery were randomly chosen to undergo routine clinical examinations at birth and digital intelligent phonocardiogram examinations. A pediatric cardiologist performed echocardiography for each neonate classified as having abnormal heart sounds using an intelligent machine or during routine medical examinations. If the pediatric cardiologist requested a follow-up examination, then the neonate was considered to have a congenital heart malformation, and the cumulative incidence was calculated accordingly.

Results

The incidence of heart malformations in our well-baby nursery was 5%. Furthermore, 45% of heart malformations were unrecognized in neonates at birth, including one critical congenital heart defect. The intelligent machine interpreted innocent murmurs as healthy heart sound.

Conclusion

We accurately and cost-effectively screened for congenital heart malformations in all neonates in our hospital using a digital intelligent phonocardiogram. Using an intelligent machine, we successfully identified neonates with CCHD and congenital heart defects that could not be detected using standard medical examinations. The Pouya Heart machine can record and analyze sounds with a spectral power level lower than the minimum level of the human hearing threshold. Furthermore, by redesigning the study, the identification of previously unrecognized heart malformations could increase to 58%.

Deep Learning for Improving the Effectiveness of Routine Prenatal Screening for Major Congenital Heart Diseases

Early prenatal screening with an ultrasound (US) can significantly lower newborn mortality caused by congenital heart diseases (CHDs). However, the need for expertise in fetal cardiologists and the high volume of screening cases limit the practically achievable detection rates. Hence, automated prenatal screening to support clinicians is desirable. This paper presents and analyses potential deep learning (DL) techniques to diagnose CHDs in fetal USs. Four convolutional neural network architectures were compared to select the best classifier with satisfactory results. Hence, dense convolutional network (DenseNet) 201 architecture was selected for the classification of seven CHDs, such as ventricular septal defect, atrial septal defect, atrioventricular septal defect, Ebstein's anomaly, tetralogy of Fallot, transposition of great arteries, hypoplastic left heart syndrome, and a normal control. The sensitivity, specificity, and accuracy of the DenseNet201 model were 100%, 100%, and 100%, respectively, for the intra-patient scenario and 99%, 97%, and 98%, respectively, for the inter-patient scenario. We used the intra-patient DL prediction model to validate our proposed model against the prediction results of three expert fetal cardiologists. The proposed model produces a satisfactory result, which means that our model can support expert fetal cardiologists to interpret the decision to improve CHD diagnostics. This work represents a step toward the goal of assisting front-line sonographers with CHD diagnoses at the population level.

Fifteen-minute consultation: Cardiac murmurs in the Newborn Infant Physical Examination (NIPE)

The finding of a cardiac murmur on the initial newborn examination is common but may be a source of anxiety for practitioners due to worries about missing critical congenital heart defects (CHDs). This article aims to provide an approach to this common finding, in particular, reviewing the evidence base behind features of the history, examination and subsequent non-specialist investigations which may increase the likelihood of CHDs. The aim of this structured approach is to give clinicians confidence in dealing with this common clinical finding, to be able to pick out those infants most at risk of having critical CHDs.

Elevated congenital heart disease birth prevalence rates found in Central Vietnam and dioxin TCDD residuals from the use of 2, 4, 5-T herbicides (Agent Orange) in the Da Nang region

Congenital heart disease (CHD) birth prevalence rate in Da Nang City and two adjacent provinces in Central Vietnam reported by Giang et al. in 2019 was 20.09/1000 births, much higher than any CHD birth rates previously reported. In this current study, three physicians trained in pediatric cardiology reanalyzed and reclassified the Giang et al 2019 cardiac anomalies data, eliminating singular small PDAs and separating cardiac defects into 27 contemporary CHD subgroups. These CHD subgroups were then statistically compared with Liu et al. 2019 Global CHD birth prevalence study of Asian Low-Middle Income Countries (LMIC) CHD subgroup rate of 9.34/1000 births (95% CI 8.07-10.70). Despite applying newer diagnostic criteria and refining the cardiac anomalies data, the Da Nang region continued to show significantly (p<0.0001) elevated total CHD birth prevalence rates at 14.71/1000 births (95% CI 12.74-16.69) compared to the Asian LMIC CHD birth prevalence rate 9.34/1000 births. This finding raises the question of whether environmental persistence of the contaminant dioxin TCDD from 2,4,5-T herbicides (Agent Orange) used during the Vietnam War (1961-1971) in the Da Nang region might be a factor associated with elevated CHD birth prevalence, as it is not present in other LMIC surrounding Vietnam. We recommend testing of soils and sediments in rural and agricultural areas in Central Vietnam that received high volume applications of contaminated herbicides to assess the relationship of the higher CHD birth prevalence rate and the presence of residual dioxin TCDD. Enhanced fetal cardiac echocardiograpy in the region to screen for CHD would enable early interventions and could improve outcomes for infants and children.

Deep Learning-Based Computer-Aided Fetal Echocardiography: Application to Heart Standard View Segmentation for Congenital Heart Defects Detection

Accurate segmentation of fetal heart in echocardiography images is essential for detecting the structural abnormalities such as congenital heart defects (CHDs). Due to the wide variations attributed to different factors, such as maternal obesity, abdominal scars, amniotic fluid volume, and great vessel connections, this process is still a challenging problem. CHDs detection with expertise in general are substandard; the accuracy of measurements remains highly dependent on humans' training, skills, and experience. To make such a process automatic, this study proposes deep learning-based computer-aided fetal heart echocardiography examinations with an instance segmentation approach, which inherently segments the four standard heart views and detects the defect simultaneously. We conducted several experiments with 1149 fetal heart images for predicting 24 objects, including four shapes of fetal heart standard views, 17 objects of heart-chambers in each view, and three cases of congenital heart defect. The result showed that the proposed model performed satisfactory performance for standard views segmentation, with a 79.97% intersection over union and 89.70% Dice coefficient similarity. It also performed well in the CHDs detection, with mean average precision around 98.30% for intra-patient variation and 82.42% for inter-patient variation. We believe that automatic segmentation and detection techniques could make an important contribution toward improving congenital heart disease diagnosis rates.