Screening For Congenital Heart Disease Research Articles

A Framework for AI-Assisted Detection of Patent Ductus Arteriosus from Neonatal Phonocardiogram

The current diagnosis of Congenital Heart Disease (CHD) in neonates relies on echocardiography. Its limited availability requires alternative screening procedures to prioritise newborns awaiting ultrasound. The routine screening for CHD is performed using a multidimensional clinical examination including (but not limited to) auscultation and pulse oximetry. While auscultation might be subjective with some heart abnormalities not always audible it increases the ability to detect heart defects. This work aims at developing an objective clinical decision support tool based on machine learning (ML) to facilitate differentiation of sounds with signatures of Patent Ductus Arteriosus (PDA)/CHDs, in clinical settings. The heart sounds are pre-processed and segmented, followed by feature extraction. The features are fed into a boosted decision tree classifier to estimate the probability of PDA or CHDs. Several mechanisms to combine information from different auscultation points, as well as consecutive sound cycles, are presented. The system is evaluated on a large clinical dataset of heart sounds from 265 term and late-preterm newborns recorded within the first six days of life. The developed system reaches an area under the curve (AUC) of 78% at detecting CHD and 77% at detecting PDA. The obtained results for PDA detection compare favourably with the level of accuracy achieved by an experienced neonatologist when assessed on the same cohort.

Detection of Cardiac Structural Abnormalities in Fetal Ultrasound Videos Using Deep Learning

Artificial Intelligence (AI) technologies have recently been applied to medical imaging for diagnostic support. With respect to fetal ultrasound screening of congenital heart disease (CHD), it is still challenging to achieve consistently accurate diagnoses owing to its manual operation and the technical differences among examiners. Hence, we proposed an architecture of Supervised Object detection with Normal data Only (SONO), based on a convolutional neural network (CNN), to detect cardiac substructures and structural abnormalities in fetal ultrasound videos. We used a barcode-like timeline to visualize the probability of detection and calculated an abnormality score of each video. Performance evaluations of detecting cardiac structural abnormalities utilized videos of sequential cross-sections around a four-chamber view (Heart) and three-vessel trachea view (Vessels). The mean value of abnormality scores in CHD cases was significantly higher than normal cases (p < 0.001). The areas under the receiver operating characteristic curve in Heart and Vessels produced by SONO were 0.787 and 0.891, respectively, higher than the other conventional algorithms. SONO achieves an automatic detection of each cardiac substructure in fetal ultrasound videos, and shows an applicability to detect cardiac structural abnormalities. The barcode-like timeline is informative for examiners to capture the clinical characteristic of each case, and it is also expected to acquire one of the important features in the field of medical AI: the development of “explainable AI.”

Teste da oximetria de pulso em unidade neonatal de referência - avaliação após 3 anos de sua implantação como teste de triagem universal

INTRODUCTION: The present study searched to evaluate the results of pulse oximetry test in the screening of critical congenital heart disease in a public maternity hospital in Brazil, especially regarding the rate of positive and false positive tests. METHODS: A descriptive, retrospective and cross-sectional study was conducted by collecting data from the oximetry test logbook and from an electronic medical record from January to December 2018.The results were compared with the others described in the literature. RESULTS: 1,976 pulse oximetry tests were performed, with 303 alterations initially. 52 newborns had kept the altered test after retest, and 39 newborns were excluded. Among the altered tests, 9 congenital heart defects were found, but no critical congenital heart defects, generating 2.6% of false positive tests. CONCLUSION: The pulse oximetry test as a neonatal screening tool was important for the diagnosis of newborns with congenital heart disease, even though no cases of critical congenital heart defects. The number of false positive tests observed was much higher than reported in the literature, causing indirect costs in length of hospital stay, unnecessary examinations and family anxiety.

The screening of congenital heart disease by cardiac auscultation and 12-lead electrocardiogram among Indonesian elementary school students.

Screening for congenital heart disease (CHD) in school students is well-established in high-income countries; however, data from low-to-middle-income countries including Indonesia are limited. This study aimed to evaluate CHD screening methods by cardiac auscultation and 12-lead electrocardiogram to obtain the prevalence of CHD, confirmed by transthoracic echocardiography, among Indonesian school students. We conducted a screening programme in elementary school students in the Province of Special Region of Yogyakarta, Indonesia. The CHD screening was integrated into the annual health screening. The trained general practitioners and nurses participated in the screening. The primary screening was by cardiac auscultation and 12-lead electrocardiogram. The secondary screening was by transthoracic echocardiography performed on school students with abnormal findings in the primary screening. A total of 6116 school students were screened within a 2-year period. As many as 329 (5.38%) school students were detected with abnormalities. Of those, 278 students (84.49%) had an abnormal electrocardiogram, 45 students (13.68%) had heart murmurs, and 6 students (1.82%) had both abnormalities. The primary screening programme was successfully implemented. The secondary screening was accomplished for 260 school students, and 18 students (6.9%) had heart abnormalities with 7 (2.7%) who were confirmed with septal defects and 11 (4.2%) had valve abnormalities. The overall prevalence was 0.29% (18 out of 6116). The primary screening by cardiac auscultation and 12-lead electrocardiogram was feasible and yielded 5.38% of elementary school students who were suspected with CHD. The secondary screening resulted in 6.9% confirmed cardiac abnormalities. The cardiac abnormality prevalence was 0.29%.

Evaluation of Circulating Cardiovascular Biomarker Levels for Early Detection of Congenital Heart Disease in Newborns in Sweden

Congenital heart disease (CHD) is the most common congenital malformation in humans worldwide. Circulating cardiovascular biomarkers could potentially improve the early detection of CHD, even in asymptomatic newborns. To assess the performance of a dried blood spot (DBS) test to measure the cardiovascular biomarker amino terminal fragment of the prohormone brain-type natriuretic peptide (NT-proBNP) levels in newborns and to compare DBS with standard EDTA analysis in control newborns during the first week of life. This diagnostic study was conducted in a single regional pediatric service in southern Sweden. Healthy, term neonates born between July 1, 2018, and May 31, 2019, were prospectively enrolled and compared against retrospectively identified newborns with CHD born between September 1, 2003, and September 30, 2019. Neonates who required inpatient treatment beyond the standard postnatal care were excluded. New DBS test for NT-proBNP quantification in newborns that used 3 μL of blood vs the current screening standard. Performance of the new test and when combined with pulse oximetry screening was measured by receiver operating characteristic curve analysis. Performance of the new test and EDTA screening was compared using Pearson linear correlation analysis. The DBS samples of 115 neonates (81 control newborns and 34 newborns with CHD, of whom 63 were boys [55%] and the mean [SD] gestational age was 39.6 [1.4] weeks) were analyzed. The new NT-proBNP test alone identified 71% (n = 24 of 34) of all CHD cases and 68% (n = 13 of 19) of critical CHD cases as soon as 2 days after birth. Detection of any CHD type improved to 82% (n = 28 of 34 newborns) and detection of critical CHD improved to 89% (n = 17 of 19 newborns) when combined pulse oximetry screening and NT-proBNP test results were used. Performance of the NT-proBNP test was excellent when control newborns were matched to newborns with CHD born between July 1, 2018, and May 31, 2019 (area under the curve, 0.96; SE, 0.027; 95% CI, 0.908-1.0; asymptotic P < .05). This study found that NT-proBNP assay using minimal DBS samples appears to be timely and accurate in detecting CHD in newborns and to discriminate well between healthy newborns and newborns with various types of CHD. This finding warrants further studies in larger cohorts and highlights the potential of NT-proBNP to improve neonatal CHD screening.

Abstract 13617: Newborn Critical Congenital Heart Disease Screening Fails to Detect Target Lesions or Reduce Mortality

Introduction: Congenital heart disease (CHD) affects over one million children in the United States. Studies show mixed outcomes regarding a survival benefit from newborn cardiac screening (NCS). California began a NCS program on 7/1/13. We evaluated the effect of mandatory NCS on surgical outcomes of our program. Hypothesis: Neonates with critical CHD (CCHD), requiring surgery as infants, who are not diagnosed prior to or at the NCS have lower survival than those diagnosed prior to or at the NCS. Methods: We evaluated all infants with CCDH undergoing cardiac surgery at our center between 07/01/13 - 12/31/18. Subjects were stratified by timing of diagnosis (pre-screen, screen positive, screen negative). Sensitivity to detect specific lesions was calculated. Primary end-points were operative mortality, absolute mortality, and actuarial survival. Results: Two-hundred-seventy-four infants with CCHD were included. Seventy-nine percent were diagnosed prior to screening, while 8% were diagnosed by NCS, and 13% were screen negative. Total anomalous pulmonary venous return (TAPVR) (47%) and aortic coarctation (CoA) (40%) were the most likely to be undiagnosed at time of NCS (p&lt;0.001). Sensitivity to detect target lesions was 38% overall [TAPVR 73%, CoA 12%, hypoplastic left heart syndrome (HLHS) 25%, Tetralogy of Fallot (TOF) 29%]. Primary end-points were not different based on timing of diagnosis (p&gt;0.05) (Figure). Conclusions: We found only a 38% sensitivity of mandatory newborn CCHD screening to detect target cardiac lesions requiring surgery in the first year of life. A high proportion of newborns with HLHS, TOF, and CoA remained undiagnosed after screening, though TAPVR was readily detected. There were no differences in survival between the screening groups. Mandatory newborn CCHD pulse oximetry screening can detect some newborns with critical heart disease, but should not replace traditional methods of monitoring in the fetal, newborn, and infant periods.

Impact of maternal obesity on fetal cardiac screening: which follow-up strategy is cost-effective?

To perform a cost-effectiveness analysis of different follow-up strategies for non-obese and obese women who had incomplete fetal cardiac screening for major congenital heart disease (CHD). Three decision-analytic models, one each for non-obese, obese and Class-III-obese women, were developed to compare five follow-up strategies for initial suboptimal fetal cardiac screening. The five strategies were: (1) no follow-up ultrasound (US) examination but direct referral to fetal echocardiography (FE); (2) one follow-up US, then FE if fetal cardiac views were still suboptimal; (3) up to two follow-up US, then FE if fetal cardiac views were still suboptimal; (4) one follow-up US and no FE; and (5) up to two follow-up US and no FE. The models were designed to identify fetuses with major CHD in a theoretical cohort of 4 000 000 births in the USA. Outcomes related to neonatal mortality and neurodevelopmental disability were evaluated. A cost-effectiveness willingness-to-pay threshold was set at US$100 000 per quality-adjusted life year (QALY). Base-case and sensitivity analysis and Monte-Carlo simulation were performed. In our base-case models for all body mass index (BMI) groups, no follow-up US, but direct referral to FE led to the best outcomes, detecting 7%, 25% and 82% more fetuses with CHD in non-obese, obese and Class-III-obese women, respectively, compared with the baseline strategy of one follow-up US and no FE. However, no follow-up US, but direct referral to FE was above the US$100 000/QALY threshold and therefore not cost-effective. The cost-effective strategy for all BMI groups was one follow-up US and no FE. Both up to two follow-up US with no FE and up to two follow-up US with FE were dominated (being more costly and less effective), while one follow-up US with FE was over the cost-effectiveness threshold. One follow-up US and no FE was the optimal strategy in 97%, 93% and 86% of trials in Monte-Carlo simulation for non-obese, obese and Class-III-obese models, respectively. For both non-obese and obese women with incomplete fetal cardiac screening, the optimal CHD follow-up screening strategy is no further US and immediate referral to FE; however, this strategy is not cost-effective. Considering costs, one follow-up US and no FE is the preferred strategy. For both obese and non-obese women, Monte-Carlo simulations showed clearly that one follow-up US and no FE was the optimal strategy. Both non-obese and obese women with initial incomplete cardiac screening examination should therefore be offered one follow-up US. Copyright © 2019 ISUOG. Published by John Wiley & Sons Ltd.

Artificial intelligence technology in cardiac auscultation screening for congenital heart disease: present and future

The electronic stethoscope combined with artificial intelligence (AI) technology has realized the digital acquisition of heart sounds and intelligent identification of congenital heart disease, which provides objective basis for heart sound auscultation and improves the accuracy of congenital heart disease diagnosis. At the present stage, the AI based cardiac auscultation technique mainly focuses on the research of AI algorithms, and the researchers have designed and summarized a variety of effective algorithms based on the characteristics of cardiac audio data, among which the mel-frequency cepstral coefficients (MFCC) is the most effective one, and widely used in the cardiac auscultation. However, the current cardiac sound analysis techniques are based on specific data sets, and have not been validated in clinic, so the performance of algorithms need to be further verified. The lack of heart sound data, especially the high-quality, standardized, publicly available heart sound database with disease labeling, further restricts the development of heart sound diagnostic analysis and its application in screening. Therefore, expert consensus is necessary in establishing an authoritative heart sound database and standardizing the heart sound auscultation screening process for congenital heart disease. This paper provides an overview of the research and application status of auscultation algorithm and hardware equipment based on AI in auscultation screening of congenital heart disease, and puts forward the problems to be solved in clinical application of AI auscultation screening technology.

A novel system to collect dual pulse oximetry data for critical congenital heart disease screening research.

Access to patient medical data is critical to building a real-time data analytic pipeline for improving care providers' ability to detect, diagnose, and prognosticate diseases. Critical congenital heart disease (CCHD) is a common group of neonatal life-threatening defects that must be promptly diagnosed to minimize morbidity and mortality. CCHD can be diagnosed both prenatally and postnatally. However, despite current screening practices involving oxygen saturation analysis, timely diagnosis is missed in approximately 900 infants with CCHD annually in the USA and can benefit from increased data processing capabilities. Adding non-invasive perfusion measurements to oxygen saturation data can improve the timeliness and fidelity of CCHD diagnostics. However, real-time monitoring and interpretation of non-invasive perfusion data are currently limited. To address this challenge, we created a hardware and software architecture utilizing a Pi-top™ for collecting, visualizing, and storing dual oxygen saturation, perfusion indices, and photoplethysmography data. Data aggregation in our system is automated and all data files are coded with unique study identifiers to facilitate research purposes. Using this system, we have collected data from 190 neonates, 130 presumably without and 60 with congenital heart disease, in total comprising 1665 min of information. From these data, we are able to extract non-invasive perfusion features such as perfusion index, radiofemoral delay, and slope of systolic rise or diastolic fall. This data collection and waveform analysis is relatively inexpensive and can be used to enhance future CCHD screening algorithms.

Accuracy of prenatal screening for congenital heart disease in population: A retrospective study in Southern France

Congenital heart diseases (CHDs) are the most common congenital malformations. The objective of our study was to evaluate the prenatal screening accuracy of congenital heart disease (CHD) in Southern France and to evaluate the impact of a prenatal diagnosis on pregnancies outcomes and neonatal outcomes. We performed a bicentric, retrospective observational study in the southern region over 4 years was conducted between 1 January 2014 and 31 December 2017. All foetuses and children under one year of age with CHD monitored in the UTHs (University Teaching Hospitals) in Marseille and Nice were included. CHD cases were divided into 3 groups: group 1, those with no possible options for anatomical repair; group 2, those with anatomical repair possibilities but that may require neonatal cardiologic management; and group 3, those with anatomical repair possibilities that do not require an emergency neonatal procedure. Among the 249070 deliveries during the study period, 677 CHD cases were included in the study. The overall prenatal screening rate was 71.5%. The screening rates were 97.8%, 63.6%, and 65.9% for groups 1, 2 and 3, respectively. Among group 2 CHD cases, 80% of the transpositions of the great arteries, 56% of the aortic coarctations, and 20% of the total anomalous pulmonary venous returns were detected during the prenatal period. A genetic anomaly was found in 16% of CHD cases. The overall mortality rate was 11.3% with a higher death rate in cases of prenatal screening (17.2% versus 2.1%; p < 0.001). However, when focusing only on children who died of CHD, prenatal screening did not create an impact (56.6% versus 100%, p = 0,140). Our data showed that the prenatal screening rate of CHD appears satisfactory in Southern France. Nevertheless, it could be improved for some CHD. This study did not find any benefit in terms of mortality from prenatal screening for CHD.

Study the universal critical congenital heart disease screening in a peripheral area of Uttarakhand, India

Background: Congenital heart disease (CHD) is the most frequently occurring congenital disorder, responsible for 28% of all congenital birth defects. The birth prevalence of CHD is reported to be 8-12/1000 live births. Considering a rate of 9/1000, about 1.35 million babies are born with CHD each year globally. Objective of research work to study the prevalence of CHD among newborn and its types.Methods: This cross-sectional study was carried among 34 cases of CHD/5126 newborn screened at 4 birthing places in Kashipur a small town in Uttrakhand at pediatrics department of Sahota Super-specialty hospital, Kashipur, Uttarakhand. Screening program between 22 August 2014, and March 30, 2019. All newborns, including preterm babies, delivered in these facilities were eligible for inclusion in this study.Results: Present study found the prevalence of CHD was 0.7 per 1000 children (34/5126). Around 26.5% participants have cyanotic CHD and 73.5% have acynotic CHD. Almost 44%, 28%, 20%, 4% and 4% participants of acynotic congenital heart diseases have VSD, ASD, PDA, AVSD and valvular PS respectively and 55.6%, 22.2%, 11.1% and 11.1% participants of cynotic congenital heart diseases have TOF, DORV/VSD, dTGA/VSD and tricuspid atresia respectively.Conclusions: Screening for congenital heart disease should be included as a part of newborn assessment as it is a common congenital problem. Early identification influences outcome. Barriers in implementation of the screening programmes in resource limited setting is a challenging feature. This study can provide observed data that can help in policy making in the health sector.

Inadequacies of hospital-level critical congenital heart disease screening data reports: implications for research and quality efforts.

Objective:Assess the quality of critical congenital heart disease (CCHD) screening data reports in California, where CCHD screening is not mandatory but reporting is.Study Design:Retrospective review of California hospital-level CCHD screening data to evaluate data reliability and adherence to state screening and reporting recommendations. Data were evaluated for internal consistency and compared to two databases.Results:Over one-third of hospitals did not submit data. Only 70.7% of the Vital Records live births were reported in CCHD screening data. Only 46% of reporting hospitals submitted data with matching numbers of completed screens and results, and 22% matched their respective live births in a second database.Conclusion:CCHD data reporting in California is incomplete, which may miss 359 CCHD cases/year from non-reporting. Data inconsistencies may miss additional cases. Mandatory screening, reporting and improvements in data reliability are urgently needed to inform screening modifications and enhance timely detection and disease surveillance.

Recommended Changes to Critical Congenital Heart Disease Screening by Pulse Oximetry in Newborns

In 2011, an algorithm for pulse oximetry screening in newborns to detect critical congenital heart disease was published and subsequently endorsed by

Updated Strategies for Pulse Oximetry Screening for Critical Congenital Heart Disease.

Seven years after its addition to the US Recommended Uniform Screening Panel, newborn screening for critical congenital heart disease (CCHD) using pulse oximetry became mandatory in the United States. Although CCHD newborn screening reduces morbidity and mortality, there remain important opportunities to improve. An expert panel convened for a 1-day meeting in September 2018, including subject matter experts and representatives from stakeholder organizations. Presentations on CCHD outcomes, variations in approach to screening, and data and quality improvement helped identify improvement opportunities. The expert panel concluded that sufficient evidence exists to recommend modifying the current American Academy of Pediatrics algorithm by (1) requiring an oxygen saturation of at least 95% in both (formerly either) the upper and lower extremities to pass and (2) requiring only 1 repeat screen instead of 2 for cases that neither pass nor fail initially. The panel underscored the importance of improving public health reporting by further specifying the targets of screening and criteria for reporting outcomes (false-negative and false-positive cases). The panel also highlighted the need to ensure sufficient public health funding for CCHD newborn screening and opportunities for education and global implementation. Newborn screening for CCHD using pulse oximetry has led to significant improvements in child health outcomes. However, further important work is required to understand and improve the effectiveness and efficiency of screening.

Pulse Oximetry and Congenital Heart Disease Screening: Results of the First Pilot Study in Morocco.

Congenital heart disease (CHD) is the most common congenital malformation. Diagnosis of critical congenital heart disease (CCHD), the most severe type of congenital heart disease, in a newborn may be difficult. The addition of CCHD screening, using pulse oximetry, to clinical assessment significantly improves the rate of detection. We conducted a pilot study in Morocco on screening neonates for critical congenital heart disease. This study was conducted in the maternity ward of Mohammed VI University Hospital of Marrakesh, Morocco, and included asymptomatic newborns delivered between March 2019 and January 2020. The screening of CCHD was performed by pulse oximetry measuring the pre- and post-ductal saturation. Screening was performed on 8013/10,451 (76.7%) asymptomatic newborns. According to the algorithm, 7998 cases passed the screening test (99.82%), including one inconclusive test that was repeated an hour later and was normal. Fifteen newborns failed the screening test (0.18%): five CCHD, five false positives, and five CHD but non-critical. One false negative case was diagnosed at 2 months of age. Our results encourage us to strengthen screening for CCHD by adding pulse oximetry to the routine newborn screening panel.

Altitude at Birth on Critical Congenital Heart Disease Screening Through Pulse Oximetry in Newborns in Colombia - A Validation by Experts

Critical Congenital Heart Diseases (CCHDs) are heart anomalies that if untreated within the first year of life, can lead to death. Current strategies for an early diagnosis involve fetal echocardiography and physical examination. However, these practices fail to diagnose more than 50% of the cases. Since most CCHDs are hypoxic, the use of pulse oximetry to measure arterial oxygen saturation (SaO2) is considered as a complementary method for their detection.

Considerations for Newborn Screening for Critical Congenital Heart Disease in Low- and Middle-Income Countries.

We propose several considerations for implementation of critical congenital heart disease (CCHD) screening for low- and middle-income countries to assess health system readiness for countries that may not have all the downstream capacity needed for treatment of CCHD. The recommendations include: (1) assessment of secondary and tertiary level CHD health services, (2) assessment of birth delivery center processes and staff training needs, (3) data collection on implementation and quality surgical outcomes, (4) budgetary consideration, and (5) consideration of the CCHD screening service as part of the overall patient care continuum.

Oxygen saturation and perfusion index screening in neonates at high altitudes: can PDA be predicted?

Screening critical congenital heart disease in neonates with 24-48 h of age could be made by oxygen saturation determination. Perfusion index may be used as an adjunct to pulse oximetry screening to detect non-cyanotic critical congenital heart disease cases such as a left heart outflow obstruction. We evaluate the results of combined screening for oxygen saturation and peripheral perfusion index at high altitudes. The study included 501 neonates older than gestational week 35. The mean oxygen saturation was lower than at sea level, and the screening test was positive in a total of 21 (4.2%) babies. Critical congenital heart diseases were not detected in any patient. A total of 10 (2%) babies were detected with PDA, nine (1.8%) of whom recorded a positive screening test. The prevalence of PDA was significantly higher in the positive screening test group when compared with those who underwent echocardiography due to clinical findings.Conclusion: The median peripheral perfusion index at high altitude was not lower than at sea level, while the mean oxygen saturation, in contrast, was lower than at sea level. The low partial oxygen pressure found at high altitudes leads to a variation in postnatal adaptation and an increased prevalence of PDA. Accordingly, oxygen saturation screening may serve to identify babies with PDA at high altitudes. What is Known: • Oxygen saturation is known to be low at high altitudes, and thus the rates of false positivity are high when screening for critical congenital heart disease. • High altitudes are also associated with an increased prevalence of simple congenital heart disease. What is New: • The peripheral perfusion index at high altitude is not lower than at sea level. • The prevalence of PDA is significantly higher in those with false positive screening results.

Implementation of diagnostic screening for congenital heart disease in Hidalgo, Mexico

Objective Implementing screening through pulse oximetry (PO) and a knowledge management model (KMM) for early detection of life-threatening congenital heart disease (CHD) in the neonatal period. Material and methods Pilot study of PO implementation supported by clinical criteria performed in newborns at two public hospitals of Hidalgo State. Those who tested positive were referred for echocardiography and those diagnosed with critical CHD (CCHD) were referred to specialized hospitals for treatment. Results 1748 newborns were screened: 29 positive, 62% with CHD and 13.8% with CCHD, one death, three referrals to palliative treatment. Conclusion PO as a method of screening helps in early diagnosis of CHD added to clinical and echocardiography studies. KMM fosters innovation and resource management.

Using pulse oximetry waveforms to detect coarctation of the aorta

BackgroundCoarctation of the aorta is a common form of critical congenital heart disease that remains challenging to diagnose prior to clinical deterioration. Despite current screening methods, infants with coarctation may present with life-threatening cardiogenic shock requiring urgent hospitalization and intervention. We sought to improve critical congenital heart disease screening by using a novel pulse oximetry waveform analysis, specifically focused on detection of coarctation of the aorta.Methods and resultsOver a 2-year period, we obtained pulse oximetry waveform data on 18 neonates with coarctation of the aorta and 18 age-matched controls hospitalized in the cardiac intensive care unit at Children’s Healthcare of Atlanta. Patients with coarctation were receiving prostaglandin E1 and had a patent ductus arteriosus. By analyzing discrete features in the waveforms, we identified statistically significant differences in the maximum rate of fall between patients with and without coarctation. This was accentuated when comparing the difference between the upper and lower extremities, with the lower extremities having a shallow slope angle when a coarctation was present (p-value 0.001). Postoperatively, there were still differences in the maximum rate of fall between the repaired coarctation patients and controls; however, these differences normalized when compared with the same individual’s upper vs. lower extremities. Coarctation patients compared to themselves (preoperatively and postoperatively), demonstrated waveform differences between upper and lower extremities that were significantly reduced after successful surgery (p-value 0.028). This screening algorithm had an accuracy of detection of 72% with 0.61 sensitivity and 0.94 specificity.ConclusionsWe were able to identify specific features in pulse oximetry waveforms that were able to accurately identify patients with coarctation and further demonstrated that these changes normalized after surgical repair. Pulse oximetry screening for congenital heart disease in neonates may thus be improved by including waveform analysis, aiming to identify coarctation of the aorta prior to critical illness. Further large-scale testing is required to validate this screening model among patients in a newborn nursery setting who are low risk for having coarctation.