Pulse Oximetry Screening for Critical Congenital Heart Defects: A Life-Saving Test for All Newborn Babies

A cluster-based ensemble approach for congenital heart disease prediction

BACKGROUND

One of the most prevalent birth disorders is congenital heart diseases (CHD). Although CHD risk factors have been the subject of numerous studies, their propensity to cause CHD has not been tested. Particularly few research has attempted to forecast CHD risk using population-based cross-sectional data, which is inherently imbalanced.

OBJECTIVE

The main goals of this study are to create a reliable data analysis model that can help with (i) a better understanding of congenital heart disease prediction in the presence of missing and unbalanced data and (ii) creating cohorts of expectant mothers with similar lifestyle characteristics.

METHODS

Clusters of patient cohorts are produced using the unsupervised data mining technique density-based spatial clustering of applications with noise (DBSCAN). For more accurate CHD prediction, a random forest model was trained using these clusters and their corresponding patterns. This study uses a dataset of 33,831 expectant mothers to make its prediction. Missing data were handled using the k-NN imputation approach, while extremely unbalanced data were balanced using SMOTE. These techniques are all data-driven and need little to no user or expert involvement.

RESULTS AND CONCLUSION

Using DBSCAN, three cohorts were found. The cluster information enhanced the random forest-based CHD prediction and revealed intricate factors that influence prediction accuracy. The proposed approach gave the highest results with 99 % accuracy and 0.91 AUC and performed better than the state-of-the-art methodologies. Hence, the suggested method using unsupervised learning can provide intricate information to the classifier and further enhance the performance of the classification.

Evaluation of critical congenital heart disease from 2018 to 2020 in Turkey: a retrospective cohort study

BACKGROUND

The aim of this study is to examine the features of critical congenital heart disease (CCHD).

METHODS

The study was planned as a retrospective cohort study. Data for the study were obtained through national data collection systems and 2018-2020 CCHD cohort was established. In this study, we divided the patients into two groups: Group 1 included seven primary target diseases of the newborn CCHD screening program and Group 2 included secondary target diseases.

RESULTS

There were 9884 CCHD cases, with a prevalence of 27.8 per 10,000 live births. Of the cases 44.4% were in Group 1 (12.3 per 10,000) and 54.8% were in Group 2 (15.2 per 10,000). Of all cases 55.5% were male and the female/male ratio was 1/1.2. While 21.8% of the cases were premature, 23.0% were babies with low birth weight (LBW), 4.8% were born from multiple pregnancies. The highest prevalence of CCHD was found in LBW (84.8 per 10,000), premature infants (57.8 per 10,000) (p < 0.001). The fatality rate in the cohort was 16.6% in the neonatal period, 31.6% in the first year of life respectively. The mean estimated survival time in the birth cohort was 40.0 months (95% CI: 39.5-40.6). The mean survival time for Group 1 diseases was 33.4 months (95% CI: 32.5-34.2), while it was 45.4 months (95% CI: 44.7-46.0) for Group 2 diseases (p < 0.001). Preterm birth, LBW, maternal age and region were evaluated as factors associated with mortality risk.

CONCLUSION

This study showed that CCHDs are common in Turkey and mortality rates are high. There are regional differences in CCHD both prevalence and survival. Improving prenatal diagnosis rates and expanding neonatal CCHD screening are of key importance.

Heart Disease Screening and False Hypoxemia in the Neonate

BACKGROUND

Screening for congenital heart diseases by pulse oximetry is used for the initial assessment of the neonate. Variants of hemoglobin F can compromise light absorbance, inducing erroneous results.

CASE REPORT

Two infants screened for congenital heart disease showed an asymptomatic low peripheral oxygen saturation. Arterial blood gases analysis revealed a normal arterial pressure of oxygen and oxygen saturation. More likely and/or severe causes of hypoxemia were ruled out. This "artifact" with SpO2-SaO2 dissociation, and after exclusion of other common etiologies of hypoxemia, raised the clinical suspicion of hemoglobinopathy. Hemoglobin molecular and genetic studies identified specific mutations in gamma chains from hemoglobin F, named hemoglobin F Sardinia.

CONCLUSION

Hemoglobin F variants may result in low peripheral oxygen saturation readings by pulse oximetry, explaining the discordance in the clinical appearance and low peripheral oxygen saturation readings.

Cyanotic congenital heart disease - Not always blue to provide a clue: Time to replace cyanosis with arterial desaturation!

Despite right-to-left shunt, not all patients with so-called cyanotic congenital heart disease (CHD) are cyanosed at all times. Moreover, despite undisputed clinical utility, cyanosis is unreliable for the detection of arterial desaturation. Pulse oximetry, on the other hand, provides a much easier, reliable, and accurate method for detecting arterial desaturation. For optimal detection, therefore, it is perhaps sensible to replace cyanosis with pulse oximetry-based detection of arterial desaturation in all cases with suspected CHD.

Newborn Critical Congenital Heart Disease Screening Using Pulse Oximetry: Value and Unique Challenges in Developing Regions

Newborn screening for critical congenital heart disease (CCHD) is recommended for implementation in many developed countries as the standard of care. Efforts to implement this point of care screen in developing regions face unique barriers, and present important opportunities. The First Pan-African Newborn Screening Conference, held in Rabat in June 2019, incorporated a workshop dedicated specifically to identifying and discussing CCHD screening issues in the Middle East Northern Africa (MENA) region. The issues explored may be beneficial as part of the greater discussion of CCHD screening's growing importance in developing regions around the world. Screening experts presented education and lessons learned from previous CCHD implementations, including a hands-on technical demonstration of CCHD screening. Children's HeartLink, The Newborn Foundation, and Children's National Hospital each presented on their experiences working with teams and pilot projects from around the world. Experience in implementation from Children's Hospital Marrakesh was presented and highlighted some of the unique findings, challenges, and experiences of screening in Morocco. As developing regions investigate the implementation of CCHD screening using pulse oximetry either as part of research studies, pilots, regional studies, or as part of a nationally supported program, data to inform policymakers on the benefits of screening and specific needs for infrastructure development and resources are essential. This special issue contains initial lessons learned on newborn CCHD screening from a select number of developing countries, including Saudi Arabia and Morocco and regions such as Latin America.