Background: With the dearth of trained care providers to diagnose congenital heart disease (CHD) and a surge in machine learning (ML) models, this review aims to estimate the diagnostic accuracy of such models for detecting CHD.Methods: A comprehensive literature search in the PubMed, CINAHL, Wiley Cochrane Library, and Web of Science databases was performed. Studies that reported the diagnostic ability of ML for the detection of CHD compared to the reference standard were included. Risk of bias assessment was performed using Quality Assessment for Diagnostic Accuracy Studies-2 tool. The sensitivity and specificity results from the studies were used to generate the hierarchical Summary ROC (HSROC) curve.Results: We included 16 studies (1217 participants) that used ML algorithm to diagnose CHD. Neural networks were used in seven studies with overall sensitivity of 90.9% (95% CI 85.2–94.5%) and specificity was 92.7% (95% CI 86.4–96.2%). Other ML models included ensemble methods, deep learning and clustering techniques but did not have sufficient number of studies for a meta-analysis. Majority (n=11, 69%) of studies had a high risk of patient selection bias, unclear bias on index test (n=9, 56%) and flow and timing (n=12, 75%) while low risk of bias was reported for the reference standard (n=10, 62%).Conclusion: ML models such as neural networks have the potential to diagnose CHD accurately without the need for trained personnel. The heterogeneity of the diagnostic modalities used to train these models and the heterogeneity of the CHD diagnoses included between the studies is a major limitation.
The management of patent ductus arteriosus (PDA) in preterm neonates remains controversial. A retrospective review was conducted to determine the outcomes in preterm neonates with PDA. Data of neonates admitted to the Aga Khan University Hospital from January 2012 to December 2016 were retrieved from patient records. Of the 208 neonates included in the study, 143 (68.7%) received no treatment, while 65 (31.2%) underwent pharmacotherapy and/or surgical ligation for PDA closure. PDA closure was spontaneous in 109 (52.4%) neonates. The mean ±SD gestational age (GA) of neonates with spontaneous ductal closure was greater as compared to those who required some form of treatment [33±3.3 vs 29.7±3.1weeks, p=0.001]. Apnoea (OR:4.47; 95% CI:1.21-16.44), sepsis (OR:3.81; 95% CI:1.33-10.87), pulmonary haemorrhage (OR:4.88; 95% CI:1.24-19.19), and lower APGAR (OR:0.69; 95% CI:0.54-0.90) were associated with higher odds of mortality in our cohort. Our findings demonstrate that PDA resolves spontaneously in most preterm neonates and provide evidence that conservative treatment is not associated with mortality. Keywords: Conservative treatment; ligation; mortality; patent ductus arteriosus; premature.
Background The conventional IMCI training for healthcare providers is delivered in 11 days, which can be expensive and disruptive to the normal clinical routines of the providers. An equally effective, shorter training course may address these challenges. Methods We conducted a quasi-experimental study in two provinces (Sindh and Punjab) of Pakistan. 104 healthcare providers were conveniently selected to receive either the abridged (7-day) or the standard (11-day) training. Knowledge and clinical skills of the participants were assessed before, immediately on conclusion of, and six months after the training. Results The improvement in mean knowledge scores of the 7-day and 11-day training groups was 31.6 (95% CI 24.3, 38.8) and 29.4 (95% CI 23.9, 34.9) respectively, p = 0.630 while the improvement in mean clinical skills scores of the 7-day and 11-day training groups was 23.8 (95% CI: 19.3, 28.2) and 23.0 (95% CI 18.9, 27.0) respectively, p = 0.784. The decline in mean knowledge scores six months after the training was − 12.4 (95% CI − 18.5, − 6.4) and − 6.4 (95% CI − 10.5, − 2.3) in the 7-day and 11-day groups respectively, p = 0.094. The decline in mean clinical skills scores six months after the training was − 6.3 (95% CI − 11.3, − 1.3) in the 7-day training group and − 9.1 (95% CI − 11.5, − 6.6) in the 11-day group, p = 0.308. Conclusion An abridged IMNCI training is equally effective as the standard training. However, training for certain illnesses may be better delivered by the standard course.
Background: We aimed to describe the outcomes of neonates born at or near term to women undergoing elective C-section without prophylactic corticosteroids. Methods: Single-centre retrospective observational study of neonates born between 36+0 and 42+0 weeks. Associations between neonatal complications and maternal and neonatal factors were evaluated by univariate analyses and multivariate logistic regression. Results: A total of 2151 (26%) neonates were born by elective C-section during the study period, of whom 429 were included in the study. Fifty-six (13.05%) neonates developed some complication with 39 (9.1%) requiring NICU admission. Respiratory distress syndrome (RDS) and hypoglycemia occurred in 21 (4.9%) and 7 (1.6%) neonates, respectively. Maternal age >35 was associated with higher odds of neonatal complications (OR: 5.52, 95% CI: 1.02-29.74, p=0.047). Conclusions: The rate of RDS was comparable to other reported studies. The study revealed a high rate of term elective C-sections, providing grounds for conducting further research on administering antenatal corticosteroid to this population to reduce new-born morbidities.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.