Prediction of cyanotic and acyanotic congenital heart disease using machine learning models

BACKGROUND Congenital heart disease is most commonly seen in neonates and it is a major cause of pediatric illness and childhood morbidity and mortality.AIM To identify and build the best predictive model for predicting cyanotic and acyanotic congenital heart disease in children during pregnancy and identify their potential risk factors.METHODS The data were collected from the Pediatric Cardiology Department at Chaudhry Pervaiz Elahi Institute of Cardiology Multan,Pakistan from December 2017 to October 2019.A sample of 3900 mothers whose children were diagnosed with identify the potential outliers.Different machine learning models were compared,and the best-fitted model was selected using the area under the curve,sensitivity,and specificity of the models.RESULTS Out of 3900 patients included,about 69.5%had acyanotic and 30.5%had cyanotic congenital heart disease.Males had more cases of acyanotic(53.6%)and cyanotic(54.5%)congenital heart disease as compared to females.The odds of having cyanotic was 1.28 times higher for children whose mothers used more fast food frequently during pregnancy.The artificial neural network model was selected as the best predictive model with an area under the curve of 0.9012,sensitivity of 65.76%,and specificity of 97.23%.CONCLUSION Children having a positive family history are at very high risk of having cyanotic and acyanotic congenital heart disease.Males are more at risk and their mothers need more care,good food,and physical activity during pregnancy.The best-fitted model for predicting cyanotic and acyanotic congenital heart disease is the artificial neural network.The results obtained and the best model identified will be useful for medical practitioners and public health scientists for an informed decision-making process about the earlier diagnosis and improve the health condition of children in Pakistan.

Epidermal growth factor receptor rs17337023 polymorphism in hypertensive gestational diabetic women: A pilot study

BACKGROUND Women with gestational diabetes mellitus have an increased risk of developing gestational hypertension,which can increase fetal and neonatal morbidity and mortality.In the past decade,single nucleotide polymorphisms in several genes have been identified as risk factors for development of gestational hypertension.The epidermal growth factor receptor activates tyrosine kinase mediated blood vessels contractility;and inflammatory cascades.Abnormalities in these mechanism are known to contribute towards hypertension.It is thus plausible that polymorphisms in the epidermal growth factor receptor gene would be associated with the development of hypertension in women with gestational diabetes.AIM To determine whether the epidermal growth factor receptor rs17337023 SNP is associated with the occurrence of hypertension in gestational diabetic women.METHODS This pilot case-control study was conducted at two tertiary care hospitals in Karachi,from January 2017-August 2018.Two hundred and two women at 28 week of gestation with gestational diabetes were recruited and classified into normotensive(n=80)and hypertensive(n=122)groups.Their blood samples were genotyped for epidermal growth factor receptor polymorphism rs17337023 using tetra-ARMS polymerase chain reaction.Descriptive analysis was applied on baseline data.Polymorphism data was analyzed for genotype and allele frequency determination using chi-squared statistics.In all cases,a P value of<0.05 was considered significant.RESULTS Subjects were age-matched and thus no difference was observed in relation to age of the study subjects(P>0.05).Body fat percentage was significantly higher in hypertensive females as compared to normotensive subjects(35.138±4.29 Case vs 25.01±8.28 Control;P<0.05).Similarly,systolic and diastolic blood pressures among groups were significantly higher in hypertensive group than the normotensive group(P<0.05).Overall epidermal growth factor receptor rs17337023 polymorphism genotype frequency was similar in both groups,with the heterozygous AT genotype(56 in Case vs 48 in Control;P=0.079)showing predominance in both groups.Furthermore,the odds ratio for A allele was 1.282(P=0.219)and for T allele was 0.780(P=0.221)in this study.CONCLUSION This pilot study indicates that polymorphisms in rs17337023 may not be involved in the pathophysiology of gestational hypertension in gestational diabetes via inflammatory cascade mechanism.Further large-scale studies should explore polymorphism in epidermal growth factor receptor and other genes in this regard.