scholarly journals Using Innovative Machine Learning Methods to Screen and Identify Predictors of Congenital Heart Diseases

2022 ◽  
Vol 8 ◽  
Author(s):  
Yanji Qu ◽  
Xinlei Deng ◽  
Shao Lin ◽  
Fengzhen Han ◽  
Howard H. Chang ◽  
...  

Objective: Congenital heart diseases (CHDs) are associated with an extremely heavy global disease burden as the most common category of birth defects. Genetic and environmental factors have been identified as risk factors of CHDs previously. However, high volume clinical indicators have never been considered when predicting CHDs. This study aimed to predict the occurrence of CHDs by considering thousands of variables from self-reported questionnaires and routinely collected clinical laboratory data using machine learning algorithms.Methods: We conducted a birth cohort study at one of the largest cardiac centers in China from 2011 to 2017. All fetuses were screened for CHDs using ultrasound and cases were confirmed by at least two pediatric cardiologists using echocardiogram. A total of 1,127 potential predictors were included to predict CHDs. We used the Explainable Boosting Machine (EBM) for prediction and evaluated the model performance using area under the Receive Operating Characteristics (ROC) curves (AUC). The top predictors were selected according to their contributions and predictive values. Thresholds were calculated for the most significant predictors.Results: Overall, 5,390 mother-child pairs were recruited. Our prediction model achieved an AUC of 76% (69-83%) from out-of-sample predictions. Among the top 35 predictors of CHDs we identified, 34 were from clinical laboratory tests and only one was from the questionnaire (abortion history). Total accuracy, sensitivity, and specificity were 0.65, 0.74, and 0.65, respectively. Maternal serum uric acid (UA), glucose, and coagulation levels were the most consistent and significant predictors of CHDs. According to the thresholds of the predictors identified in our study, which did not reach the current clinical diagnosis criteria, elevated UA (>4.38 mg/dl), shortened activated partial thromboplastin time (<33.33 s), and elevated glucose levels were the most important predictors and were associated with ranges of 1.17-1.54 relative risks of CHDs. We have developed an online predictive tool for CHDs based on our findings that may help screening and prevention of CHDs.Conclusions: Maternal UA, glucose, and coagulation levels were the most consistent and significant predictors of CHDs. Thresholds below the current clinical definition of “abnormal” for these predictors could be used to help develop CHD screening and prevention strategies.

2020 ◽  
Vol 75 (11) ◽  
pp. 648
Author(s):  
Tuyen Kim Le ◽  
Vien Truong ◽  
Thanh-Hoang Nguyen-Vo ◽  
Binh P. Nguyen ◽  
Tam N.M. Ngo ◽  
...  

Pediatric cardiomyopathy is considered as one of the heart diseases, which causes by abnormal disorder of the heart muscle. If pediatric cardiomyopathy remains untreated and unidentified at the early stages, it leads to heart failure. The global number of deaths and disability attributed to cardiomyopathy has steadily increased. Hence, machine learning approaches can solves the problem of identifying the critical problem by determining the pediatric cardiomyopathy disease associated genes from the collection of differentially expressed genes that are recognized by biological process of genes. The main objective of this study is to design a machine learning model which can predict the likelihood of pediatric cardiomyopathy in genes specified biological features with maximum of accuracy. Identified high throughput machine learning algorithms like Logistic Regression, Naive Bayes, Random Forest, and Support Vector Machine were used in this experiment to determine the genes which can be derived from internal database repository having biological process of genes specified. Experiments are conducted on Gene Expression Omnibus (GEO) datasets which sourced from cardiogenomics.org and Biohunter tool. The performance of these machine learning algorithms is evaluated on various measures like Accuracy, Precision, Recall, F-Measure, and Receiver Operating Characteristics (ROC). From the obtained results shows that Random Forest provides high accuracy 84.4% when compared to other four machine learning algorithms.


Author(s):  
M.V. Medvedev, M.V. Kubrina

Main prenatal ultrasound differential patterns of congenital heart diseases including interventricular septal defect and dextroposed aorta are presented.


Sign in / Sign up

Export Citation Format

Share Document