Predicting congenital heart defects: A comparison of three data mining methods

• Published in: PloS one 2017-05, Vol.12 (5), p.e0177811-e0177811
• Main Authors: Luo, Yanhong, Li, Zhi, Guo, Husheng, Cao, Hongyan, Song, Chunying, Guo, Xingping, Zhang, Yanbo
• Format: Article
• Language: English
• Subjects: Adult; Algorithms; Biology and Life Sciences; Birth; Birth defects; Brain research; Cancer; Childbirth & labor; Children; China - epidemiology; Classification; Computer and Information Sciences; Congenital defects; Congenital heart defects; Cross-Sectional Studies; Data mining; Data Mining - methods; Data processing; Datasets; Diagnosis; Engineering and Technology; Entropy; Environmental risk; Family planning; Female; Folic acid; Fourier transforms; Health risk assessment; Health risks; Heart; Heart Defects, Congenital - epidemiology; Heart Defects, Congenital - etiology; Humans; Illnesses; Infant, Newborn; Learning algorithms; Machine learning; Medicine and Health Sciences; People and Places; Physical Sciences; Population; Pregnancy; Public health; Research and Analysis Methods; Retrospective Studies; Risk Factors; Sampling techniques; Studies; Support Vector Machine; Support vector machines; Womens health
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0177811

Congenital heart defects (CHD) is one of the most common birth defects in China. Many studies have examined risk factors for CHD, but their predictive abilities have not been evaluated. In particular, few studies have attempted to predict risks of CHD from, necessarily unbalanced, population-based cross-sectional data. Therefore, we developed and validated machine learning models for predicting, before and during pregnancy, women's risks of bearing children with CHD. We compared the results of these models in a large-scale, comprehensive population-based retrospective cross-sectional epidemiological survey of birth defects in six counties in Shanxi Province, China, covering 2006 to 2008. This contained 78 cases of CHD among 33831 live births. We constructed nine synthetic variables to use in the models: maternal age, annual per capita income, family history, maternal history of illness, nutrition and folic acid deficiency, maternal illness in pregnancy, medication use in pregnancy, environmental risk factors in pregnancy, and unhealthy maternal lifestyle in pregnancy. The machine learning algorithms Weighted Support Vector Machine (WSVM) and Weighted Random Forest (WRF) were trained on, and a logistic regression (Logit) was fitted to, two-thirds of the data. Their predictive abilities were then tested in the remaining data. True positive rate (TPR), true negative rate (TNR), accuracy (ACC), area under the curves (AUC), G-means, and Weighted accuracy (WTacc) were used to compare the classification performance of the models. Median values, from repeating the data partitioning 1000 times, were used in all comparisons. The TPR and TNR of the three classifiers were above 0.65 and 0.93, respectively, better than any reported in the literature. TPR, wtACC, AUC and G were highest for WSVM, showing that it performed best. All three models are precise enough to identify groups at high risk of CHD. They should all be considered for future investigations of other birth defects and diseases.