Comparison of Bayesian Networks for Diabetes Prediction
A Bayesian network (BN) can be used to predict the prevalence of diabetes from the cause–effect relationship among risk factors. By applying a BN model, we can capture the interdependencies between direct and indirect risks hierarchically. In this study, we propose to investigate and compare the predictive performances of BN models with non-hierarchical (BNNH), and non-hierarchical and reduced variables (BNNHR) structures, hierarchical structure by expert judgment (BNHE), and hierarchical learning structure (BNHL) with type-2 diabetes. ROC curves, AUC, percentage error, and F1 score were applied to compare performances of those classification techniques. The results of the model comparison from both datasets (training and testing) obtained from the Thai National Health Examination Survey IV ensured that BNHE can predict the prevalence of diabetes most effectively with the highest AUC values of 0.7670 and 0.7760 from the training and the testing dataset, respectively.
KeywordsBayesian network Diabetes Machine learning
This research is supported by King Mongkut’s Institute of Technology Ladkrabang [No. 2559-02-05-050]. We would like to thank the Thai Public Health Survey Institute for Health Systems Research for providing helpful datasets.
- 4.Leerojanaprapa, K., van der Meer, R., Walls, L.: Modeling supply risk using belief networks: a process with application to the distribution of medicine. In: 2013 IEEE International Conference on Industrial Engineering and Engineering Management, pp. 201–205 (2013)Google Scholar
- 5.Xiao-xuan, H., Hui, W., Shuo, W.: Using expert’s knowledge to build bayesian networks. In: 2007 International Conference on Computational Intelligence and Security Workshops (CISW 2007), pp. 220–223 (2007)Google Scholar
- 6.Atoui, H., Fayn, J., Gueyffier, F., Rubel, P.: Cardiovascular risk stratification in decision support systems: a probabilistic approach. Application to pHealth (2006)Google Scholar
- 10.Leerojanaprapa, K., Atthirawong, W., Aekplakorn, W., Sirikasemsuk, K.: Applying Bayesian network for noncommunicable diseases risk analysis: implementing national health examination survey in Thailand. In: IEEE International Conference on Industrial Engineering and Engineering Management, vol. 2017–December (2018)Google Scholar
- 11.Aekplakorn, W., Satheannoppakao, W., Putwatana, P., Taneepanichskul, S., Kessomboon, P., Chongsuvivatwong, V., Chariyalertsak, S.: Dietary pattern and metabolic syndrome in thai adults. J. Nutr. Metab. 2015, 468759 (2015)Google Scholar
- 13.Kudikyala, U.K., Bugudapu, M., Jakkula, M.: Graphical Structure of Bayesian Networks by Eliciting Mental Models of Experts, pp. 333–341. Springer, Singapore (2018)Google Scholar
- 15.Bouckaert, R.R.: Bayesian Network Classification in Weka for Version 3-5-7. University of Waikato (2008)Google Scholar