Stroke Patients Classification Using Resampling Techniques and Decision Tree Learning
How to Cite?
Sumitra Nuanmeesri, Wongkot Sriurai, Nattanon Lamsamut, "Stroke Patients Classification Using Resampling Techniques and Decision Tree Learning," International Journal of Engineering Trends and Technology, vol. 69, no. 6, pp. 115-120, 2021. Crossref, https://doi.org/10.14445/22315381/IJETT-V69I6P217
Stroke is a major global and worldwide public health problem. It is a major cause of mortality, morbidity, and disability in developed and increasingly in less developed countries. The goal of this study is to develop a classification model for stroke patients towards the application of resampling techniques together with the decision tree learning methods. Since the size of the collected dataset to construct the model was small, the research team applied the resampling techniques to solve the problem. When the datasets of predicted outputs were imbalanced, the data size needs balance adjustment between 100%-300%. Afterward, decision tree learning was applied to the construction of the classification model for stroke patients by which the results from three decision tree learning methods, including ID3, C4.5, and Random Forest, were compared. The model’s effectiveness was evaluated by 10-fold cross-validation. The evaluation results showed that the model tested with 10-fold cross-validation and adjusted by resampling to 200% with the Random Forest technique provided the highest level of effectiveness, with the classification accuracy of 96.40%, precision of 96.45%, and recall of 96.60%. This model gave higher efficiency than the results gained from both ID3 and C4.5 techniques.
Cerebrovascular Disease, Decision Tree, Patient Classification, Resampling, Stoke
 Bureau of Non-Communicable Diseases, World stroke day campaign keystones, Department of Disease Control, (2017) 1–4.
 S. Uhmn, D. Kim, S. W. Cho, J. K. Cheong, and J. Kim, Chronic hepatitis classification using SNP data and data mining techniques, in Proc. Frontiers in the Convergence of Bioscience and Information Technologies, Jeju, South Korea, (2007) 81–86.
 G. Choudhary and S. N. Singh, Prediction of cardiovascular disease using data mining technique, in Proc. 4th International Conf. Information Systems and Computer Networks, 2019, pp. 99–103.
 N. Hongboonmee, P. Sornroong, Applying decision tree classification techniques for diagnose the disease in cow on mobile phone, Journal of Science and Technology, Ubon Ratchathani University, 20 (1) (2018) 44–58.
 S. K. Mohapatra, Mohanty, Analysis of resampling method for arrhythmia classification using random forest classifier with selected features, in Proc. 2nd International Conf. Data Science and Business Analytics, Changsha, China, (2018) 495–499.
 N. S. Kumar, M. Thangamani, V. Sasikumar, and S. Nallusamy, An improved machine learning approach for predicting ischemic stroke, International Journal of Engineering Trends and Technology, 69(11) (2021) 111–115.
 P. Pisuttakoon. Stroke [Online]. Available: http://www.med.nu.ac.th/dpMed/fileKnowledge/106_2017-08-19.pdf. (2018).
 J. Han, and M. Kamber, Data Mining Concepts and Techniques, U.K.: Morgan Kaufmann Publishers, (2011).
 P. N. Tan, M. Steinbach, A. Karpatne, and V. Kumar, Introduction to Data Mining, 1st ed., NJ: Pearson, (2014).
 Aman and R. S. Chhillar, Disease predictive models for healthcare by using data mining techniques: State of the art, International Journal of Engineering Trends and Technology, 68 (10) (2020) 52–57.
 C. Kaewchinporn, Data classification with decision tree and clustering techniques, Thesis in Computer Science, King Mongkut’s Institute of Technology Ladkrabang, Thailand, (2010).
 L. Breiman, Random forests, Machine Learning, 45 (2001) 5–32.
 S. Nuanmeesri, Development of community tourism enhancement in emerging cities using gamification and adaptive tourism recommendation, Journal of King Saud University - Computer and Information Sciences, (in press), (2021).
 S. Nuanmeesri and W. Sriurai, Thai water buffalo disease analysis with the application of feature selection technique and Multi-Layer Perceptron Neural Network, Engineering, Technology & Applied Science Research, 11 (2021) 6907–6911.