Prediction Models of the Sele-Harm for Psychiatric Patients using Data Mining Techniques
Article Sidebar
Main Article Content
Abstract
The objective of this research is to create and compare the effectiveness of a self-harm model for psychiatric patients. The data were collected from Khon Kaen Rajanagarindra Psychiatric Hospital database, Khon Kaen province from January 2019 to December 2021. The records were 4,179 records in total. Gain Ratio and Relief methods were used to select relevant factors for building the prediction models. Naive Bay, Decision tree, Machine support, Deep learning, Partial rule techniques were utilized to build self-harm in psychiatric patients prediction models. In this experiment, 10-fold cross validation was used to divide the data into learning and testing datasets. Accuracy, sensitivity, and specificity were employed to compare the effectiveness of the models. The experimental results showed that selection of factors using the Gain Ratio method when used C4.5 decision tree or machine support vector machine techniques has the same highest accuracy at 84.66 %.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
Boonma, R. and Chirawichitchai, N. (2019). Classification of Diabetes Patient by Using Data Mining Techniques and Correlation Based Feature Selection. PKRU SciTech Journal, 3(2), 11-19. https://ph01.tci-thaijo.org/index.php/pkruscitech/article/view/201722/164122
Boonprasom, C. and Sarach, C. (2019). The Exploratory Factor Analysis of Undergraduate Students’ Dropout at Ubon Ratchathani Rajabhat University. Technical Education Journal: King Mongkut’s University of Technology North Bangkok, 10(1), 86-97. https://ojs.kmutnb.ac.th/index.php/jote/article/view/2909/2239
Chinprasatsak, K., Insuk, P., Foosarmpok, N. and Sonpanow, N. (2023). The Essence of DEEP LEARNING: AI, illustrated. Made By AI Company Limited.
Digital Government Development Agency. (2022). AI Artificial Intelligence Technology for Government Administration and Services. Sor. Phichit Printing Company Limited. (in Thai)
Eibe, F. and Ian, W. (1998). Generating Accurate Rule Sets Without Global Optimization. Research Gate.
Harnmongkolpipat, P. (2017). Principles of Statistics 1 (7thed). Bangkok: Kasetsart University Press.
Hongboonmee, N. and Thammakorn, T. (2019). Screening System for Depression on Smartphone using Data Mining Techniques. Srinakharinwirot University Journal of Sciences and Technology, 11(21), 100-113. https://ejournals.swu.ac.th/index.php/SWUJournal/article/view/11425/9654
Kenji, K. and Larry, A.R. (1992). The Feature Selection Problum: Traditional Methods and a New Algorithm. https://cdn.aaai.org/AAAI/1992/AAAI92-020.pdf
Khonkaen Rajanagarindra Psychiatric Hopital, National Center for Suicide. (2022). E-Reports. https://suicide.dmh.go.th/report/
Molee, A., Saokaew, N. and Hemmanee, B. (2019). A Study of Disease Risk of Elderly with Data Mining Technique. Narkbhutparitat Journal Nakhon Si Thammarat Rajabhat University, 11(3), 29-34. (in Thai)
Rungrattanaubol, J. (2022). Data Mining Techniques. Naresuan University Publishing House.
Sanguansat, P. (2019). Artificial Intelligence with Machine Learning, AI with Machine Learning. Infopress
Senthil Kumar, A.V. (2016). Web Usage Mining Techniques and Applications Across Industries. IGI Global, United States of America.
World Health Organization. (2019). Suicide Worldwide in 2019: Global Health Estimates. WHO.
World Health Organization. (2021). One in 100 Deaths is by Suicide. WHO. https://www.who.int/news/item/17-06-2021-one-in-100-deaths-is-by-suicide
Xiaowei, H., Gaojie, J. and Wenjie, R. (2023). Machine Learning Safety. Singapore.