Finding discriminatory features from electronic health records for depression prediction
- PDF / 2,616,072 Bytes
- 26 Pages / 439.642 x 666.49 pts Page_size
- 14 Downloads / 208 Views
Finding discriminatory features from electronic health records for depression prediction Liang Kuang Tai1 · Winny Setyonugroho2 · Arbee L. P. Chen3 Received: 26 February 2020 / Revised: 2 June 2020 / Accepted: 13 July 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Depression, a common mental disorder, affects not only individuals but also families and society. In the beginning stage, most of the depressive people do not know they are suffering from depression. Some of them visit different medical departments to ask for help. However, their symptoms may not be relieved because of not having a proper diagnosis. In this paper, we find discriminatory features for establishing an early depression detection model by analyzing medical data. These features are composed of patients’ medical information, including diagnosed diseases and medical departments. We use real-world electronic health records dataset from the Taiwan National Health Insurance Research Database for the analysis and focus on young people aged 10-24 years. The experiment results show that our model can detect future diagnosis of depression based on patients’ records up to 90 days in advance. Furthermore, even better performance can be achieved with longer observation time. Keywords Depression · Prediction model · Discriminatory features · Medical data analysis
1 Introduction Depression is a common mental disorder, which affects more than 300 million people in the world (World Health Organization 2020a). It is the result of an interplay of social, psychological, and biological factors. People who experience adverse life events, such as unemployment, bereavement, and psychological trauma, are more likely to suffer from Arbee L. P. Chen
[email protected] Liang Kuang Tai [email protected] Winny Setyonugroho [email protected] 1
Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan
2
Master of Hospital Management, University of Muhammadiyah Yogyakarta, Yogyakarta, Indonesia
3
Department of Computer Science and Information Engineering, Asia University, Taichung, Taiwan
Journal of Intelligent Information Systems
depression. At its worst situation, depression can lead to committing suicide (World Health Organization 2020a). Close to 800,000 people die due to suicide in the world every year, and sixty-one percent of them come from Asia (Vijayakumar 2005). In the vast majority of cases, suicidal behavior occurs in the context of psychiatric disorders, in which depression is the most important one (Hegerl 2016). According to the psychological autopsy research works (Cheng 1995; Chen et al. 2011), the rate of depression in suicide victims in Taiwan is 87%. The statistical analysis of the causes of death in 2018 in Taiwan shows that the number of suicides increases by 2.58% compared with 2016 (Ministry of Health and Welfare 2020). In addition, suicide is the second leading cause of death in 15-29-year-olds (World Health Organization 2020a). It really matters for these young people to rec
Data Loading...
