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.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Center for Biomedical Resources of NHRI. (2020). Taiwan National Health Insurance Research Database. https://nhird.nhri.org.tw/en/. Accessed 22 Feb 2020.
Cheng, ATA. (1995). Mental illness and suicide: a case-control study in east Taiwan. Archives of General Psychiatry, 52(7), 594–603.
Cohn, JF, Kruez, TS, Matthews, I, Yang, Y, Nguyen, MH, Padilla, MT, Zhou, F, & De la Torre, F. (2009). Detecting depression from facial actions and vocal prosody. In International conference on affective computing and intelligent interaction and workshops (pp. 1–7).
Chen, Y-Y, Wu, KC-C, Yousuf, S, & Yip, PSF. (2011). Suicide in asia: opportunities and challenges. Epidemiologic Reviews, 34(1), 129–144.
Domchek, SM, Eisen, A, Calzone, K, Stopfer, J, Blackwood, A, & Weber, BL. (2003). Application of breast cancer risk prediction models in clinical practice. Journal of Clinical Oncology, 21(4), 593–601.
Hegerl, U. (2016). Prevention of suicidal behavior. Dialogues in Clinical Neuroscience, 18(2), 183–90.
Huang, Y, Chiang, C-F, & Chen, ALP. (2019). Predicting depression tendency based on image, text and behavior data from instagram. In The 8th international conference on data science, technology and applications. https://doi.org/10.5220/0007833600320040.
Huang, SH, LePendu, P, Iyer, SV, Tai-Seale, M, Carrell, D, & Shah, NH. (2014). Toward personalizing treatment for depression: predicting diagnosis and severity. Journal of the American Medical Informatics Association: JAMIA, 21(6), 1069–1075.
Tekell, JL, Hoffmann, R, Hendrickse, W, Greene, RW, Rush, AJ, & Armitage, R. (2005). High frequency EEG activity during sleep: characteristics in schizophrenia and depression. Clinical EEG and Neuroscience, 36(1), 25–35.
Vijayakumar, L. (2005). Suicide and mental disorders in Asia. International Review of Psychiatry, 17(2), 109–114.
Lu, C-Y, Huang, H-C, Chang, H-H, Yang, T-H, Chang, C-J, Chang, S-W, & Chen, P-C. (2017). Acupuncture therapy and incidence of depression after stroke. Stroke, 48(6), 1682–1684.
Low, L, Maddage, N, Lech, M, Sheeber, L, & Allen, N. (2010). Influence of acoustic low-level descriptors in the detection of clinical depression in adolescents. In IEEE international conference on acoustics, speech and signal processing (pp. 5154–5157).
Lee, T-Y, Wang, C-B, Chen, T-T, Kuo, KN, Wu, M-S, Lin, J-T, & Wu, C-Y. (2015). A tool to predict risk for gastric cancer in patients with peptic ulcer disease on the basis of a nationwide cohort. Clinical Gastroenterology and Hepatology, 13(2), 287–293.
Ministry of Health and Welfare. (2020). 2018 Cause of Death Statistics. https://www.mohw.gov.tw/lp-4650-2.html. Accessed 22 Feb 2020.
Norton, J, de Roquefeuil, G, David, M, Boulenger, J-P, Ritchie, K, & Mann, A. (2011). The mental health of doctor-shoppers: experience from a patient-led fee-for-service primary care setting. Journal of Affective Disorders, 131 (1–3), 428–432.
Radloff, LS. (1977). The CES-d scale. Applied Psychological Measurement, 1(3), 385–401.
Scheurwegs, E, Cule, B, Luyckx, K, Luyten, L, & Daelemans, W. (2017). Selecting relevant features from the electronic health record for clinical code prediction. Journal of Biomedical Informatics, 74, 92–103.
Spitzer, RL, Kroenke, K, Williams, JBW, & Löwe, B. (2006). A brief measure for assessing generalized anxiety disorder. Archives of Internal Medicine, 166(10), 1092–1097.
Sansone, RA, & Sansone, LA. (2012). Doctor shopping. Innovations in Clinical Neuroscience, 9(11-12), 42–46.
Siontis, GCM, Tzoulaki, I, Siontis, KC, & Ioannidis, JPA. (2012). Comparisons of established risk prediction models for cardiovascular disease: systematic review. BMJ, 344, e3318.
Suhara, Y, Xu, Y, & Pentland, A. (2017). Deepmood: forecasting depressed mood based on self-reported histories via recurrent neural networks. In International world wide web conferences (pp. 715–724).
Shen, T-C, Yang, C-Y, Huang, Y-J, Lin, C-L, & Sung, F-C. (2017). Risk of depression in patients with uterine leiomyoma: a nationwide population-based cohort study. Journal of Affective Disorders, 213, 126–130.
Tsai, T-Y, Lu, M-C, Livneh, H, Chiu, S-Y, Lai, N-S, & Guo, H-R. (2017). Does depression increase the risk of stroke in patients with rheumatoid arthritis? a population-based cohort study. BMJ Open, 7(4), e014233.
World Health Organization. (2020). Depression. https://www.who.int/news-room/fact-sheets/detail/depression. Accessed 22 Feb 2020.
World Health Organization. (2020). Adolescent health in the South-East Asia Region. https://www.who.int/news-room/fact-sheets/detail/depression. Accessed 22 Feb 2020.
The University of Waikato. (2020). Weka 3: machine learning software in java. https://www.cs.waikato.ac.nz/ml/weka/. Accessed 22 Feb 2020.
Wu, PH, Koh, J-L, & Chen, ALP. (2019). Event detection for exploring emotional upheavals of depressive people. The 34th ACM/SIGAPP Symposium on Applied Computing, 2086–2095.
Wu, J, Liu, C, Lee, S, Kuo, Y, & Hsieh, T. (2018). Assessment of the charlson comorbidity index score, CHADS2 and CHA2DS2-VASc scores in predicting death in patients with thoracic empyema. Heart & Lung, 47(2), 157–161.
Wu, MY, Shen, C-Y, En, TW, & Chen, ALP. (2018). A deep architecture for depression detection using posting, behavior, and living environment data. Journal of Intelligent Information Systems, 1–20.
Xiong, H, Zhang, J, Yu, H, Leach, K, & Barnes, LE. (2017). Daehr: a discriminant analysis framework for electronic health record data and an application to early detection of mental health disorders. ACM Transactions on Intelligent Systems and Technology, 8(3), 1–21.
Yang, H, Chen, Y-H, Hsieh, T-F, Chuang, S-Y, & Wu, M-J. (2016). Prediction of mortality in incident hemodialysis patients: a validation and comparison of CHADS2, CHA2DS2, and CCI scores. PLoS One, 11(5), e0154627.
Zhang, J, Xiong, H, Yu, H, Wu, H, Leach, K, & Barnes, LE. (2015). M-SEQ: early detection of anxiety and depression via temporal orders of diagnoses in electronic health data. In IEEE international conference on big data (pp. 2569–2577).
Acknowledgements
This work was partially supported by a joint project numbered 106-ASIA-UMY-06 between Asia University and Muhammadiyah University of Yogyakarta.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interests
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Tai, L.K., Setyonugroho, W. & Chen, A.L.P. Finding discriminatory features from electronic health records for depression prediction. J Intell Inf Syst 55, 371–396 (2020). https://doi.org/10.1007/s10844-020-00611-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10844-020-00611-y