Travma Sonrası Stres Bozukluğunun Derin Öğrenme Yöntemleri ile Tespiti

Year 2022, , 1274 - 1281, 31.12.2022

Engin Seven , Cansın Turguner , Muhammed Ali Aydın

https://doi.org/10.31202/ecjse.1133463

Abstract

Travma sonrası stres bozukluğu (TSSB), kişinin yaşadığı travmatik bir olay sonrasında ruhsal ve fiziksel hayatını olumsuz yönde etkileyen psikiyatrik bir sorundur. Hastalığın erken aşamada fark edilip tedavi edilmemesi bipolar bozukluk, anksiyete veya intihar eğilimi gibi olumsuz sonuçlar ortaya çıkarabilmektedir. TSSB nin erken aşamada tespiti için yapay zeka temelli bir model geliştirilmiştir. Yapılan çalışmada K-En Yakın Komşu algoritması, Destek Vektör Makineleri, Karar Ağaçları, Gaus Naive Bayes ve Yapay Sinir Ağları kullanılmış Covid-19 pandemisi devam ederken tıp öğrencilerinden toplanan veri seti üzerinde testler gerçekleştirilmiştir. Yapılan çalışmada doğruluk, kesinlik, hassasiyet ve f1 skoru değerleri karşılaştırmalı incelenmiştir. Yapay sinir ağları 0,987 doğruluk oranı ile en iyi sonucu elde etmiştir. Ayrıca 0,966 f1 skoru ile yapay sinir ağları en iyi TSSB tahmininde bulunmuştur.

Keywords

Travma sonrası stres bozukluğu, Derin Öğrenme, Akıllı teşhis, Özellik Seçimi

Detection of Post Traumatic Stress Disorder with Deep Learning Methods

Abstract

Post-traumatic stress disorder (PTSD) is a psychiatric problem that negatively affects a person's mental and physical life after a traumatic event. If the disease is not recognized and treated at an early stage, negative consequences such as bipolar disorder, anxiety or suicidality can occur. An artificial intelligence-based model has been developed for the early detection of PTSD. In the study, K-Nearest Neighbor algorithm, Support Vector Machines, Decision Trees, Gaus Naive Bayes and Artificial Neural Networks were used and tests were carried out on the dataset collected from medical students during the Covid-19 pandemic. In the study; accuracy, precision, recall and f1 score values were examined comparatively. Artificial neural networks achieved the best result with an accuracy rate of 0,987. In addition, artificial neural networks found the best PTSD prediction with an f1 score of 0,966.

Keywords

Post-traumatic stress disorder, Deep learning, Intelligent diagnosis, Feature Selection

References

• [1]. A. P. Association et al., Diagnostic and statistical manual of mental disorders (DSM-5®, American Psychiatric Pub, 2013.
• [2]. A. A. M. Thabet, Y. Abed and P. Vostanis, "Comorbidity of PTSD and depression among refugee children during war conflict", Journal of Child Psychology and Psychiatry, vol. 45, no. 3, pp. 533-542, 2004.
• [3]. K. A. McLaughlin, K. C. Koenen, E. D. Hill, M. Petukhova, N. A. Sampson, A. M. Zaslavsky, et al., "Trauma exposure and posttraumatic stress disorder in a national sample of adolescents", Journal of the American Academy of Child & Adolescent Psychiatry, vol. 52, no. 8, pp. 815-830, 2013.
• [4]. C. Jones, R. D. Griffiths, G. Humphris and P. M. Skirrow, "Memory delusions and the development of acute posttraumatic stress disorder-related symptoms after intensive care", Critical Care Medicine, vol. 29, no. 3, pp. 573-580, 2001.
• [5]. Y. Li, P. Liu, Q. Cai, J. Guo, Z. Zhou, H. Yan, et al., "Posttraumatic stress disorder and mobile health: App investigation and scoping literature review", JMIR mHealth and uHealth, vol. 5, no. 10, pp. e156, 2017.
• [6]. F. W. Weathers, M. J. Bovin, D. J. Lee, D. M. Sloan, P. P. Schnurr, D. G. Kaloupek, et al., The clinician-administered ptsd scale for dsm–5 (caps-5): Development and initial psychometric evaluation in military veterans, 2017.
• [7]. Hahn, T., Nierenberg, A. A., & Whitfield-Gabrieli, S. (2017). Predictive analytics in mental health: applications, guidelines, challenges and perspectives. Molecular psychiatry, 22(1), 37-43.
• [8]. Marinić, I., Supek, F., Kovačić, Z., Rukavina, L., Jendričko, T., & Kozarić-Kovačić, D. (2007). Posttraumatic stress disorder: diagnostic data analysis by data mining methodology. Croatian medical journal, 48(2.), 185-197.
• [9]. Kessler, R. C., Rose, S., Koenen, K. C., Karam, E. G., Stang, P. E., Stein, D. J., ... & Carmen Viana, M. (2014). How well can post‐traumatic stress disorder be predicted from pre‐trauma risk factors? An exploratory study in the WHO World Mental Health Surveys. World Psychiatry, 13(3), 265-274.
• [10]. Köbach, A., Nandi, C., Crombach, A., Bambonyé, M., Westner, B., & Elbert, T. (2015). Violent offending promotes appetitive aggression rather than Posttraumatic stress—A replication study with Burundian ex-combatants. Frontiers in psychology, 6, 1755.
• [11]. Karstoft, K. I., Statnikov, A., Andersen, S. B., Madsen, T., & Galatzer-Levy, I. R. (2015). Early identification of posttraumatic stress following military deployment: Application of machine learning methods to a prospective study of Danish soldiers. Journal of affective disorders, 184, 170-175.
• [12]. Reece, A. G., Reagan, A. J., Lix, K. L., Dodds, P. S., Danforth, C. M., & Langer, E. J. (2017). Forecasting the onset and course of mental illness with Twitter data. Scientific reports, 7(1), 1-11.
• [13]. He, Q., Veldkamp, B. P., Glas, C. A., & de Vries, T. (2017). Automated assessment of patients’ self-narratives for posttraumatic stress disorder screening using natural language processing and text mining. Assessment, 24(2), 157-172.
• [14]. Gradus, J. L., King, M. W., Galatzer‐Levy, I., & Street, A. E. (2017). Gender differences in machine learning models of trauma and suicidal ideation in veterans of the Iraq and Afghanistan Wars. Journal of traumatic stress, 30(4), 362-371.
• [15]. Augsburger, M., & Elbert, T. (2017). When do traumatic experiences alter risk-taking behavior A machine learning analysis of reports from refugees. PLoS one, 12(5), e0177617.
• [16]. Leightley, D., Williamson, V., Darby, J., & Fear, N. T. (2019). Identifying probable post-traumatic stress disorder: applying supervised machine learning to data from a UK military cohort. Journal of Mental Health, 28(1), 34-41.
• [17]. Spitzer RL, Kroenke K, Williams JB, Löwe B. A brief measure for assessing generalized anxiety disorder: the GAD-7. Arch Intern Med. 2006 May 22;166(10):1092–7. pmid:16717171
• [18]. Prins A, Bovin MJ, Smolenski DJ, Marx BP, Kimerling R, Jenkins-Guarnieri MA, et al. The Primary Care PTSD Screen for DSM-5 (PC-PTSD-5): Development and evaluation within a veteran primary care sample. J Gen Intern Med. 2016;31(10):1206–1211. pmid:27170304
• [19]. Lee, C. M., Juarez, M., Rae, G., Jones, L., Rodriguez, R. M., Davis, J. A., ... & Harries, A. J. (2021). Anxiety, PTSD, and stressors in medical students during the initial peak of the COVID-19 pandemic. PloS one, 16(7), e0255013.
• [20]. Cover, T., & Hart, P. (1967). Nearest neighbor pattern classification. IEEE transactions on information theory, 13(1), 21-27.
• [21]. Boser, B. E., Guyon, I. M., & Vapnik, V. N. (1992, July). A training algorithm for optimal margin classifiers. In Proceedings of the fifth annual workshop on Computational learning theory (pp. 144-152).
• [22]. Badulescu, L. A. (2007). Attribute selection measure in decision tree growing.
• [23]. John, G. H., & Langley, P. (2013). Estimating continuous distributions in Bayesian classifiers. arXiv preprint arXiv:1302.4964.