Research Article
BibTex RIS Cite

Travma Sonrası Stres Bozukluğu Yönetimi: Makine Öğrenmesi Yaklaşımı

Year 2020, Ejosat Special Issue 2020 (HORA), 284 - 288, 15.08.2020
https://doi.org/10.31590/ejosat.779973

Abstract

Travma sonrası stres bozukluğu (TSSB), doğal afet, salgın, ciddi bir kaza, terör eylemi, kavga/savaş, tecavüz veya benzeri, yaşamı tehdit eden bir deneyim veya olay yaşayan veya buna tanık olan kişide meydana gelen travmatik bir yaralanma olarak tanımlanır. Makine öğrenmesi (MÖ), TSSB tabanlı klinik ruhsal hastalıkları tespit etme, dijitalleştirme, riskleri önleme, izleme, sınıflandırarak ve kişilere özgü sonuçlar çıkararak psikolojik ve fiziksel sağlık üzerinde son on yıldır çalışmalarını arttırarak devam ettirmektedir. Bu çalışmada, Mississippi-Civilian Versiyon Veri Seti ve DSM-5 (PCL-5) Veri Setini MÖ’nde kullanarak, katılımcıların TSSB skorlarını öngördük. Deneylerimiz için k-en yakın komşu (k-nn), Destek Vektör Makinesi (DVM), karar ağacı (KA), Gauss Naive Bayes (GNB) ve Yapay Sinir Ağları (YSA) yöntemleri kullandık. Tahmin sonuçlarının karşılaştırılmasına göre Mississippi Ölçeği Veri Seti için TSSB tahmini sınıflandırma performans sonuçları göz önüne alındığında, YSA’nın doğruluk, F1 skoru ve anımsatma açısından en iyi tahmin sonuçlarını verdiğini gözlemledik. Hassasiyet alanında ise Gauss Naive Bayes (GNB) en iyi tahmin sonucunu verdi. Öte yandan, tüm bu yöntemleri DSM-5 (PCL-5) ölçekli veri setine uyguladığımızda YSA'nın doğruluk, F1 skoru ve hassasiyet açısından en iyi sonuçları verdiğini gözlemledik. Anımsatma açısından ise, Gaussian Naive Bayes (GNB) en iyi tahmin skorunu verdi. Tüm yöntemleri bu iki farklı veri setinde deneyip sonuçları karşılaştırarak, TSSB olan hastaların tahmin, tanı ve izlenmesinde hangi yöntemin daha verimli olabileceğini gösterdik.

References

  • A. G. Ünlü, Operasyonel Görev Yapan Askeri̇ Personelde Travma Sonrası Stres Bozukluğu (TSSB) Sıklığını Etki̇leyen Faktörler, GATA Tıpta Uzmanlık Tezi, 2014.
  • A. N. Karancı, A. T. Aker S. Işıklı, Yetişkinlerde Travmatik Olay Yaşama Yaygınlığı, Travma Sonrası Stres Bozukluğu ve Travma Sonrası Gelişimin Değerlendirilmesi, Tübitak Projesi (No:107K323), 2009.
  • A.Priyaa, S. Garga, N. Tiggaa, Stress in Modern Life using Machine Learning Algorithms, Procedia Computer Science, vol. 167, pp. 1258-1267, 2020.
  • Borsboom, D., A Network Theory of Mental Disorders, World Psychiatry, vol. 16, pp. 5–13, 2017.
  • C. Heim, C.B. Nemeroff, Neurobiological Pathways Involved in Fear, Stress and PTSD, Neurobiology of PTSD, Oxford University Press, pp. 220-238, 2016.
  • D. Banerjee, K. Islam, K. Xue, G. Mei, L. Xiao, G. Zhang, R. Xu, C. Lei, S. Ji, J. Li, A Deep Transfer Learning Approach for Improved Post-traumatic Stress Disorder Diagnosis, Knowledge and Information Systems, vol. 60, pp. 1693-1724, 2019.
  • F. H. Norris and JJ. L. Perilla, The Revised Civilian Mississippi Scale for PTSD: Reliability, Validity, and Cross-Language Stability, Journal of Traumatic Stress, vol. 9, pp. 285-298, 1996.
  • F. Lamos-Lima, V. Waikamp, T.Antonelli-Salgado, I. Cavalcante Passos, L. Freitas, The Use of Machine Learning Techniques in Trauma-related Disorders: A Systematic Review, Journal of Psychiatric Research, vol. 121, pp. 159-172, 2020.
  • F. W. Weathers, B. T. Litz, T. M. Keane, P. A Palmieri, B. P. Marx, and P. P. Schnurr, The PTSD Checklist for DSM-5 (PCL-5), National Centre for PTSD, 2013.
  • I. R. Galatzer-Levy, K. Karstoft, A. Statnikov, and A. Y. Shalev, Quantitative Forecasting of PTSD from Early Trauma Responses: A Machine Learning Application, Journal of Psychiatry Research, vol. 59, pp. 68–76, 2014.
  • J. L. Gradus, M. W. King, I. Galatzer-Levy, and A. E. Street, Gender Differences in Machine Learning Models of Trauma and Suicidal Ideation in Veterans of the Iraq and Afghanistan Wars, Journal of Trauma Stress, vol. 30, no. 4, pp. 362–371, 2017.
  • J. L. Steel, A. C. Dunlavy, J. Stillman,H. C. Pape, Measuring Depression and PTSD after Trauma: Common Scales and Checklists. Journal of Injury, vol. 42, no.3. pp. 288–300, 2011.
  • R. Levy, K. Karstoft, A. Statnikov, and A. Shalev, Quantitative Forecasting of PTSD from Early Trauma Responses: A Machine Learning Application, Journal of Traumatic Stress, vol. 32, pp. 215-225, 2019.
  • S. İ. Omurca and E. Ekinci, An Alternative Evaluation of Post Traumatic Stress Disorder with Machine Learning Methods, International Symposium on Innovations in Intelligent Systems and Applications, Madrid, Spain, pp. 1-7, 2015.
  • T. Armstrong, S. Federman, K. Hampson, et al., Fear Learning in Veterans with Combat-Related PTSD is Linked to Anxiety Sensitivity: Evidence from Self-Report and Pupillometry, Behavior Therapy, In Press, 2020.
  • T. Roushan et al., Towards Predicting Risky Behavior Among Veterans with PTSD by Analyzing Gesture Patterns, IEEE Annual Computer Software and Applications Conference, Milwaukee, USA, pp. 690-695, 2019.
  • T. Wörtwein and S. Scherer, An Information Gain Analysis of Questions and Reactions in Automated PTSD Screenings, International Conference on Affective Computing and Intelligent Interaction, San Antonio, USA, pp. 15-20, 2017.

Post-Traumatic Stress Disorder (PTSD) Management: A Machine Learning Approach

Year 2020, Ejosat Special Issue 2020 (HORA), 284 - 288, 15.08.2020
https://doi.org/10.31590/ejosat.779973

Abstract

Post-traumatic stress disorder (PTSD) is defined as a traumatic injury developed after facing or witnessing a life-threatening experience or event such as a natural disaster, a pandemic, a serious accident, a terrorist act, war/combat, rape or other violent personal assault. Machine Learning (ML) has been widening its scope on psychological and physical healthcare for a decade by predicting detecting, personalizing, digitalizing, preventing risks, monitoring, and classifying PTSD based clinical mental diseases. In this study, we predict PTSD scores of the participants obtained from Mississippi-Civilian Version Scale and DSM-5 (PCL-5) Scale by applying ML. For our experiments we used the following methods namely k-nearest neighbor (k-nn), support vector machine (SVM), decision tree (DT), Gaussian Naive Bayes (GNB) and artificial neural networks (ANN). According to the comparison of the prediction results Considering PTSD prediction classification performance results for Mississippi (Civilian version) scale data set in comparison to the above mentioned methods, ANN offers the best prediction in terms of accuracy, F1 score and recall. However, Gaussian Naive Bayes (GNB) gives the best prediction score in terms of precision. On the other hand, when we applied all these methods to DSM-5 (PCL-5) scale data set, we have observed that ANN offers the best prediction in terms of accuracies, F1 score and precision. Nevertheless, in terms of recall Gaussian Naive Bayes (GNB) gives the best prediction score. By applying all the methods to these two different data sets and comparing the results, we demonstrate which method can be more efficient in prediction, diagnosis and monitoring the patients with PTSD.

References

  • A. G. Ünlü, Operasyonel Görev Yapan Askeri̇ Personelde Travma Sonrası Stres Bozukluğu (TSSB) Sıklığını Etki̇leyen Faktörler, GATA Tıpta Uzmanlık Tezi, 2014.
  • A. N. Karancı, A. T. Aker S. Işıklı, Yetişkinlerde Travmatik Olay Yaşama Yaygınlığı, Travma Sonrası Stres Bozukluğu ve Travma Sonrası Gelişimin Değerlendirilmesi, Tübitak Projesi (No:107K323), 2009.
  • A.Priyaa, S. Garga, N. Tiggaa, Stress in Modern Life using Machine Learning Algorithms, Procedia Computer Science, vol. 167, pp. 1258-1267, 2020.
  • Borsboom, D., A Network Theory of Mental Disorders, World Psychiatry, vol. 16, pp. 5–13, 2017.
  • C. Heim, C.B. Nemeroff, Neurobiological Pathways Involved in Fear, Stress and PTSD, Neurobiology of PTSD, Oxford University Press, pp. 220-238, 2016.
  • D. Banerjee, K. Islam, K. Xue, G. Mei, L. Xiao, G. Zhang, R. Xu, C. Lei, S. Ji, J. Li, A Deep Transfer Learning Approach for Improved Post-traumatic Stress Disorder Diagnosis, Knowledge and Information Systems, vol. 60, pp. 1693-1724, 2019.
  • F. H. Norris and JJ. L. Perilla, The Revised Civilian Mississippi Scale for PTSD: Reliability, Validity, and Cross-Language Stability, Journal of Traumatic Stress, vol. 9, pp. 285-298, 1996.
  • F. Lamos-Lima, V. Waikamp, T.Antonelli-Salgado, I. Cavalcante Passos, L. Freitas, The Use of Machine Learning Techniques in Trauma-related Disorders: A Systematic Review, Journal of Psychiatric Research, vol. 121, pp. 159-172, 2020.
  • F. W. Weathers, B. T. Litz, T. M. Keane, P. A Palmieri, B. P. Marx, and P. P. Schnurr, The PTSD Checklist for DSM-5 (PCL-5), National Centre for PTSD, 2013.
  • I. R. Galatzer-Levy, K. Karstoft, A. Statnikov, and A. Y. Shalev, Quantitative Forecasting of PTSD from Early Trauma Responses: A Machine Learning Application, Journal of Psychiatry Research, vol. 59, pp. 68–76, 2014.
  • J. L. Gradus, M. W. King, I. Galatzer-Levy, and A. E. Street, Gender Differences in Machine Learning Models of Trauma and Suicidal Ideation in Veterans of the Iraq and Afghanistan Wars, Journal of Trauma Stress, vol. 30, no. 4, pp. 362–371, 2017.
  • J. L. Steel, A. C. Dunlavy, J. Stillman,H. C. Pape, Measuring Depression and PTSD after Trauma: Common Scales and Checklists. Journal of Injury, vol. 42, no.3. pp. 288–300, 2011.
  • R. Levy, K. Karstoft, A. Statnikov, and A. Shalev, Quantitative Forecasting of PTSD from Early Trauma Responses: A Machine Learning Application, Journal of Traumatic Stress, vol. 32, pp. 215-225, 2019.
  • S. İ. Omurca and E. Ekinci, An Alternative Evaluation of Post Traumatic Stress Disorder with Machine Learning Methods, International Symposium on Innovations in Intelligent Systems and Applications, Madrid, Spain, pp. 1-7, 2015.
  • T. Armstrong, S. Federman, K. Hampson, et al., Fear Learning in Veterans with Combat-Related PTSD is Linked to Anxiety Sensitivity: Evidence from Self-Report and Pupillometry, Behavior Therapy, In Press, 2020.
  • T. Roushan et al., Towards Predicting Risky Behavior Among Veterans with PTSD by Analyzing Gesture Patterns, IEEE Annual Computer Software and Applications Conference, Milwaukee, USA, pp. 690-695, 2019.
  • T. Wörtwein and S. Scherer, An Information Gain Analysis of Questions and Reactions in Automated PTSD Screenings, International Conference on Affective Computing and Intelligent Interaction, San Antonio, USA, pp. 15-20, 2017.
There are 17 citations in total.

Details

Primary Language English
Subjects Engineering
Journal Section Articles
Authors

Mustafa Dağtekin 0000-0002-0797-9392

Engin Seven 0000-0002-7994-2679

Ahmet Emre Balsever This is me 0000-0002-3655-1571

Eda Nur Var This is me

Leyla Türker Şener This is me 0000-0002-7317-9086

Nilüfer Alçalar This is me 0000-0001-9122-5421

Betül Ensari This is me 0000-0003-0425-7252

Tolga Ensari 0000-0003-0896-3058

Publication Date August 15, 2020
Published in Issue Year 2020 Ejosat Special Issue 2020 (HORA)

Cite

APA Dağtekin, M., Seven, E., Balsever, A. E., Var, E. N., et al. (2020). Post-Traumatic Stress Disorder (PTSD) Management: A Machine Learning Approach. Avrupa Bilim Ve Teknoloji Dergisi284-288. https://doi.org/10.31590/ejosat.779973