Prediction of the Level of Alexithymia through Machine Learning Methods Applied to Automatic Thoughts

Abstract

This study aims to investigate the relationship among alexithymia levels and automatic thoughts from cognitive behavioral therapy concepts. For this aim, Fisher Score analysis was applied to determine the most effective attributes of the automatic thoughts scale. In addition, the level of alexithymia was predicted by the introduction of the data set into the machine learning methods of the Artificial Neural Network (ANN) and Support Vector Machine (SVM). It is aimed to develop a roadmap of what automatic thoughts should be given priorities in studies. The research, from 10 different provinces of Turkey, was performed with a total of 714 participants, of which 386 (54%) male and 328 (46%) female. Personal information form, Automatic Thoughts Scale and Toronto Alexithymia scale were applied to the participants. The data set obtained from the scale of automatic thoughts was applied to the feature selection by using the Fisher Score method and a data set containing 5 attributes was obtained. As a result of the implementation of the SVM method to this data set, the alexithymia level was predicted with 4.01 RMSE error. The results show that the features of the automatic thoughts are related to the alexithymia level.

Keywords

• Alexithymia,automatic thoughts,machine learning

Otomatik Düşüncelere Makine Öğrenme Yöntemlerinin Uygulanması ile Aleksitimi Düzeyinin Tahmini

Öz

Bu araştırmada bilişsel davranışçı terapi kavramlarından otomatik düşüncelerin aleksitimi ile ilişkisi incelenmiştir. Bu amaçla otomatik düşünceler ölçeğini oluşturan en etkili öznitelikleri tespit etmek için FisherScore analizi uygulanmıştır. Ayrıca veri kümesinin Yapay Sinir Ağı (YSA) ve Destek Vektör Makinesi (DVM) makine öğrenmesi yöntemlerine giriş olarak verilmesiyle aleksitimi düzeyi tahmin edilmiş ve bu sayede önceliğin hangi otomatik düşüncelere vermesi gerektiği konusunda bir yol haritası sunulması amaçlanmıştır. Araştırma Türkiye’nin 10 farklı ilinden 386 (%54) erkek 328 (%46) kadın olmak üzere 714 katılımcı ile gerçekleştirilmiştir. Katılımcılara kişisel bilgiler formu, Otomatik Düşünceler Ölçeği ve Toronto Aleksitimi ölçeği uygulanmıştır. Otomatik düşünceler ölçeğinden elde edilen veri kümesine Fisher Score yöntemi ile öznitelik seçim işlemi uygulanarak 5 adet öznitelik içeren veri kümesi elde edilmiştir. Bu veri kümesine DVM yönteminin uygulanması sonucunda 4.01 RMSE hatası ile aleksitimi seviyesi tahmin edilmiştir. Sonuçlar otomatik düşünceler ölçeğindeki özniteliklerin aleksitimi düzeyi ile ilişkili olduğunu göstermektedir.

Anahtar Kelimeler

• Aleksitimi,otomatik düşünce,makine öğrenmesi

Kaynakça

1. Arcan K, Yüce ÇB (2016) İnternet Bağımlılığı ve İlişkili Psiko-Sosyal Değişkenler: Aleksitimi Açısından Bir Değerlendirme. Türk Psikoloji Dergisi, 31(77):46-56.
2. Ayhan S, Erdoğmuş Ş (2014) Destek vektör makineleriyle sınıflandırma problemlerinin çözümü için çekirdek fonksiyonu seçimi [Kernel Function Selection for the Solution of Classification Problems via Support Vector Machines.] Eskişehir Osmangazi Üniversitesi İktisadi ve İdari Bilimler Dergisi, 9(1):175-198.
3. Bagby RM, Parker JDA, Taylor GJ (1994) The twenty-item Toronto Alexithymia Scale-I Item selection and cross validation of the factor structure. Journal of Psychosomatic Research 38 (1): 23-32.doi:10.1016/0022-3999(94)90005-1
4. Beck, A.T. (1979). Cognitive therapy and the emotional disorders. New York, Penguin.
5. Baca-García E et al. (2006) Using data mining to explore complex clinical decisions: a study of hospitalization after a suicide attempt. Journal of Clinical Psychiatry, 67(7): 1124-1132. doi:10.4088/JCP.v67n0716
6. Bae SM, Lee SH, Park YM, Hyun MH, Yoon H (2010) Predictive factors of social functioning in patients with schizophrenia: exploration for the best combination of variables using data mining. Psychiatry investigation, 7(2): 93-101. doi:10.4306/pi.2010.7.2.93
7. Bellanger M (2000). Digital processing of signal: theory and practice. New York, John Wiley and Sons.
8. Berthoz S, Perdereau F, Godart N, Corcos M, Haviland M (2007) Observerand self-relate dalexithymia in eating disorder patients: Level sand correspondance among three measures. Journal of Psychosomatic Research 62(3):341-347. doi:10.1016/j.jpsychores.2006.10.008

9. Besharat MA (2010) Relationship of alexthymia with coping styles and interpersonal problems. Procedia – Social and Behavioral Sciences 5:614-618. doi10.1016/j.sbspro.2010.07.152
10. Bilge U (2007) Tıpta Yapay Zeka ve Uzman Sistemler [Artificial Intelligence and Expert Systems in Medicine]. Department of Biostatistics and Medicine Informatics. Akdeniz University Faculty of Medicine, Antalya, Türkiye.
11. Cai R, Hao Z, Yang X, Wen W (2009) An efficient gene selection algorithm based on mutual information. Neurocomputing, 72 (4-6): 991-999. doi:10.1016/j.neucom.2008.04.005
12. Chai T, Draxler RR (2014). Root mean square error (rmse) or mean absolute error (MAE). Geoscientific Model Development, 7: 1247-1250. doi:10.5194/gmd-7-1247-2014
13. Coolidge FL, Estey AJ, Segal DL, Marle PD (2013) Are alexithymia and schizoid personality disorder synonymous diagnoses? Comprehensive Psychiatry 54 (2):141-148. doi:10.1016/j.comppsych.2012.07.005
14. Coriale G, Bilotta E, Leone L, Cosimi F, Porrari R, De Rosa F (2012) Avoidance coping strategies, alexithymia and alcohol abuse: A mediation analysis. Addictive Behaviors 37 (11): 1224-1229. doi:10.1016/j.addbeh.2012.05.018
15. Coyne JC, Gotlib IH (1983) The role of cognition in depression: A critical appraisal. Psychological Bulletin, 94(3):472-505. doi:10.1037/0033-2909.94.3.472Declercq F, Vanheule S, Deheegber J (2010) Alexithymia and posttraumatic stress: Subscales and symptom clusters. Journal of Clinical Psychology, 66 (10): 1076-1089. doi:10.1002/jclp.20715
16. Demuth H, Beale M (2000) Neural Network Toolbox for use with Matlab. Math Works Inc.
17. Elmas Ç (2003) Yapay Sinir Ağları (Kuram, Mimari, Eğitim, Uygulama). Ankara: Seçkin Yayınları.
18. Ferreira AJ, Figueiredo MAT (2012) Efficient feature selection filters for high dimensional data. Pattern Reconition Letters, 33 (13):1794-1804. doi:10.1016/j.patrec.2012.05.019
19. Garver MS (2002) Using Data Mining For Customer Satisfaction Research. Journal of Marketing Research, 14(1): 8–12.
20. Ghazav SN, Liao TW (2008) Medical data mining by fuzzy modeling with selected features. Artificial Intelligence in Medicine, 43(3):195-206. doi:10.1016/j.artmed.2008.04.004
21. Grabe HJ, Spitzer C, Freyberger HJ (2004) Alexithymia and personality in relation to dimensions of psychopathology. American Journal of Psychiatry, 161(7):1299-1301. doi:10.1176/appi.ajp.161.7.1299
22. Güleç H, Köse S, Güleç YM, Çitak S, Evren C, Borckardt J, Sayar K, (2009). Reliability and Factorial Validity of The Turkish Version of The 20-Item Toronto Alexithymia Scale (TAS-20). Bulletin of Clinical Psychopharmacology, 19 (3): 214-220.
23. Güneri N, Apaydin A (2004) Öğrenci Başarılarının Sınıflandırılmasında Lojistik Regresyon Analizi ve Sinir Ağları Yaklaşımı [Logistic Regression Analysis and Neural Networks Approach in the Classification of Students Achievement]. Ticaret ve Turizm Eğitim Fakültesi Dergisi, 1: 170 – 188.
24. Hagan MT, Menhaj MB (1994) Training feedforward networks with the Marquardt algorithm. IEEE transactions on Neural Networks, 5(6): 989-993.
25. Hastie T, Tibshirani R, Friedman J (2009). Unsupervised learning. In The elements of statistical learning. New York, Springer.
26. Haykin S (1999). Neural Networks: A Comprehensive Foundation. New Jersey, Prentice Hall International.
27. Hearst MA, Dumais ST, Osuna E, Platt J, Scholkopf B (1998). Support vector machines. IEEE Intelligent Systems and their applications, 13(4): 18-28.doi:10.1109/5254.708428
28. Hollon S, Kendal P (1980) Cognitive self-statement in depression: Clinical validation of an automatic thoughts question naire. Cognitive Therapy and Research, 4 (4):383-395.
29. Honkalampi K, Hintikka J, Tanskanen A, Lehtonen J, Viinamaki H (2000) Depression is strongly associated with alexithymia in the general population. Journal of Psychosomatic Research 48 (1): 99-104. doi:10.1016/S0022-3999(99)00083-5
30. Hsu H, Hsieh C, Lu M (2011) Hybrid feature selection by combining filters and wrappers. Expert Systems with Applications, 38 (7): 8144-8150. doi:10.1016/j.eswa.2010.12.156
31. Kaastra I, Boyd M (1996) Designing a neural network for forecasting financial and econometric time series. Neurocomputing, 10:215-236.doi:10.1016/0925-2312(95)00039-9
32. Kim KJ (2003) Financial time series forecasting using support vector machines. Neurocomputing, 55(1-2): 307-319.
33. Koçak R (2016) Duygusal ifade eğitimi programının üniversite öğrencilerinin aleksitimi ve yalnızlık düzeylerine etkisi. Türk Psikolojik Danışmave Rehberlik Dergisi 3 (23):29-45
34. Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In Ijcai 14(2): 1137-1145.
35. Krystal HJ (1982) Alekxithymia and effectiveness of psychoanalytic treatment. International Journal of Pychoanalytic Psychotherapy 9:353-378.
36. Lazarus RS (1982) Thoughts on the relation between emotion and cognition. American Psychologist 37 (9):1019-1024. doi:10.1037/0003-066X.37.9.1019.
37. Lee PH (2014) Is a cutoff of 10% appropriate for the change-in-estimate criterion of confounder identification? Journal of epidemiology 24(2): 161-167.
38. Lesser LM (1985) Cuntent concepts LO psychiatry, alexithymia. The New England Journal of Medicine, 312(11): 690-694.
39. Levant FR (1992) Toward there construction of masculinity. Journal of Family Psychology, 5: 379-402.
40. Martin JB, Pihl RO (1986) Influence of alexithymic characteristics on physiological and subjective stress responses in normal individuals. Psychotherapy and Psychosomatics 45: 66-77. doi:10.1159/000287930
41. Nabiyev VV (2003).Yapay zeka, Ankara, Seçkin Yayıncılık.
42. Nitze I, Schulthess U, Asche H (2012) Comparison of machine learning algorithms random forest, artificial neural network and support vector machine to maximum likelihood for supervised crop type classification. Proc. of the 4th GEOBIA (7-9 May 2012, Rio de Janeiro), p.7-9, Rio de Janeiro, Brazil.
43. Nguyên X, Chaskalovis J, Rakotonanahary D, Fleury B (2010) Insomnia symptoms and CPAP compliance in OSAS patients: A descriptive study using Data Mining methods. Sleep medicine 11(8): 777-784. doi:10.1016/j.sleep.2010.04.008
44. Ogrodniczuk JS, Sochting I, Piper WE Joyce AS (2012) A naturalistic study of alexithymia among psychiatric out patient streated in an integrated group therapy program. Psychology and Psychotherapy: Theory, Reserach and Practice 85 (3): 278-291. doi:10.1111/j.2044-8341.2011.02032.x.
45. Osowski S, Siwekand K, Markiewicz T (2004) MLP and SVM Networks – a Comparative Study. Proceedings of the 6th Nordic Signal Processing Symposium –NORSIG.
46. Osuna EE, Freund R, Girosi F (1997) Support vector machines: training and applications, Massachusetts Institute of Technology and Artificial Intelligence Laboratory. Massachusetts. 1602:144.
47. Öztemel E (2003)Yapay sinir ağları. Istanbul, Papatya Yayıncılık.
48. Öztürk A (2008) Doppler işaretlerinin kaotik ölçütlerle sınıflandırılması. Phd Thesis, Konya, Selçuk University, Konya.
49. Pardo M, Sberveglieri G (2005) Classification of electronic nose data with support vector machines. Sensors and Actuators B: Chemical, 107(2): 730-737.
50. Rosenthal DA, Dalton JA, Gervey R (2007) Analyzing vocational outcomes of individuals with psychiatric disabilities who received state vocational rehabilitation services: A data mining approach. International Journal of Social Psychiatry, 53(4): 357-368. doi:10.1177/0020764006074555
51. Saeys Y, Inza I, Larranaga P, (2007) A review of feature selection techniques in bioinformatics. Bioinformatics, 23(19): 2507-2517. doi:10.1093/bioinformatics/btm344
52. Soman KP, Loganathan R, Ajay V (2011) Machine learning with SVM and other kernel methods, New Delhi, PHI Learning Pvt. Ltd.
53. Song Q (2010) The comparison and analysis of classification methods for psychological assessment data. Information Science and Engineering (ICISE), 2nd International Conference on. IEEE. 4133-4135.
54. Sifneos PE, Apfel SR, Frankel FH, (1977) The phenomenon of alexithymia. Psychotherapy Psychosomatic, 28: 47-57. doi:10.1159/000287043
55. Spitzer C, Siebel-Jürges U, Barnow S, Grabe HJ, Freyberger HJ, (2005) Alexithymia and interpersonal problems. Psychotherapy and Psychosomatics, 74 (4): 240-246. doi:10.1159/000085148
56. Steinwart I, Christmann A (2008) Support vector machines. New York, Springer Science& Business Media.
57. Stephanos S (1975) A concept of analytical treatment for patients with psychosomatic disorders. Psychoter Psychosom, 26:178-187.
58. Stoudemire A (1991) Somatothymia: parts I and II. Psychosomatics, 32(4): 365-381. doi:10.1016/S0033-3182(91)72037-9
59. Şahin NH, Şahin N, (1992) Reliability and validity of the Turkish version of the automatic thoughts questionnaire. Journal of Clinical Psychology, 48: 334-340. doi:10.1002/1097-4679(199205)48:3<334::AID-JCLP2270480311>3.0.CO;2-P
60. Taylor GJ, Parker JDA, Bagby RM, Acklin MV, (1992) Is alexithymia and somatic complaints psychiatric out paitents. Journal of Psychosomatic Research, 36(5):417-424. doi:10.1016/0022-3999(92)90002-J
61. Türkçapar MH, (2009) Bilişselterapi: temel ilkeler ve uygulamalar, Ankara, HYB.
62. Qinghua J (2016) Data Mining and Management System Design and Application for College Student Mental Health. Intelligent Transportation, Big Data & Smart City (ICITBS), International Conference on. IEEE: 410-413.
63. Vanheule S, Desmet M, Meganck R, Bogaerts S (2007) Alexthymia and interpersonal problems. Journal of Clinical Psychology, 63:109-117.doi:10.1002/jclp.20324
64. Vapnik V, Chapelle O (2000) Bounds on error expectation for support vector machines. Neural computation, 12(9): 2013-2036. doi:10.1162/089976600300015042
65. Willmott CJ, Matsuura C, (2005) Advantages of the mean absolute error (mae) over the root mean square error (rmse) in assessing average model performance. Climate Research 30: 79-82. doi:10.3354/cr030079
66. Wolff HH, (1977) The contribution of interview situation to the restriction of fantasy life and emotional expression in psychosomatic patients. Psychoter Psychosom 28: 58- 67.
67. Yavuz Ö, Tecim V (2011) Cbs Tabanlı Suç Önleme Çalışmalarında Yapay Sinir Ağları Kullanılarak Mekansal Karar Sistemi Oluşturulması. Suç Önleme Sempozyumu (7 - 8 October Bursa), 2011, p.295-309, Bursa, Türkiye.