Reduction and hierarchization of the SPRINT-E scale for the primary diagnosis of post-traumatic stress syndrome in university students
Keywords:
Decision tree, Earthquake, Rough sets, Post-traumatic stress syndromeAbstract
Post-traumatic stress syndrome is a disorder caused by a person's direct or indirect exposure to a situation that has violated their physical and emotional health. If the affected person does not receive treatment, they are prone to alcohol and drug use and, in severe cases, suicide. Before receiving specialized care, primary or screening tests allow identifying people at risk of acquiring this syndrome and referring them to mental health specialists. Instruments that allow for a comprehensive diagnosis usually contain a large number of questions in their assessment scales. However, this forces the people being assessed to answer numerous questions, which can cause them emotional distress due to the effort involved in answering all the questions to be assessed. In this context, a system based on the minimization of questions using the theory of rough sets forming a reduct that makes up the original instrument is proposed. With the reduct obtained, decision trees are used to create a sequence of questions that allows for an assessment to be obtained in less time than that required to answer the full version, without sacrificing diagnostic power. Since the rough set theory does not depend on the amount of data, this study focused on assessing the mental health of students from different semesters who were pursuing a Bachelor's Degree in Medicine, and enrolled at the University of Colima, Mexico. Using a Google Forms template, the 11-question SPRINT-E scale was applied at two moments after the 7.7-magnitude earthquake on the Richter scale that affected the city of Colima, Mexico, on September 19, 2022. The survey had the participation of 158 students in the September survey and 42 in November. The results showed that women obtained an internal reliability greater than 0.9. The survey answered by men in September had a Cronbach's alpha of 0.948 and was not evaluable in November. The diagnosis for men was negative in both periods. On the other hand, in women, ten positive and two negative primary diagnoses were recorded in September, while in November, two cases decreased and no false positives were reported. Rough set theory allowed reducing the number of questions on the SPRINT-E scale from 11 to 4, and decision trees were used to establish the hierarchical order and cut-off points to identify a positive, negative, and false positive primary diagnosis. Finally, the tree model was validated with the November data, showing the same diagnoses regarding the full scale. This study does not intend to replace the primary diagnoses of post-traumatic syndrome, but offers the interviewer a reduced version of questions that, in case that the participant responds with the highest intensity, proceeds with the rest of the validation scale in order to channel the affected persons more efficiently to a mental health specialist.
References
[1] Mendoza Bermúdez, Constanza. (2009). Sociología y salud mental: una reseña de su asociación. Revista Colombiana de Psiquiatría, 38(3), 555-573.
[2] Asociación Americana de Psicología. (2010). Diccionario conciso de Psicología. Editorial El Manual Moderno.
[3] Organización Mundial de la Salud. (2016). CIE-10. Trastornos Mentales y del Comportamiento. Décima Revisión de la Clasificación Internacional de las Enfermedades. Descripciones Clínicas y pautas para el diagnóstico. Organización Mundial de la Salud, Ginebra.
[4] Udomratn, P. (2008). Mental health and the psychosocial consequences of natural disasters in Asia. International review of psychiatry, 20(5), 441–444. https://doi.org/10.1080/09540260802397487
[5] Guerra, C., Cumsille, P., & Martínez, M. L. (2014). Post traumatic stress symptoms in adolescents exposed to an earthquake: Association with self-efficacy, perceived magnitude, and fear. International Journal of Clinical and Health Psychology, 14(3), 202–207. https://doi.org/10.1016/j.ijchp.2014.05.001
[6] Secretaría de Protección Civil. (2022). Situación sísmica. http://data.proteccioncivil.cdmx.gob.mx/simulacros/CDMX/Situacion-sismica.html
[7] Programa Integral para el Bienestar Socioemocional. (2023). Atentamente cambio yo, cambia todo. https://www.atentamente.com.mx/
[8] Instituto de Salud Pública. (2023). Línea de investigación en prevención de lesiones y violencia. https://www.insp.mx/avisos/4761-seguridad-vial-accidentes-transito.html
[9] Tapia-Conyer, R. C., Sepulveda-Amor, J., & Medina-Mora, M. E. (1987). Prevalencia del síndrome de estrés postraumático en la población sobreviviente a un desastre natural. Salud pública de México, 29(5), 406–411.
[10] Davidson, J. R. T., et al. (1997). Assessment of a new self-rating scale for posttraumatic stress disorder. Psychological Medicine, 27, 153–160. https://doi.org/10.1037//1040-3590.9.4.445
[11] Jimenez-López, J. L., Angeles-Garay, U., & Arenas-Osuna, J. (2019). Estrés postraumático en médicos residentes posterior a los sismos de septiembre 2017 en México. Revista Mexicana de Psiquiatría y Salud Mental, 1(2), 45–51.
[12] García, A. M. S., Estrada, V. M. E., & Noriega, I. C. (2019). Trastorno por estrés postraumático posterior al sismo de septiembre 2017 en personal de enfermería en el hospital de especialidades del Centro Médico Nacional. Revista Mexicana de Psicología, 1(3), 87–96.
[13] Cieslak, S., et al. (2009). Predicting posttraumatic growth among Hurricane Katrina survivors living with HIV: the role of self-efficacy, social support, and PTSD. Anxiety, Stress & Coping, 22(4), 449-463. https://doi.org/10.1080/10615800802403815
[14] Leiva, M. & Araneda, A. (2013). Prevalencia y sintomatología del estrés post traumático en personas que experimentan un terremoto y un tsunami. Salud y Sociedad, 4(2), 146-151. https://doi.org/10.22199/s07187475.2013.0002.00003
[15] Kilic, C. & Ulusoy, M. (2003). Psychological effects of the November 1999 earthquake in Turkey: An epidemiological study. Acta Psychiatrica Scandinavica, 108(3), 23.
[16] Leiva-Bianchi, M. C., & Gallardo, I. (2013). Validación de la escala breve para diagnosticar estrés postraumático (SPRINT-E) en una muestra de personas afectadas por el terremoto y tsunami del 27-F en Chile. Anales de psicología, 29(2), 328–334. https://doi.org/10.6018/analesps.29.2.130681
[17] Norris, F. H., et al. (2008). Validation of the short posttraumatic stress disorder rating interview (expanded version, sprint-e) as a measure of postdisaster distress and treatment need. American Journal of Disaster Medicine, 3(4), 201–212.
[18] Alvarez Icaza, D., & Medina-Mora, M. E. (2018). Impacto de los sismos de septiembre de 2017 en la salud mental de la población y acciones recomendadas. Salud pública de México, 60, 52–58. https://doi.org/10.21149/9399
[19] Pawlak, Z. (1982). Rough sets. International journal of computer information sciences, 11, 341–356. https://doi.org/10.1007/978-1-4613-1461-5_1
[20] Cherry, H. (2009). Medical Information System for Diabetes Mellitus by using Rough Set Theory (Doctoral dissertation, MERAL Portal).
[21] Greco, S., et al. (2001). Rough sets theory for multicriteria decision analysis. European journal of operational research, 129(1), 1–47. https://doi.org/10.1016/s0377-2217(00)00167-3
[22] Liu, T. K., et al. (2014). Noninvasive evaluation of mental stress using a refined rough set technique based on biomedical signals. Artificial intelligence in medicine, 61(2), 97–103. https://doi.org/10.1016/j.artmed.2014.05.001
[23] Tang, X., et al. (2015). Application of rough set theory in item cognitive attribute identification. Acta Psychologica Sinica, 47(7), 950. https://doi.org/10.3724/sp.j.1041.2015.00950
[24] Torbas, O., et al. (2020). Student survey for higher education quality and challenges to design and analyze data. Humanities & Social Sciences Reviews, 8(2), 85–92. https://doi.org/10.18510/hssr.2020.82e09
[25] Abey, P. & Bennett, D. (2021). Using deliberate mistakes to heighten student attention. Journal of University Teaching and Learning Practice, 18(6), 193-212. https://doi.org/10.53761/1.18.6.13
[26] Quinlan, J. R. (1996). Learning decision tree classifiers. ACM Computing Surveys (CSUR), 28(1), 71–72. https://doi.org/10.1145/234313.234346
[27] Cheruku, R., et al. (2018). A fuzzy rule miner integrating rough set feature selection and bat optimization for detection of diabetes disease. Applied Soft Computing, 67, 764–780. https://doi.org/10.1016/j.asoc.2017.06.032
[28] Reddy, G. T., et al. (2020). Hybrid genetic algorithm and a fuzzy logic classifier for heart disease diagnosis. Evolutionary Intelligence, 13, 185–196. https://doi.org/10.1007/s12065-019-00327-1
[29] Quinlan, J. R. (1996). Learning decision tree classifiers. ACM Computing Surveys (CSUR), 28(1), 71–72. https://doi.org/10.1145/234313.234346
[30] Rosellini, A. J., et al. (2018). Predicting posttraumatic stress disorder following a natural disaster. Journal of psychiatric research, 96, 15–22. https://doi.org/10.1016/j.jpsychires.2017.09.010
[31] Ge, F., et al. (2020). Identifying predictors of probable posttraumatic stress disorder in children and adolescents with earthquake exposure: a longitudinal study using a machine learning approach. Journal of affective disorders, 264, 483–493. https://doi.org/10.1016/j.jad.2019.11.079
[32] Diario Oficial de la Federación. (2022). Declaratoria de desastre natural por la ocurrencia de sismo magnitud 7.7 el 19 de septiembre de 2022, en 10 municipios del edo de Colima. https://www.dof.gob.mx/nota_detalle.php?codigo=5666009&fecha=30/09/2022
[33] Rotundo, G. Z., & Giner, M. T. C. (2008). Propuesta metodológica para la construcción de escalas de medición a partir de una aplicación empírica. Actualidades investigativas en Educación, 8(2).
[34] Morales Vallejo, P. (2011). Estadística aplicada a las ciencias sociales. Editorial Universidad Pontificia Comillas.
[35] Thangavel, P., et al. (2005). Effective classification with improved quick reduct for medical databases using a rough system. Biomedical Informatics and Medicine Education Journal, 5(1), 7–14.
[36] Stepaniuk, J. (1999). Rough set data mining of diabetes data. En Raś, Z.W., Skowron, A. (eds) Foundations of Intelligent Systems. ISMIS 1999. Lecture Notes in Computer Science, vol 1609. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0095133
[37] Hourani, L. L., et al. (2011). Approaches to the primary prevention of posttraumatic stress disorder in the military: a review of the stress control literature. Military Medicine, 176(7), 721–730. https://doi.org/10.7205/milmed-d-09-00227
[38] McLean, D., et al. (2012). Review of the civil defense emergency management response to the 22 February Christchurch.
[40] Quispe Limaylla, A. (2013). El uso de la encuesta en las ciencias sociales. Ediciones Díaz de Santos.
