Top

Published in:

01-12-2020 | Suicide | Research article

Recognizing states of psychological vulnerability to suicidal behavior: a Bayesian network of artificial intelligence applied to a clinical sample

Authors: Jorge Barros, Susana Morales, Arnol García, Orietta Echávarri, Ronit Fischman, Marta Szmulewicz, Claudia Moya, Catalina Núñez, Alemka Tomicic

Published in: BMC Psychiatry | Issue 1/2020

Abstract

Background

This study aimed to determine conditional dependence relationships of variables that contribute to psychological vulnerability associated with suicide risk. A Bayesian network (BN) was developed and applied to establish conditional dependence relationships among variables for each individual subject studied. These conditional dependencies represented the different states that patients could experience in relation to suicidal behavior (SB). The clinical sample included 650 mental health patients with mood and anxiety symptomatology.

Results

Mainly indicated that variables within the Bayesian network are part of each patient’s state of psychological vulnerability and have the potential to impact such states and that these variables coexist and are relatively stable over time. These results have enabled us to offer a tool to detect states of psychological vulnerability associated with suicide risk.

Conclusion

If we accept that suicidal behaviors (vulnerability, ideation, and suicidal attempts) exist in constant change and are unstable, we can investigate what individuals experience at specific moments to become better able to intervene in a timely manner to prevent such behaviors. Future testing of the tool developed in this study is needed, not only in specialized mental health environments but also in other environments with high rates of mental illness, such as primary healthcare facilities and educational institutions.

Conditional dependency relationships: measures of the probability of an event occurring given that another event has (by assumption, presumption, assertion or evidence) occurred [14].

Support vector machine models: Supervised learning models associated with learning algorithms that analyze data used for regression and classification analysis. Starting with a set of training examples, each marked as belonging to one or the other of two categories, an SVM training algorithm builds a model that assigns new examples to one category or the other, hence resolving a non-probabilistic binary linear classifier [6].

Decision tree technique: A model of computation in which an algorithm is considered to be a sequence of branching operations based on comparisons of some quantities, the comparisons being assigned the unit computational cost. The branching operations are called “queries or tests”. The algorithm may be considered a computation of a Boolean function where the input is a series of queries and the output is a final decision, in which every query is dependent on previous queries or tests [7].

American Psychiatric Association. Diagnostic and statistical manual of mental disorders, vol. 25. 5th ed edA. P. P. Incorporated, Ed: American Psychiatric Publishing, Inc; 2013. https://doi.org/10.1176/appi.books.9780890425596.744053.

Antonucci A, Zaffalon M. Probabilistic graphical models. In: Introduction to imprecise probabilities. Chichester: Wiley; 2014. p. 207–29.

Bae SM. The prediction model of suicidal thoughts in Korean adults using decision tree analysis: a nationwide cross-sectional study. PLoS One. 2019;14(10):1–10. https://doi.org/10.1371/journal.pone.0223220.CrossRef

Baader T, Richter P, Mundt C. Suicidios de pacientes psiquiátricos hospitalizados y sus factores de riesgo: un estudio Caso control. Revista chilena de neuro-psiquiatría. 2004;42(4):293–316. https://doi.org/10.4067/S0717-92272004000400006.CrossRef

Barros J, Morales S, Echávarri O, García A, Ortega J, Asahi T, et al. Suicide detection in Chile: proposing a predictive model for suicide risk in a clinical sample of patients with mood disorders. Rev Bras Psiquiatr. 2017;39(1):1–11. https://doi.org/10.1590/1516-4446-2015-1877.CrossRefPubMed

Boser BE, Guyon IM, Vapnik VN. A training algorithm for optimal margin classifiers. In: Proceedings of the 5th annual acm workshop on computational learning theory; 1992. p. 144–52.

Bramer M. Principles of data mining. London: Springer; 2007.

Burke TA, Ammerman BA, Jacobucci R. The use of machine learning in the study of suicidal and non-suicidal self-injurious thoughts and behaviors: a systematic review. J Affect Disord. 2019;15(245):869–84. https://doi.org/10.1016/j.jad.2018.11.073.CrossRef

Chung DT, Ryan CJ, Hadzi-Pavlovic D, Singh SP, Stanton C, Large MM. Suicide rates after discharge from psychiatric facilities. JAMA Psychiatry. 2017;74(7):694–702. https://doi.org/10.1001/jamapsychiatry.2017.1044.CrossRefPubMedPubMedCentral

10.

De Berardis D, Fornaro M, Orsolini L, Valchera A, Carano A, Vellante F, et al. Alexithymia and suicide risk in psychiatric disorders: a mini-review. Frontiers in Psychiatry. 2017;8(148):1–6. https://doi.org/10.3389/fpsyt.2017.00148.CrossRef

11.

Erlangsen A, Zarit SH, Conwell Y. Hospital-diagnosed dementia and suicide: a longitudinal study using prospective, Nationwide register data. Am J Geriatr Psychiatr. 2008;16(3):220–8. https://doi.org/10.1097/JGP.0b013e3181602a12.CrossRef

12.

Franklin JC, Ribeiro JD, Fox KR, Bentley KH, Kleiman EM, Huang X, et al. Risk factors for suicidal thoughts and behaviors: a meta-analysis of 50 years of research. Psychol Bull. 2017;143(2):187. https://doi.org/10.1037/bul0000084.CrossRefPubMed

13.

Galynker I, Yaseen ZS, Cohen A, Benhamou O, Hawes M, Briggs J. Prediction of suicidal behavior in high risk psychiatric patients using an assessment of acute suicidal state: the suicide crisis inventory. Depress Anxiety. 2017;34(2):147–58. https://doi.org/10.1002/da.22559.CrossRefPubMed

14.

Gut A. Probability: a graduate course. 2nd ed. New York: Springer; 2013. ISBN 978-1-4614-4707-8.CrossRef

15.

Hawgood J, De Leo D. Suicide prediction – a shift in paradigm is needed. Crisis. 2016;37(4):251–5. https://doi.org/10.1027/0227-5910/a000440.CrossRefPubMed

16.

Hawton K, Casañasi Comabella C, Haw C, Saunders K. Risk factors for suicide in individuals with depression: a systematic review. J Affect Disord. 2013;147(3):17–28. https://doi.org/10.1016/j.jad.2013.01.004.CrossRefPubMed

17.

Herzog DB, Greenwood DN, Dorer DJ, Flores AT, Ekeblad ER, Richards A, et al. Mortality in eating disorders: a descriptive study. Int J Eat Disord. 2000;28(1):20–6. https://doi.org/10.1002/(SICI)1098-108X(200007)28:1<20::AID-EAT3>3.0.CO;2-X.CrossRefPubMed

18.

Lambert MJ, Burlingame GM, Umphress V, Hansen NB, Vermeersch D a, Clouse GC, et al. The reliability and validity of the outcome questionnaire. Clin Psychol Psychother. 1996;3(4):249–58. https://doi.org/10.1002/(SICI)1099-0879(199612)3:4<249::AID-CPP106>3.0.CO;2-S.CrossRef

19.

Large M, Kaneson M, Myles N, Myles H, Gunaratne P, Ryan C. Meta-analysis of longitudinal cohort studies of suicide risk assessment among psychiatric patients: heterogeneity in results and lack of improvement over time. PLoS One. 2016;11(6):1–17. https://doi.org/10.1371/journal.pone.0156322.CrossRef

20.

Lemmi V, Bantjes J, Coast E, Channer K, Leone T, McDaid D, et al. Suicide and poverty in low-income and middle-income countries: a systematic review. Lancet Psychiatry. 2016;3(8):774–83. https://doi.org/10.1016/S2215-0366(16)30066-9.CrossRef

21.

Liu X, Huang Y, Liu Y. Prevalence, distribution, and associated factors of suicide attempts in young adolescents: school-based data from 40 low-income and middle-income countries. PLoS One. 2018;13(12):1–12. https://doi.org/10.1371/journal.pone.0207823.CrossRef

22.

Ma J, Batterham PJ, Calear AL, Han J. A systematic review of the predictions of the interpersonal-psychological theory of suicidal behaviour. Clin Psychol Rev. 2016;46(1):34–45.CrossRef

23.

Maino MD, Morales S, Echávarri O, Barros J, García A, Moya C, et al. Suicide risk configuration system in a clustered clinical sample: a generalized linear model obtained through the LASSO technique. Braz J Psychiatry. 2018;41(2):112–21. https://doi.org/10.1590/1516-4446-2017-0028.CrossRefPubMedPubMedCentral

24.

Morales S, Armijo I, Moya C, Echávarri O, Barros J, Varela C, et al. Percepción de cuidados parentales tempranos en consultantes a salud mental con intento e ideación suicida. Avances En Psicología Latinoamericana. 2014;32(3):403–17. https://doi.org/10.12804/apl32.03.2014.06.CrossRef

25.

Morales S, Barros J, Echávarri O, García F, Osses A, Moya C, et al. Acute mental discomfort associated with suicide behavior in a clinical sample of patients with affective disorders: ascertaining critical variables using artificial intelligence tools. Front Psychiatry. 2017;8:1–16. https://doi.org/10.3389/fpsyt.2017.00007.CrossRef

26.

Morales S, Echávarri O, Barros J, Maino M, Armijo I, Fischman R, et al. Intento e Ideación Suicida en Consultantes a Salud mental: Estilos Depresivos, Malestar interpersonal y Satisfacción familiar. Psykhe. 2016;26(1):1–14. https://doi.org/10.7764/psykhe.26.1.939.CrossRef

27.

Nagarajan RN, Scutari M, Lëbre S. Bayesian networks in R: with applications in systems biology. New York: Springer; 2013. https://doi.org/10.1007/978-1-4614-64463.

28.

Nowicki E, Smutnicki C. A fast tabu search algorithm for the permutation flow-shop problem. Eur J Oper Res. 1996;91(1):160–75. https://doi.org/10.1016/0377-2217(95)00037-2.CrossRef

29.

OCDE. Health at a glance 2015: OECD indicators. Paris: OECD Publishing; 2015. https://doi.org/10.1787/health_glance-2015-en.CrossRef

30.

Oh J, Yun K, Hwang J-H, Chae J-H. Classification of suicide attempts through a machine learning algorithm based on multiple systemic psychiatric scales. Front Psychiatry. 2017;8:1–8. https://doi.org/10.3389/fpsyt.2017.00192.CrossRef

31.

Core Team R. R: a language and environment for statistical computing. Vienna; 2019. Retrieved from https://www.R-project.org/.

32.

Shlens J. A tutorial on principal component analysis; 2014. Retrieved from https://arxiv.org/pdf/1404.1100v1.pdf.

33.

Sucar L, Tonantzintla M. Redes Bayesianas. In Aprendizaje Automático: conceptos básicos y avanzados; 2006. p. 77–100. Retrieved from http://www-users.cs.umn.edu/~andre/arquivos/pdfs/bayesianas.pdf.

34.

Taylor T, Morales S, Zuloaga F, Echávarri O, Barros J. Lo que nos dicen los padres: Perspectivas de los padres de pacientes hospitalizados por ideación o intento suicida. Revista Argentina de Clínica Psicológica. 2012;21(3):271–80 https://www.redalyc.org/pdf/2819/281929021008.pdf.

35.

Tucker RP, Michaels MS, Rogers ML, Wingate LRR, Joiner TE. Construct validity of a proposed new diagnostic entity: acute suicidal affective disturbance (ASAD). J Affect Disord. 2016;189:365–78. https://doi.org/10.1016/j.jad.2015.07.049.CrossRefPubMed

36.

Verrocchio MC, Carrozzino D, Marchetti D, Andreasson K, Fulcheri M, Bech P. Mental pain and suicide: a systematic review of the literature. Front Psychiatry. 2016;7:1–17. https://doi.org/10.3389/fpsyt.2016.00108.CrossRef

37.

Von Bergen A, de la Parra G. OQ-45.2 Cuestionario Para evaluación de resultados y evolución en psicoterapia: Adaptación, validación e indicaciones Para su aplicación e interpretación. Terapia Psicológica. 2002;20(2):161–76 https://pesquisa.bvsalud.org/portal/resource/pt/lil-389263.

38.

Ribeiro JD, Franklin JC, Fox KR, Bentley KH, Kleiman EM, Chang BP, Nock MK. Self-injurious thoughts and behaviors as risk factors for future suicide ideation, attempts, and death: a meta-analysis of longitudinal studies. Psychol Med. 2016:46(2). https://doi.org/10.1017/S0033291715001804. http://www.bnlearn.com/documentation/man/structure.learning.htm.

39.

Walsh CG, Ribeiro JD, Franklin JC. Predicting risk of suicide attempts over time through machine learning. Clin Psychol Sci. 2017;5(3):457–69. https://doi.org/10.1177/2167702617691560.CrossRef

40.

Walsh G, Sara G, Ryan CJ, Large M. Meta-analysis of suicide rates among psychiatric in-patients. Acta Psychiatr Scand. 2015;131(3). https://doi.org/10.1111/acps.12383.

41.

White J. What can critical suicidology do? Death Studies. 2017;41(8):472–80. https://doi.org/10.1080/07481187.2017.1332901.CrossRefPubMed

42.

World Health Organization-WHO. Informe mundial sobre la violencia y la salud; 2002. Retrieved September 10, 2017 from http://www.who.int/violence_injury_prevention/violence/world_report/es/.

43.

World Health Organization (WHO). WHO mental health atlas 2014. Geneva: WHO; 2014. Retrieved from http://www.who.int/mental_health/evidence/atlas/mental_health_atlas_2014/en.

Title: Recognizing states of psychological vulnerability to suicidal behavior: a Bayesian network of artificial intelligence applied to a clinical sample
Authors: Jorge Barros
Susana Morales
Arnol García
Orietta Echávarri
Ronit Fischman
Marta Szmulewicz
Claudia Moya
Catalina Núñez
Alemka Tomicic
Publication date: 01-12-2020
Publisher: BioMed Central
Keywords: Suicide
Suicide
Artificial Intelligence
Published in: BMC Psychiatry / Issue 1/2020
Electronic ISSN: 1471-244X
DOI: https://doi.org/10.1186/s12888-020-02535-x

2024 ASCO Annual Meeting

Springer Medicine

Recognizing states of psychological vulnerability to suicidal behavior: a Bayesian network of artificial intelligence applied to a clinical sample

Abstract

Background

Results

Conclusion

2024 ASCO Annual Meeting

Springer Medicine

Abstract

Background

Results

Conclusion

Please log in to get access to this content

Other articles of this Issue 1/2020

Evaluation of evidence grades in psychiatry and psychotherapy guidelines

Attitudes towards psychopharmacology and psychotherapy in psychiatric patients with and without migration background

Empirical examination of executive functioning, ADHD associated behaviors, and functional impairments in adults with persistent ADHD, remittent ADHD, and without ADHD

The needs and service preferences of caregivers of youth with mental health and/or addictions concerns

Safety and efficacy of guanfacine extended-release in adults with attention-deficit/hyperactivity disorder: an open-label, long-term, phase 3 extension study

Service user and family participation in mental health policy making in Timor-Leste: a qualitative study with multiple stakeholders