Prädiktion suizidalen Verhaltens

ZUSAMMENFASSUNG

Eine Vorhersage suizidalen Verhaltens ist nicht sicher möglich. Frühe Arbeiten zeigen genauso wie aktuelle Metaanalysen, dass weder das klinische Urteil noch Risikoskalen und Fragebögen eine zufriedenstellende Vorhersage suizidalen Verhaltens erlauben. Gründe für die unzureichende Prädiktion werden erläutert und Chancen sowie Grenzen der Anwendung künstlicher Intelligenz werden reflektiert. Abschließend wird hervorgehoben, dass Suizidprävention möglich ist, auch wenn sichere Suizidprädiktion nicht möglich ist.

ABSTRACT

Prediction of suicidal behavior is not possible with certainty. Early studies as well as recent meta-analyses show that neither clinical judgment nor risk scales and questionnaires allow a satisfactory prediction of suicidal behavior. Reasons for the imprecise prediction are explained and opportunities as well as limitations of the application of artificial intelligence are considered. Finally, it is emphasized that suicide prevention is possible even though suicide prediction is not.

Schlüsselwörter

Suizidalität - Risikoabschätzung - künstliche Intelligenz - maschinelles Lernen

Key words

Suicidality - risk assessment - artificial intelligence - machine learning

Publication History

Article published online:
04 April 2022

• Literatur

• 1 Nock MK, Borges G, Ono Y. Suicide. Global perspectives from the WHO World Mental Health Survey.. Cambridge: University Press, Cambridge; 2012
• 2 Statistisches Bundesamt. Todesursachenstatistik 2021 http://www.destatis.de
• 3 Franklin JC, Ribeiro JD, Fox KR. et al Risk factors for suicidal thoughts and behaviors.. Psychol Bull 2017; 143: 187-232
• 4 Teismann T, Koban C, Illes F. et al Psychotherapie suizidaler Patienten.. Göttingen: Hogrefe; 2016
• 5 Chu C, Klein KM, Buchman-Schmitt JM. et al Routinized assessment of suicide risk in clinical practice: an empirically informed update.. J Clin Psychol 2015; 71: 1186-1200
• 6 Paterson B, Dowding D, Harries C. et al Managing the risk of suicide in acute psychiatric inpatients: a clinical judgement analysis of staff predictions of imminent suicide risk.. J Ment Health 2008; 17: 410-423
• 7 Woodford R, Spittal MJ, Milner A. et al Accuracy of clinician predictions of future self-harm: a systematic review and meta-analysis of predictive studies.. Suicide Life-Threat 2019; 49: 23-40
• 8 Rosen A. Detection of suicidal patients: An example of some limitations in the prediction of infrequent events.. J Consult Psychol 1954; 18: 397-403
• 9 Meehl PE. Clinical versus statistical prediction: A theoretical analysis and a review of the evidence.. Boston: University of Minnesota Press; 1954
• 10 Carter G, Milner A, McGill K. et al Predicting suicidal behaviours usinc clinical instruments: systematic review and meta-analysis of positive predictive values for risk scales.. Br J Psychiatry 2017; 210: 387-395
• 11 Steeg S, Quinlivan L, Nowland R. et al Accuracy of risk scales for predicting repeat self-harm and suicide: a multicenter, population-level cohort study using routine clinical data.. BMC Psychiat 2018; 18: 113
• 12 Simon GE, Rutter CM, Peterson D. et al Does response on the PHQ-9 Depression Questionnaire predict subsequent suicide attempt or suicide death?. Psychiatr Serv 2013; 64: 1195-202
• 13 Bryan C. Rethinking suicide.. New York: Oxford University Press; 2021
• 14 Franklin JC.. After decades of research, science is no better able to predict suicidal behavior.. 2016 https://www.apa.org/news/press/releases/2016/11/suicidal-behaviors
• 15 Chu C, Buchman-Schmitt JM, Stanley ICH. et al The interpersonal theory of suicide. A systematic review and meta-analysis of a decade of cross-national research.. Psychol Bull 2017; 143: 1313-1345
• 16 Yaseen ZS, Hawes M, Barzilay S. et al Predictive validity of proposed diagnostic criteria for the suicide crisis syndrome: an acute presuicidal state.. Suicid Life-Threat Behav 2019; 49: 1124-1135
• 17 Rath D, Teismann T, Schmitz F. et al Predicting suicidal behavior by implicit associations with death? Examination of the death IAT in two inpatient samples of differing suicide risk.. Psychol Assess 2021; 33: 287-299
• 18 Deming CA, Harris JA, Castro-Ramirez F. et al Inconsistencies in self-reports of suicidal ideation and attempts across assessment methods.. Psychol Assess 2021; 33: 218-229
• 19 Hallensleben N, Glaesmer H, Forkmann T. et al Predicting suicidal ideation by interpersonal variables, hopelessness and depression in real-time. An ecological momentary assessment study in psychiatric inpatients with depression.. European Psychiat 2019; 56: 43-50
• 20 Paashaus L, Forkmann T, Glaesmer H. et al From decision to action: suicidal history and time between decision to die and actual suicide attempt.. Clin Psychol Psychother 2021; 28: 1427-1434
• 21 Wastler HM, Bryan AO, Bryan CJ.. Suicide attempts among adults denying active suicidal ideation: An examination of the relationship between suicidal thought content and suicidal behavior.. J Clin Psychol 2021
• 22 Huang X, Ribeiro JD, Franklin JC. The differences between suicide ideators and suicide attempters: Simple, complicated, or complex?. J Consult Clin Psychol 2020; 88: 554-569
• 23 Teismann T, Forkmann T, Glaesmer H. Risikoabschätzung bei suizidalen Patienten – Geht das überhaupt?. Verhaltenstherapie 2019; 29: 80-84
• 24 Teismann T. Wannemüller, A. „Ich habe da ein schlechtes Gefühl!“ Intuition im Umgang mit suizidalen Patienten.. Suizidprophylaxe 2020; 47: 49-52
• 25 Sels L, Homan S, Ries A. et al SIMON: A digital protocol to monitor and predict suicidal ideation.. Front Psychiatry 2021; 12: 554811
• 26 Bernert RA, Hilberg AM, Melia R. et al Artificial intelligence and suicide prevention: A systematic review of machine learning investigations.. Int J Environ Res Public Health 2020; 17: 5929
• 27 Ophir Y, Tikochinski R, Brunstein Klomek A. et al The hitchhiker’s guide to computational linguistics in suicide prevention.. Clin Psychol Sci 2021
• 28 Ribeiro J, Huang X, Fox KR. et al Predicting imminent suicidal thoughts and nonfatal attempts: the role of complexity.. Clin Psychol Sci 2019; 07: 941-957
• 29 Belsher BE, Smolenski DJ, Prutt LD. et al Prediction models for suicide attempts and deaths: a systematic review and simulation.. JAMA Psychiat 2019; 76: 642-651
• 30 Fazel S, Wolf A, Larsson H. et al The prediction of suicide in severe mental illness: development and validation of a clinical prediction rule (OxMIS).. Trans Psychiat 2019; 09: 98
• 31 Mishara BL, Bardon C, Dupont S. Can CCTV identify people in public transit stations who are at risk of attempting suicide? An analysis of CCTV video recordings of attempters and a comparative investigation.. BMC Pub Health 2016; 16: 1245
• 32 Gomes de Andrade N, Pawson D, Muriello D. et al Ethics and artificial intelligence: Suicide prevention on Facebook.. Philos Technol 2018; 31: 669-684
• 33 O’Dea B, Wan S, Batterham P. et al Detecting suicidality on Twitter. Internet Interventions. 2015
• 34 Teismann T, Glasow N.. Means Restriction: Suizidprävention durch Zugangsbeschränkung. In: Teismann T, et al. (Hrsg.) Suizidales Erleben und Verhalten. Ein Handbuch.. Köln: Psychiatrie-Verlag; 2021: 212-23
• 35 Teismann T.. Gysin-Maillart. Psychotherapie nach einem Suizidversuch – Evidenzlage und Bewertung. Bundesgesundheitsblatt. 2021
• 36 Nuij C, van Ballegooijen W, de Beurs D. et al Safety planning type interventions for suicide prevention: meta-analysis.. Br J Psychiaty 2021
• 37 Machado D, Williamson E, Pescarini J. et al The impact of a national cash transfer programme on reducing suicide: A study using the 100 million Brazilian cohort. SSRN Electronic Journal. 2021