Lasse Bosse Sander
Lena Spangenberg
Louise La Sala
Wouter Van Ballegooijen- 1Medical Psychology and Medical Sociology, Faculty of Medicine, University of Freiburg, Freiburg, Germany
- 2Department of Medical Psychology and Medical Sociology, Leipzig University, Leipzig, Germany
- 3Orygen, Centre for Youth Mental Health, University of Melbourne, Parkville, VIC, Australia
- 4Department of Clinical, Neuro and Developmental Psychology & Department of Psychiatry, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, Netherlands
Editorial on the Research Topic
Digital Suicide Prevention
Suicide is a major public health concern and a leading cause of death in young people around the world, with a global mortality rate of over 700,000 people per year (1). Despite advances in mental health care and suicide prevention efforts, suicide rates continue to be high (1). In addition, the ability to predict suicides has not progressed in the last five decades of research, also because studies repeatedly investigated the same set of potential risk factors in most trials and used assessments, which do not adequately take the complexity of suicidality into account (2). Suicidal ideation is a complex condition that can manifest both within and outside of various mental health and physical health disorders (3–6). Furthermore, the fluctuation of suicidal ideation and associated risk factors within hours or days necessitate more precise and detailed assessments (7, 8). Thus, to make progress in suicide research, multiple underlying processes or mechanisms may need to be investigated.
The digital era has brought a range of opportunities and methodological advances for comprehending, predicting, and averting suicidal behaviour. Ecological Momentary Assessment (EMA) allows for the timely identification of suicidal ideation and potentially related risk factors in a naturalistic setting (9). The utilization of machine learning techniques presents a unique approach for the analysis of intricate datasets (10). Furthermore, digital technologies can provide access to support and information, allow for early identification and intervention, and facilitate data-driven approaches to suicide prevention (11–15).
This Research Topic, Digital Suicide Prevention, has brought together seven articles that explore the potential of digital technologies to reduce suicide-related harm from a range of international experts.
In one study, Cohen et al. evaluate the performance of a machine learning suicide risk prediction model in the emergency department setting. The results show that the language-based suicide risk model performed with good discrimination in an external validation set.
A second study (Janssen et al.) explores whether motivational interviewing is an improvement over the five-phase model for a chat-based suicide-prevention helpline. The authors conclude that motivational interviewing adds more structure but does not seem to be associated with greater symptom reductions. Several next steps to improve in this field are described.
Three articles deal with different aspects of the use of EMA in suicide research. Based on the widespread use of smartphones and immense technological advancements, the number and quality of EMA studies has greatly increased during the last decade. Kivelä et al. review the current evidence on EMA in suicide research highlighting main findings (i.e., fluctuation of suicide ideation, general feasibility of EMA) and open questions (i.e., balancing study design and ethical/ safety issues). Ernst et al. present a study protocol for a study investigating the transdiagnostic risk and resilience factors associated with suicidal ideation using EMA. Brüdern et al. introduce the dual-system model of suicidality, which takes new directions to conceptualize suicidality and advertise EMAs as a well-suited methodological approach to investigate the proposed processes in detail.
In another study, Benson et al. present a dashboard prototype for real-time suicide mortality data using a dataset from the Suicide Support and Information System in Southern Ireland. This intuitive interface integrates a cluster detection approach and demonstrates real-world applicability as a proactive monitoring tool for timely action in suicide prevention.
Finally, Hopkins et al. review the use of machine learning prediction models in structured (human interpretable such as psychometric instruments) vs. unstructured (only machine interpretable such as electronic health records) datasets. The meta-analysis indicates that structured data and unstructured data showed similar outcome accuracy, despite different levels of data organization and specificity regarding the outcome of suicide risk prediction.
The articles in this Research Topic provide valuable insights into the potential of digital technologies to aid in understanding suicide and suicide prevention initiatives. The content of the articles reflects a diverse range of digital suicide prevention techniques, including but not limited to EMA, crisis chat services, and machine learning algorithms. Yet, it shows that each of these facets is only just developing and has a long way ahead to reach its full potential. Digital technologies can be quickly adapted to changing contexts and have the potential to reach large numbers of people. Online or app-based support might even reach those who are reluctant to seek help or those who cannot easily find mental healthcare. However, these technologies must be developed in an ethical and responsible way, with due consideration of the potential harms that may arise from the use of digital technologies (16). All authors critically discuss current boundaries and potential barriers related to the use of digital technologies and point out the next challenges for the field. We would like to thank the authors for their contributions to this Research Topic, and we look forward to engaging in further dialogue and collaboration on this important topic.
Author contributions
LBS wrote the first draft of this manuscript. All authors contributed to the article and approved the submitted version.
Conflict of interest
LBS was received research grants from the German Research Foundation, the German Joint Federal Committee innovation funds and the German Academic Exchange Service and received personal fees from psychotherapy training institutes, clinic providers and the German pension fund, which were not related to the submitted work. LS has received research grants from the German Research Foundation. LLS is funded by a Postdoctoral Fellowship from Suicide Prevention Australia. The remaining author declares that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Publisher's note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.
References
1. World Health Organization. World mental health report: Transforming mental health for all. Geneva: World Health Organization (2022).
2. 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) 143:187–232. doi: 10.1037/bul0000084
3. Millner AJ, Robinaugh DJ, Nock MK. Advancing the understanding of suicide: the need for formal theory and rigorous descriptive research. Trends Cogn Sci. (2020) 24:704–16. doi: 10.1016/j.tics.2020.06.007
4. Nock MK, Hwang I, Sampson NA, Kessler RC. Mental disorders, comorbidity and suicidal behavior: results from the national comorbidity survey replication. Mol Psychiatry. (2010) 15:868–76. doi: 10.1038/mp.2009.29
5. Goodwin RD, Kroenke K, Hoven CW, Spitzer RL. Major depression, physical illness, and suicidal ideation in primary care. Psychosom Med. (2003) 65:501–5. doi: 10.1097/01.PSY.0000041544.14277.EC
6. Scott KM, Hwang I, Chiu W-T, Kessler RC, Sampson NA, Angermeyer M, et al. Chronic physical conditions and their association with first onset of suicidal behavior in the world mental health surveys. Psychosom Med. (2010) 72:712–9. doi: 10.1097/PSY.0b013e3181e3333d
7. Bryan CJ, Rozek DC, Butner J, Rudd MD. Patterns of change in suicide ideation signal the recurrence of suicide attempts among high-risk psychiatric outpatients. Behav Res Ther. (2019) 120:103392. doi: 10.1016/j.brat.2019.04.001
8. Hallensleben N, Glaesmer H, Forkmann T, Rath D, Strauss M, Kersting A, et al. Predicting suicidal ideation by interpersonal variables, hopelessness and depression in real-time. An ecological momentary assessment study in psychiatric inpatients with depression. Eur Psychiatry. (2019) 56:43–50. doi: 10.1016/j.eurpsy.2018.11.003
9. Shiffman S, Stone AA, Hufford MR. Ecological momentary assessment. Annu Rev Clin Psychol. (2008) 4:1–32. doi: 10.1146/ANNUREV.CLINPSY.3.022806.091415
10. Linthicum KP, Schafer KM, Ribeiro JD. Machine learning in suicide science: applications and ethics. Behav Sci Law. (2019) 37:214–22. doi: 10.1002/bsl.2392
11. Büscher R, Beisemann M, Doebler P, Micklitz HM, Kerkhof A, Cuijpers P, et al. Digital cognitive–behavioural therapy to reduce suicidal ideation and behaviours: a systematic review and meta-analysis of individual participant data. Evid Based Mental Health. (2022) 25:e8–e17. doi: 10.1136/ebmental-2022-300540
12. Sels L, Homan S, Ries A, Santhanam P, Scheerer H, Colla M, et al. SIMON: a digital protocol to monitor and predict suicidal ideation. Front Psychiatry. (2021) 12:1–11. doi: 10.3389/fpsyt.2021.554811
13. Torous J, Larsen ME, Depp C, Cosco TD, Barnett I, Nock MK, et al. Smartphones, sensors, and machine learning to advance real-time prediction and interventions for suicide prevention: a review of current progress and next steps. Curr Psychiatry Rep. (2018) 20:51–7. doi: 10.1007/s11920-018-0914-y
14. Sander LB, Lemor M-L, van der Sloot RJA, de Jaegere E, Büscher R, Messner E-M, et al. A systematic evaluation of Mobile health applications for the prevention of suicidal behavior or non-suicidal self-injury. Front Digit Health. (2021) 3:1–10. doi: 10.3389/fdgth.2021.689692
15. la Sala L, Teh Z, Lamblin M, Rajaram G, Rice S, Hill NTM, et al. Can a social media intervention improve online communication about suicide? A feasibility study examining the acceptability and potential impact of the #chatsafe campaign. PLoS One. (2021) 16:e0253278. doi: 10.1371/journal.pone.0253278
Keywords: suicide, ecological momentary assessment (EMA), prevention, prediction, technology
Citation: Sander LB, Spangenberg L, La Sala L and Van Ballegooijen W (2023) Editorial: Digital suicide prevention. Front. Digit. Health 5:1148356. doi: 10.3389/fdgth.2023.1148356
Received: 20 January 2023; Accepted: 3 February 2023;
Published: 3 March 2023.
Edited by:
Heleen Riper, VU Amsterdam, Netherlands© 2023 Sander, Spangenberg, La Sala and Van Ballegooijen. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: Lasse Bosse Sander lasse.sander@mps.uni-freiburg.de
Specialty Section: This article was submitted to Digital Mental Health, a section of the journal Frontiers in Digital Health