Frontiers in Psychiatry (Feb 2019)
Risk Assessment Tools and Data-Driven Approaches for Predicting and Preventing Suicidal Behavior
- Sumithra Velupillai,
- Sumithra Velupillai,
- Sumithra Velupillai,
- Gergö Hadlaczky,
- Gergö Hadlaczky,
- Enrique Baca-Garcia,
- Enrique Baca-Garcia,
- Enrique Baca-Garcia,
- Enrique Baca-Garcia,
- Enrique Baca-Garcia,
- Enrique Baca-Garcia,
- Enrique Baca-Garcia,
- Genevieve M. Gorrell,
- Nomi Werbeloff,
- Dong Nguyen,
- Dong Nguyen,
- Rashmi Patel,
- Rashmi Patel,
- Daniel Leightley,
- Johnny Downs,
- Johnny Downs,
- Matthew Hotopf,
- Matthew Hotopf,
- Rina Dutta,
- Rina Dutta
Affiliations
- Sumithra Velupillai
- Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom
- Sumithra Velupillai
- School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden
- Sumithra Velupillai
- South London and Maudsley NHS Foundation Trust, London, United Kingdom
- Gergö Hadlaczky
- National Center for Suicide Research and Prevention (NASP), Department of Learning, Informatics, Management and Ethics (LIME), Karolinska Institutet, Stockholm, Sweden
- Gergö Hadlaczky
- National Center for Suicide Research and Prevention (NASP), Centre for Health Economics, Informatics and Health Services Research (CHIS), Stockholm Health Care Services (SLSO), Stockholm, Sweden
- Enrique Baca-Garcia
- Department of Psychiatry, IIS-Jimenez Diaz Foundation, Madrid, Spain
- Enrique Baca-Garcia
- Department of Psychiatry, Autonoma University, Madrid, Spain
- Enrique Baca-Garcia
- Department of Psychiatry, General Hospital of Villalba, Madrid, Spain
- Enrique Baca-Garcia
- CIBERSAM, Carlos III Institute of Health, Madrid, Spain
- Enrique Baca-Garcia
- 0Department of Psychiatry, University Hospital Rey Juan Carlos, Móstoles, Spain
- Enrique Baca-Garcia
- 1Department of Psychiatry, University Hospital Infanta Elena, Valdemoro, Spain
- Enrique Baca-Garcia
- 2Department of Psychiatry, Universidad Católica del Maule, Talca, Chile
- Genevieve M. Gorrell
- 3Department of Computer Science, University of Sheffield, Sheffield, United Kingdom
- Nomi Werbeloff
- 4Division of Psychiatry, University College London, London, United Kingdom
- Dong Nguyen
- 5Alan Turing Institute, London, United Kingdom
- Dong Nguyen
- 6School of Informatics, University of Edinburgh, Edinburgh, United Kingdom
- Rashmi Patel
- Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom
- Rashmi Patel
- South London and Maudsley NHS Foundation Trust, London, United Kingdom
- Daniel Leightley
- Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom
- Johnny Downs
- Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom
- Johnny Downs
- South London and Maudsley NHS Foundation Trust, London, United Kingdom
- Matthew Hotopf
- Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom
- Matthew Hotopf
- South London and Maudsley NHS Foundation Trust, London, United Kingdom
- Rina Dutta
- Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom
- Rina Dutta
- South London and Maudsley NHS Foundation Trust, London, United Kingdom
- DOI
- https://doi.org/10.3389/fpsyt.2019.00036
- Journal volume & issue
-
Vol. 10
Abstract
Risk assessment of suicidal behavior is a time-consuming but notoriously inaccurate activity for mental health services globally. In the last 50 years a large number of tools have been designed for suicide risk assessment, and tested in a wide variety of populations, but studies show that these tools suffer from low positive predictive values. More recently, advances in research fields such as machine learning and natural language processing applied on large datasets have shown promising results for health care, and may enable an important shift in advancing precision medicine. In this conceptual review, we discuss established risk assessment tools and examples of novel data-driven approaches that have been used for identification of suicidal behavior and risk. We provide a perspective on the strengths and weaknesses of these applications to mental health-related data, and suggest research directions to enable improvement in clinical practice.
Keywords
- suicide risk prediction
- suicidality
- suicide risk assessment
- clinical informatics
- machine learning
- natural language processing