Risk assessment tools and data-driven approaches for predicting and preventing suicidal behavior

Sumithra Velupillai; Gergö Hadlaczky; Enrique Baca-Garcia; Genevieve M. Gorrell; Nomi Werbeloff; Dong Nguyen; Rashmi Patel; Daniel Leightley; Johnny Downs; Matthew Hotopf; Rina Dutta

doi:10.3389/fpsyt.2019.00036

Risk assessment tools and data-driven approaches for predicting and preventing suicidal behavior

Sumithra Velupillai, Gergö Hadlaczky, Enrique Baca-Garcia, Genevieve M. Gorrell, Nomi Werbeloff, Dong Nguyen, Rashmi Patel, Daniel Leightley, Johnny Downs, Matthew Hotopf, Rina Dutta

Research output: Contribution to journal › Review article › peer-review

48 Scopus citations

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.

Original language	English
Article number	36
Journal	Frontiers in Psychiatry
Volume	10
Issue number	FEB
DOIs	https://doi.org/10.3389/fpsyt.2019.00036
State	Published - 2019
Externally published	Yes

Bibliographical note

Publisher Copyright:
Copyright © 2019 Velupillai, Hadlaczky, Baca-Garcia, Gorrell, Werbeloff, Nguyen, Patel, Leightley, Downs, Hotopf and Dutta. 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.

Funding

SV is supported by the Swedish Research Council (2015-00359) and the Marie Skłodowska Curie Actions, Cofund, Project INCA 600398. EB-G is partially supported by grants from Instituto de Salud Carlos III (ISCIII PI13/02200; PI16/01852), Delegación del Gobierno para el Plan Nacional de Drogas (20151073); American Foundation for Suicide Prevention (AFSP) (LSRG-1-005-16). NW is supported by the UCLH NIHR Biomedical Research Centre. DN is supported by The Alan Turing Institute under the EPSRC grant EP/N510129/1, with an Alan Turing Institute Fellowship (TU/A/000006). RP has received support from a Medical Research Council (MRC) Health Data Research UK Fellowship (MR/S003118/1) and a Starter Grant for Clinical Lecturers (SGL015/1020) supported by the Academy of Medical Sciences, The Wellcome Trust, MRC, SV and RD proposed the manuscript and its contents. All authors participated in the workshop The Interplay of Evaluating Information Extraction approaches and real-world Clinical Research that was held at the Institute of Psychiatry, Psychology and Neuroscience, King’s College London, April 27 2017, and financially supported by the European Science Foundation (ESF) Research Networking Programme Evaluating Information Access Systems: http://elias-network.eu/. SV and RD outlined the first draft of the manuscript. Each author contributed specifically to certain manuscript sections: GH on risk assessment tools, EB-G on data-driven methods, GG on NLP, NW, JD, and RP on NLP specifically for mental health, DN on explainability of data-driven methods, DL on deployment and real-world implications, MH on the overall manuscript. All authors contributed to editing and revising the manuscript. SV incorporated edits of the other authors. All authors approved the final version. This manuscript was written as a result of a workshop that was held at the Institute of Psychiatry, Psychology and Neuroscience, King's College London, financially supported by the European Science Foundation (ESF) Research Networking Programme Evaluating Information Access Systems: http://eliasnetwork.eu/. SV is supported by the Swedish Research Council (2015-00359) and the Marie Skłodowska Curie Actions, Cofund, Project INCA 600398. EB-G is partially supported by grants from Instituto de Salud Carlos III (ISCIII PI13/02200; PI16/01852), Delegación del Gobierno para el Plan Nacional de Drogas (20151073); American Foundation for Suicide Prevention (AFSP) (LSRG-1-005-16). NW is supported by the UCLH NIHR Biomedical Research Centre. DN is supported by The Alan Turing Institute under the EPSRC grant EP/N510129/1, with an Alan Turing Institute Fellowship (TU/A/000006). RP has received support from a Medical Research Council (MRC) Health Data Research UK Fellowship (MR/S003118/1) and a Starter Grant for Clinical Lecturers (SGL015/1020) supported by the Academy of Medical Sciences, The Wellcome Trust, MRC, British Heart Foundation, Arthritis Research UK, the Royal College of Physicians and Diabetes UK. DL is supported by the UK Medical Research Council under grant MR/N028244/2 and the King's Centre for Military Health Research. JD is supported by a Medical Research Council (MRC) Clinical Research Training Fellowship (MR/L017105/1). RD is funded by a Clinician Scientist Fellowship (research project e-HOST-IT) from the Health Foundation in partnership with the Academy of Medical Sciences. This paper represents independent research part funded by the National Institute for Health Research (NIHR) Biomedical Research Centre at South London and Maudsley NHS Foundation Trust and King's College London. The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health.

Funders	Funder number
Delegación del Gobierno para el Plan Nacional de Drogas	20151073
Health Data Research UK	SGL015/1020
American Foundation for Suicide Prevention	LSRG-1-005-16
King’s College London
Wellcome Trust
Seventh Framework Programme	600398
Alan Turing Institute
Medical Research Council	MR/S003118/1
Engineering and Physical Sciences Research Council	TU/A/000006, EP/N510129/1
Marie Curie	INCA 600398
Academy of Medical Sciences
European Science Foundation
Vetenskapsrådet	2015-00359
Instituto de Salud Carlos III	PI13/02200, PI16/01852
Medical Research Council Canada	MR/L017105/1, MR/N028244/2
UCLH Biomedical Research Centre

Keywords

Clinical informatics
Machine learning
Natural language processing
Suicidality
Suicide risk assessment
Suicide risk prediction

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.3389/fpsyt.2019.00036

Cite this

@article{3f01d5e014c24d78a517ce1a305ab930,

title = "Risk assessment tools and data-driven approaches for predicting and preventing suicidal behavior",

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 = "Clinical informatics, Machine learning, Natural language processing, Suicidality, Suicide risk assessment, Suicide risk prediction",

author = "Sumithra Velupillai and Gerg{\"o} Hadlaczky and Enrique Baca-Garcia and Gorrell, {Genevieve M.} and Nomi Werbeloff and Dong Nguyen and Rashmi Patel and Daniel Leightley and Johnny Downs and Matthew Hotopf and Rina Dutta",

note = "Publisher Copyright: Copyright {\textcopyright} 2019 Velupillai, Hadlaczky, Baca-Garcia, Gorrell, Werbeloff, Nguyen, Patel, Leightley, Downs, Hotopf and Dutta. 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.",

year = "2019",

doi = "10.3389/fpsyt.2019.00036",

language = "אנגלית",

volume = "10",

journal = "Frontiers in Psychiatry",

issn = "1664-0640",

publisher = "Frontiers Media S.A.",

number = "FEB",

}

TY - JOUR

T1 - Risk assessment tools and data-driven approaches for predicting and preventing suicidal behavior

AU - Velupillai, Sumithra

AU - Hadlaczky, Gergö

AU - Baca-Garcia, Enrique

AU - Gorrell, Genevieve M.

AU - Werbeloff, Nomi

AU - Nguyen, Dong

AU - Patel, Rashmi

AU - Leightley, Daniel

AU - Downs, Johnny

AU - Hotopf, Matthew

AU - Dutta, Rina

N1 - Publisher Copyright: Copyright © 2019 Velupillai, Hadlaczky, Baca-Garcia, Gorrell, Werbeloff, Nguyen, Patel, Leightley, Downs, Hotopf and Dutta. 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.

PY - 2019

Y1 - 2019

N2 - 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.

AB - 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.

KW - Clinical informatics

KW - Machine learning

KW - Natural language processing

KW - Suicidality

KW - Suicide risk assessment

KW - Suicide risk prediction

UR - http://www.scopus.com/inward/record.url?scp=85062732148&partnerID=8YFLogxK

U2 - 10.3389/fpsyt.2019.00036

DO - 10.3389/fpsyt.2019.00036

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.systematicreview???

C2 - 30814958

AN - SCOPUS:85062732148

SN - 1664-0640

VL - 10

JO - Frontiers in Psychiatry

JF - Frontiers in Psychiatry

IS - FEB

M1 - 36

ER -

Risk assessment tools and data-driven approaches for predicting and preventing suicidal behavior

Abstract

Bibliographical note

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this