Toward Automatic Risk Assessment to Support Suicide Prevention

Marios Adamou, Grigoris Antoniou, Elissavet Greasidou, Vincenzo Lagani, Paulos Charonyktakis, Ioannis Tsamardinos, Michael Doyle

Research output: Contribution to journalArticle

1 Citation (Scopus)
70 Downloads (Pure)

Abstract

Background: Suicide has been considered an important public health issue for years and is one of the main causes of death worldwide. Despite prevention strategies being applied, the rate of suicide has not changed substantially over the past decades. Suicide risk has proven extremely difficult to assess for medical specialists, and traditional methodologies deployed have been ineffective. Advances in machine learning make it possible to attempt to predict suicide with the analysis of relevant data aiming to inform clinical practice. Aims: We aimed to (a) test our artificial intelligence based, referral-centric methodology in the context of the National Health Service (NHS), (b) determine whether statistically relevant results can be derived from data related to previous suicides, and (c) develop ideas for various exploitation strategies. Method: The analysis used data of patients who died by suicide in the period 2013-2016 including both structured data and free-text medical notes, necessitating the deployment of state-of-the-art machine learning and text mining methods. Limitations: Sample size is a limiting factor for this study, along with the absence of non-suicide cases. Specific analytical solutions were adopted for addressing both issues. Results and Conclusion: The results of this pilot study indicate that machine learning shows promise for predicting within a specified period which people are most at risk of taking their own life at the time of referral to a mental health service.

Original languageEnglish
Pages (from-to)249-256
Number of pages8
JournalCrisis
Volume40
Issue number4
Early online date26 Nov 2018
DOIs
Publication statusPublished - Jul 2019

Fingerprint

Suicide
Referral and Consultation
Data Mining
Artificial Intelligence
National Health Programs
Mental Health Services
Risk-Taking
Sample Size
Cause of Death
Public Health
Machine Learning

Cite this

Adamou, M., Antoniou, G., Greasidou, E., Lagani, V., Charonyktakis, P., Tsamardinos, I., & Doyle, M. (2019). Toward Automatic Risk Assessment to Support Suicide Prevention. Crisis, 40(4), 249-256. https://doi.org/10.1027/0227-5910/a000561
Adamou, Marios ; Antoniou, Grigoris ; Greasidou, Elissavet ; Lagani, Vincenzo ; Charonyktakis, Paulos ; Tsamardinos, Ioannis ; Doyle, Michael. / Toward Automatic Risk Assessment to Support Suicide Prevention. In: Crisis. 2019 ; Vol. 40, No. 4. pp. 249-256.
@article{ee12c290d7094eba962596f7065af7af,
title = "Toward Automatic Risk Assessment to Support Suicide Prevention",
abstract = "Background: Suicide has been considered an important public health issue for years and is one of the main causes of death worldwide. Despite prevention strategies being applied, the rate of suicide has not changed substantially over the past decades. Suicide risk has proven extremely difficult to assess for medical specialists, and traditional methodologies deployed have been ineffective. Advances in machine learning make it possible to attempt to predict suicide with the analysis of relevant data aiming to inform clinical practice. Aims: We aimed to (a) test our artificial intelligence based, referral-centric methodology in the context of the National Health Service (NHS), (b) determine whether statistically relevant results can be derived from data related to previous suicides, and (c) develop ideas for various exploitation strategies. Method: The analysis used data of patients who died by suicide in the period 2013-2016 including both structured data and free-text medical notes, necessitating the deployment of state-of-the-art machine learning and text mining methods. Limitations: Sample size is a limiting factor for this study, along with the absence of non-suicide cases. Specific analytical solutions were adopted for addressing both issues. Results and Conclusion: The results of this pilot study indicate that machine learning shows promise for predicting within a specified period which people are most at risk of taking their own life at the time of referral to a mental health service.",
keywords = "Automated machine learning, Suicide prevention, Risk assessment, Clinical data, Text mining",
author = "Marios Adamou and Grigoris Antoniou and Elissavet Greasidou and Vincenzo Lagani and Paulos Charonyktakis and Ioannis Tsamardinos and Michael Doyle",
year = "2019",
month = "7",
doi = "10.1027/0227-5910/a000561",
language = "English",
volume = "40",
pages = "249--256",
journal = "Crisis",
issn = "0227-5910",
publisher = "Hogrefe Publishing",
number = "4",

}

Adamou, M, Antoniou, G, Greasidou, E, Lagani, V, Charonyktakis, P, Tsamardinos, I & Doyle, M 2019, 'Toward Automatic Risk Assessment to Support Suicide Prevention', Crisis, vol. 40, no. 4, pp. 249-256. https://doi.org/10.1027/0227-5910/a000561

Toward Automatic Risk Assessment to Support Suicide Prevention. / Adamou, Marios; Antoniou, Grigoris; Greasidou, Elissavet; Lagani, Vincenzo; Charonyktakis, Paulos ; Tsamardinos, Ioannis; Doyle, Michael.

In: Crisis, Vol. 40, No. 4, 07.2019, p. 249-256.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Toward Automatic Risk Assessment to Support Suicide Prevention

AU - Adamou, Marios

AU - Antoniou, Grigoris

AU - Greasidou, Elissavet

AU - Lagani, Vincenzo

AU - Charonyktakis, Paulos

AU - Tsamardinos, Ioannis

AU - Doyle, Michael

PY - 2019/7

Y1 - 2019/7

N2 - Background: Suicide has been considered an important public health issue for years and is one of the main causes of death worldwide. Despite prevention strategies being applied, the rate of suicide has not changed substantially over the past decades. Suicide risk has proven extremely difficult to assess for medical specialists, and traditional methodologies deployed have been ineffective. Advances in machine learning make it possible to attempt to predict suicide with the analysis of relevant data aiming to inform clinical practice. Aims: We aimed to (a) test our artificial intelligence based, referral-centric methodology in the context of the National Health Service (NHS), (b) determine whether statistically relevant results can be derived from data related to previous suicides, and (c) develop ideas for various exploitation strategies. Method: The analysis used data of patients who died by suicide in the period 2013-2016 including both structured data and free-text medical notes, necessitating the deployment of state-of-the-art machine learning and text mining methods. Limitations: Sample size is a limiting factor for this study, along with the absence of non-suicide cases. Specific analytical solutions were adopted for addressing both issues. Results and Conclusion: The results of this pilot study indicate that machine learning shows promise for predicting within a specified period which people are most at risk of taking their own life at the time of referral to a mental health service.

AB - Background: Suicide has been considered an important public health issue for years and is one of the main causes of death worldwide. Despite prevention strategies being applied, the rate of suicide has not changed substantially over the past decades. Suicide risk has proven extremely difficult to assess for medical specialists, and traditional methodologies deployed have been ineffective. Advances in machine learning make it possible to attempt to predict suicide with the analysis of relevant data aiming to inform clinical practice. Aims: We aimed to (a) test our artificial intelligence based, referral-centric methodology in the context of the National Health Service (NHS), (b) determine whether statistically relevant results can be derived from data related to previous suicides, and (c) develop ideas for various exploitation strategies. Method: The analysis used data of patients who died by suicide in the period 2013-2016 including both structured data and free-text medical notes, necessitating the deployment of state-of-the-art machine learning and text mining methods. Limitations: Sample size is a limiting factor for this study, along with the absence of non-suicide cases. Specific analytical solutions were adopted for addressing both issues. Results and Conclusion: The results of this pilot study indicate that machine learning shows promise for predicting within a specified period which people are most at risk of taking their own life at the time of referral to a mental health service.

KW - Automated machine learning

KW - Suicide prevention

KW - Risk assessment

KW - Clinical data

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=85057521353&partnerID=8YFLogxK

U2 - 10.1027/0227-5910/a000561

DO - 10.1027/0227-5910/a000561

M3 - Article

VL - 40

SP - 249

EP - 256

JO - Crisis

JF - Crisis

SN - 0227-5910

IS - 4

ER -

Adamou M, Antoniou G, Greasidou E, Lagani V, Charonyktakis P, Tsamardinos I et al. Toward Automatic Risk Assessment to Support Suicide Prevention. Crisis. 2019 Jul;40(4):249-256. https://doi.org/10.1027/0227-5910/a000561