Mining Free-Text Medical Notes for Suicide Risk Assessment

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Suicide has been considered as an important public health issue for a very long time, and is one of the main causes of death worldwide. Despite suicide prevention strategies being applied, the rate of suicide has not changed substantially over the past decades. Advances in machine learning make it possible to attempt to predict suicide based on the analysis of relevant data to inform clinical practice. This paper reports on findings from the analysis of data of patients who died by suicide in the period 2013-2016 and made use of both structured data and free-text medical notes. We focus on examining various text-mining approaches to support risk assessment. The results show that using advance machine learning and text-mining techniques, it is possible to predict 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
Title of host publicationProceedings - 10th Hellenic Conference on Artificial Intelligence, SETN 2018
Place of PublicationNew York, New York, USA
PublisherAssociation for Computing Machinery (ACM)
Number of pages8
ISBN (Electronic)9781450364331
ISBN (Print)9781450364331
DOIs
Publication statusPublished - 9 Jul 2018
Event10th Hellenic Conference on Artificial Intelligence - Patras, Greece
Duration: 9 Jul 201812 Jul 2018
Conference number: 10
http://setn2018.upatras.gr/ (Link to Conference Website)

Conference

Conference10th Hellenic Conference on Artificial Intelligence
Abbreviated titleSETN 2018
CountryGreece
CityPatras
Period9/07/1812/07/18
Internet address

Fingerprint

Risk assessment
Learning systems
Public health
Health

Cite this

Adamou, M., Antoniou, G., Greasidou, E., Lagani, V., Charonyktakis, P., & Tsamardinos, I. (2018). Mining Free-Text Medical Notes for Suicide Risk Assessment. In Proceedings - 10th Hellenic Conference on Artificial Intelligence, SETN 2018 [47] New York, New York, USA: Association for Computing Machinery (ACM). https://doi.org/10.1145/3200947.3201020
Adamou, Marios ; Antoniou, Grigoris ; Greasidou, Elissavet ; Lagani, Vincenzo ; Charonyktakis, Paulos ; Tsamardinos, Ioannis. / Mining Free-Text Medical Notes for Suicide Risk Assessment. Proceedings - 10th Hellenic Conference on Artificial Intelligence, SETN 2018. New York, New York, USA : Association for Computing Machinery (ACM), 2018.
@inproceedings{f2a317f6db2f44e3a3fe4715851f1243,
title = "Mining Free-Text Medical Notes for Suicide Risk Assessment",
abstract = "Suicide has been considered as an important public health issue for a very long time, and is one of the main causes of death worldwide. Despite suicide prevention strategies being applied, the rate of suicide has not changed substantially over the past decades. Advances in machine learning make it possible to attempt to predict suicide based on the analysis of relevant data to inform clinical practice. This paper reports on findings from the analysis of data of patients who died by suicide in the period 2013-2016 and made use of both structured data and free-text medical notes. We focus on examining various text-mining approaches to support risk assessment. The results show that using advance machine learning and text-mining techniques, it is possible to predict 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, Clinical data, Risk assessment tool, Suicide prevention, Text mining",
author = "Marios Adamou and Grigoris Antoniou and Elissavet Greasidou and Vincenzo Lagani and Paulos Charonyktakis and Ioannis Tsamardinos",
year = "2018",
month = "7",
day = "9",
doi = "10.1145/3200947.3201020",
language = "English",
isbn = "9781450364331",
booktitle = "Proceedings - 10th Hellenic Conference on Artificial Intelligence, SETN 2018",
publisher = "Association for Computing Machinery (ACM)",
address = "United States",

}

Adamou, M, Antoniou, G, Greasidou, E, Lagani, V, Charonyktakis, P & Tsamardinos, I 2018, Mining Free-Text Medical Notes for Suicide Risk Assessment. in Proceedings - 10th Hellenic Conference on Artificial Intelligence, SETN 2018., 47, Association for Computing Machinery (ACM), New York, New York, USA, 10th Hellenic Conference on Artificial Intelligence, Patras, Greece, 9/07/18. https://doi.org/10.1145/3200947.3201020

Mining Free-Text Medical Notes for Suicide Risk Assessment. / Adamou, Marios; Antoniou, Grigoris; Greasidou, Elissavet; Lagani, Vincenzo; Charonyktakis, Paulos; Tsamardinos, Ioannis.

Proceedings - 10th Hellenic Conference on Artificial Intelligence, SETN 2018. New York, New York, USA : Association for Computing Machinery (ACM), 2018. 47.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Mining Free-Text Medical Notes for Suicide Risk Assessment

AU - Adamou, Marios

AU - Antoniou, Grigoris

AU - Greasidou, Elissavet

AU - Lagani, Vincenzo

AU - Charonyktakis, Paulos

AU - Tsamardinos, Ioannis

PY - 2018/7/9

Y1 - 2018/7/9

N2 - Suicide has been considered as an important public health issue for a very long time, and is one of the main causes of death worldwide. Despite suicide prevention strategies being applied, the rate of suicide has not changed substantially over the past decades. Advances in machine learning make it possible to attempt to predict suicide based on the analysis of relevant data to inform clinical practice. This paper reports on findings from the analysis of data of patients who died by suicide in the period 2013-2016 and made use of both structured data and free-text medical notes. We focus on examining various text-mining approaches to support risk assessment. The results show that using advance machine learning and text-mining techniques, it is possible to predict 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 - Suicide has been considered as an important public health issue for a very long time, and is one of the main causes of death worldwide. Despite suicide prevention strategies being applied, the rate of suicide has not changed substantially over the past decades. Advances in machine learning make it possible to attempt to predict suicide based on the analysis of relevant data to inform clinical practice. This paper reports on findings from the analysis of data of patients who died by suicide in the period 2013-2016 and made use of both structured data and free-text medical notes. We focus on examining various text-mining approaches to support risk assessment. The results show that using advance machine learning and text-mining techniques, it is possible to predict 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 - Clinical data

KW - Risk assessment tool

KW - Suicide prevention

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=85052017170&partnerID=8YFLogxK

U2 - 10.1145/3200947.3201020

DO - 10.1145/3200947.3201020

M3 - Conference contribution

SN - 9781450364331

BT - Proceedings - 10th Hellenic Conference on Artificial Intelligence, SETN 2018

PB - Association for Computing Machinery (ACM)

CY - New York, New York, USA

ER -

Adamou M, Antoniou G, Greasidou E, Lagani V, Charonyktakis P, Tsamardinos I. Mining Free-Text Medical Notes for Suicide Risk Assessment. In Proceedings - 10th Hellenic Conference on Artificial Intelligence, SETN 2018. New York, New York, USA: Association for Computing Machinery (ACM). 2018. 47 https://doi.org/10.1145/3200947.3201020