An Approach for Data Mining of Electronic Health Record Data for Suicide Risk Management: Database Analysis for Clinical Decision Support

Sofian Berrouiguet; Romain Billot; Mark Erik Larsen; Jorge Lopez-Castroman; Isabelle Jaussent; Michel Walter; Philippe Lenca; Enrique Baca-García; Philippe Courtet

doi:10.2196/mental.9766

An Approach for Data Mining of Electronic Health Record Data for Suicide Risk Management: Database Analysis for Clinical Decision Support

JMIR Ment Health. 2019 May 7;6(5):e9766. doi: 10.2196/mental.9766.

Authors

Sofian Berrouiguet^{1

2

3

4}, Romain Billot⁴, Mark Erik Larsen^#⁵, Jorge Lopez-Castroman⁶, Isabelle Jaussent⁷, Michel Walter¹, Philippe Lenca⁴, Enrique Baca-García^{8

9

10

11

12

13

14}, Philippe Courtet^{7

10

11

15

16}

Affiliations

¹ Adult Psychiatry, Brest Medical University Hospital at Bohars, Brest, France.
² EA 7479 Soins Primaires, Santé Publique, Registre des Cancers de Bretagne Occidentale, Université de Bretagne Occidentale, Brest, France.
³ Mental Health Department, University Hospital of Brest, Brest, France.
⁴ F-29238, Laboratoire des Sciences et Techniques de l'information de la Communication et de la Connaissance, IMT Atlantique, Brest, France.
⁵ Black Dog Institute, University of New South Wales, Sydney, Australia.
⁶ Inserm U1061, Crisis Admission Center, University Hospital of Nîmes, Nîmes, France.
⁷ Inserm U1061, La Colombières Hospital, University of Montpellier, Montpellier, France.
⁸ Carlos III Institute Of Health, Centro de Investigation en Salud Mental, Madrid, Spain.
⁹ Department of Psychiatry, Universitad Catolica del Maule, Talca, Chile.
¹⁰ Department of Psychiatry, General Hospital of Villaba, Madrid, Spain.
¹¹ Department of Psychiatry, University Hospital Rey Juan Carlos, Mostoles, Spain.
¹² Department of Psychiatry, University Hospital Infanta Elena, Valdemoro, Spain.
¹³ Psychiatry Department, Universidad Autónoma de Madrid, Madrid, Spain.
¹⁴ Department of Psychiatry, Instituto de Investigación Sanitaria de la Fundación Jiménez Díaz, Madrid, Spain.
¹⁵ Department of Emergency Psychiatry and Acute Care, Centre Hospitalier Universitaire de Montpellier, Université Montpellier, Montpellier, France.
¹⁶ Fondamental Foundation, Créteil, France.

^# Contributed equally.

Abstract

Background: In an electronic health context, combining traditional structured clinical assessment methods and routine electronic health-based data capture may be a reliable method to build a dynamic clinical decision-support system (CDSS) for suicide prevention.

Objective: The aim of this study was to describe the data mining module of a Web-based CDSS and to identify suicide repetition risk in a sample of suicide attempters.

Methods: We analyzed a database of 2802 suicide attempters. Clustering methods were used to identify groups of similar patients, and regression trees were applied to estimate the number of suicide attempts among these patients.

Results: We identified 3 groups of patients using clustering methods. In addition, relevant risk factors explaining the number of suicide attempts were highlighted by regression trees.

Conclusions: Data mining techniques can help to identify different groups of patients at risk of suicide reattempt. The findings of this study can be combined with Web-based and smartphone-based data to improve dynamic decision making for clinicians.

Keywords: clinical decision support system; data mining; electronic health; mobile phone; prevention; suicide; suicide attempts.

©Sofian Berrouiguet, Romain Billot, Mark Erik Larsen, Jorge Lopez-Castroman, Isabelle Jaussent, Michel Walter, Philippe Lenca, Enrique Baca-García, Philippe Courtet. Originally published in JMIR Mental Health (http://mental.jmir.org), 07.05.2019.