Open Access Highly Accessed Open Badges Research article

Risk stratification using data from electronic medical records better predicts suicide risks than clinician assessments

Truyen Tran12, Wei Luo1, Dinh Phung1, Richard Harvey34, Michael Berk4567, Richard Lee Kennedy45 and Svetha Venkatesh1*

Author Affiliations

1 Centre for Pattern Recognition and Data Analytics, Deakin University, Geelong 3220, Australia

2 Department of Computing, Curtin University, Bentley, Australia

3 Mental Health Services, Barwon Health, Geelong, Australia

4 School of Medicine, Deakin University, Geelong, Australia

5 Barwon Health, Geelong, Australia

6 Mental Health Research Institute, University of Melbourne, Parkville, Australia

7 Orygen Youth Health Research Centre, Parkville, Australia

For all author emails, please log on.

BMC Psychiatry 2014, 14:76  doi:10.1186/1471-244X-14-76

Published: 14 March 2014



To date, our ability to accurately identify patients at high risk from suicidal behaviour, and thus to target interventions, has been fairly limited. This study examined a large pool of factors that are potentially associated with suicide risk from the comprehensive electronic medical record (EMR) and to derive a predictive model for 1–6 month risk.


7,399 patients undergoing suicide risk assessment were followed up for 180 days. The dataset was divided into a derivation and validation cohorts of 4,911 and 2,488 respectively. Clinicians used an 18-point checklist of known risk factors to divide patients into low, medium, or high risk. Their predictive ability was compared with a risk stratification model derived from the EMR data. The model was based on the continuation-ratio ordinal regression method coupled with lasso (which stands for least absolute shrinkage and selection operator).


In the year prior to suicide assessment, 66.8% of patients attended the emergency department (ED) and 41.8% had at least one hospital admission. Administrative and demographic data, along with information on prior self-harm episodes, as well as mental and physical health diagnoses were predictive of high-risk suicidal behaviour. Clinicians using the 18-point checklist were relatively poor in predicting patients at high-risk in 3 months (AUC 0.58, 95% CIs: 0.50 – 0.66). The model derived EMR was superior (AUC 0.79, 95% CIs: 0.72 – 0.84). At specificity of 0.72 (95% CIs: 0.70-0.73) the EMR model had sensitivity of 0.70 (95% CIs: 0.56-0.83).


Predictive models applied to data from the EMR could improve risk stratification of patients presenting with potential suicidal behaviour. The predictive factors include known risks for suicide, but also other information relating to general health and health service utilisation.

Suicide risk; Electronic medical record; Predictive models