Suicide is a prominent cause of death worldwide, particularly among young people. It occurs throughout the lifespan and was the fourth leading cause of death among 15-19 year-olds globally in 2019.
Suicide prevention guidelines recommend safety planning alongside follow-up treatment by mental health services for those at-risk of suicide. Safety planning and other evidence-based psychological interventions involve maintaining and updating paper-based records or worksheets in between sessions. Insight researchers have found that mobile technology can offer a way to support the implementation of evidence-based psychological techniques and the acquisition of protective coping skills.
SafePlan is a mobile app, developed by a team led by Insight FI, Professor Jim Duggan with the support of the HSE National Office for Suicide Prevention. The app aims to facilitate service users to access their safety plan when they need it and in-situ. The development process involved eliciting expert input from clinicians who are actively engaged in the provision of mental health care. The project is an integral part of the Connecting for Life Suicide Prevention Action Plan 2022-2024 for HSE Community Healthcare West. You can read about the app development process here.
So how does it work from a data science perspective? Annual suicide figures are critical in identifying trends and guiding research, yet challenges arising from significant lags in reporting can delay and complicate real-time interventions. In a parallel project, Prof. Duggan and the SafePlan team utilized Google Trends search volumes for behavioural forecasting of national suicide rates in Ireland between 2004 and 2015.
Official suicide rates are recorded by the Central Statistics Office in Ireland. While similar investigations using Google trends data have been carried out in other jurisdictions like the United Kingdom and the United States of America, similar research had not yet been completed in Ireland.
The team compiled a collection of suicide- and depression-related search terms suggested by Google Trends and manually sourced from the literature. Monthly search rate terms at different lags were compared with suicide occurrences to determine the degree of correlation. Their findings supported the findings in other countries that there is real benefit in using Google Trends, the neural network approach, and the applied search terms to forecast suicide risk increase.
Overall, the combination of societal data and online behaviour provides a good indication of societal risks; building on past research, the team’s improvements led to robust models integrating search query and unemployment data for suicide risk forecasting in Ireland. You can read more about that here.
For more information on mental health supports and services, see: www.yourmentalhealth.ie
The SafePlan Team includes researchers from Insight at the University of Galway and the University’s School of Computer Science (Jim Duggan, Karen Young and Hamda Ajmal), the School of Psychology at the University of Galway (John Bogue), and the Health Service Executive (Ruth Melia and Mary O’Sullivan).