JMIR Publications

ABSTRACT

Background:

Despite decades of research to better understand suicide risk and to develop detection and prevention methods, suicide is still one of the leading causes of death globally. While large-scale studies using real world evidence from electronic health records are able to identify who is at risk, they have not been successful at pinpointing when someone is at risk. Social media and search history could provide an on-going real-world stream of information about people’s states of mind.

Objective:

This study determines the feasibility and acceptability of using personalized online information seeking behavior in the identification of risk for suicide attempts.

Methods:

This was a cohort survey study to assess attitudes of participant with a prior suicide attempt about using search data for suicide prevention purposes, dates of lifetime suicide attempts and an optional one-time download of their past web searches on Google. The study was conducted at the University of Washington School of Medicine Psychiatry Research Offices. Main outcomes were participants’ opinions on internet search data for suicide prediction and intervention. Individualized non-parametric association analysis was used to to assess the magnitude of difference in web search data derived features proximal (7,15,30, and 60 days) to the suicide attempts and the typical (“baseline”) search behavior of participants.

Results:

Sixty-two participants who were suicide attempt survivors agreed to participate in the study. Internet search activity was variable from person to person (Median = 2-24 searches per day). Changes in online search behavior proximal to suicide attempts were evident up to 60 days before attempt. For a subset of attempts (N=7/30, 23.3%) search features showed association from 2 months to a week before the attempt. The top 3 search constructs associated with attempts were online searching patterns (9/30 attempts, 30%) and semantic relatedness of search queries to suicide methods (7/30 attempts, 23.3%) and anger (7/30 attempts, 23.3%). 68% of participants indicated that use of this personalized web search data for prevention purposes was acceptable with non-invasive potential interventions such as connection to a real person e.g. friend, family member or counselor. However, concerns were raised about detection accuracy, privacy and potential for overly invasive intervention.

Conclusions:

Changes in online search behavior may be a useful and acceptable means of detecting suicide risk. Personalized analysis of online information seeking behavior showed notable changes in search behavior and search terms that are tied to early warning signs of suicide and are evident two months to seven days before a suicide attempt.