Perceived Utility and Characterization of Personal Google Search Histories to Detect Data Patterns Proximal to a Suicide Attempt in Individuals Who Previously Attempted Suicide: Pilot Cohort Study

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 can identify who is at risk, they have not been successful at pinpointing when someone is at risk. Personalized social media and online search history data, by contrast, could provide an ongoing real-world datastream revealing internal thoughts and personal states of mind. Objective We conducted this study to determine 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 participants with a prior suicide attempt about using web 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. The main outcomes were participants’ opinions on internet search data for suicide prediction and intervention and any potential change in online information-seeking behavior proximal to a suicide attempt. Individualized nonparametric association analysis was used to assess the magnitude of difference in web search data features derived from time periods proximal (7, 15, 30, and 60 days) to the suicide attempts versus the typical (baseline) search behavior of participants. Results A total of 62 participants who had attempted suicide in the past agreed to participate in the study. Internet search activity varied 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 (7/30, 23%) search features showed associations 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%), semantic relatedness of search queries to suicide methods (7/30 attempts, 23%), and anger (7/30 attempts, 23%). Participants (40/59, 68%) indicated that use of this personalized web search data for prevention purposes was acceptable with noninvasive potential interventions such as connection to a real person (eg, friend, family member, or counselor); however, concerns were raised about detection accuracy, privacy, and the 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 2 months to 7 days before a suicide attempt.

Profiling the Digital Mosaic of Uncensored Suicidal Thought and Behavior: A Theory-Driven Network Analysis of Online Written Expression

“…This theme is likely unique to the digital environment of Sanctioned Suicide as it is only possible to detect within a setting boasting a combination of minimal censorship and maximal anonymity. While there are no known studies which have addressed this association explicitly, the finding is supported by research on search behaviors of at-risk individuals (Areán et al, 2021;Harris et al, 2009;Kemp & Collings, 2011). There is evidence that STB-related online activity is elevated in those who report greater STB risk-related symptoms, have perceptions of decreased social support, and are less likely to engage in helpseeking behaviors, leading to a greater propensity for individuals to visit "pro-suicide" sites and search for suicide methods relative to others at-risk who do not utilize the internet for STBrelated purposes (Harris et al, 2009).…”

Behavioral Activation and Depression Symptomatology: Longitudinal Assessment of Linguistic Indicators in Text-Based Therapy Sessions

“…An important factor to consider when proposing such automated analyses is the degree to which passive monitoring of therapist-client communication for the purpose of measuring BA may be construed as invasive or intrusive. While we did not directly engage with patients in the current work, we note that our recent work in the suicide prevention domain provides some indication that passive monitoring of this sort may be acceptable to patients when conducted by a trusted party, with 68% of survey participants indicating that the automated analysis of personalized web search data for suicide prevention would be acceptable provided this triggered minimally invasive interventions (such as connection to a support network or therapist) only [ 48 ].…”

Artificial Intelligence: An Interprofessional Perspective on Implications for Geriatric Mental Health Research and Care

“…Thus, understanding and preventing the root causes for bias in AI systems must be a priority to monitor and mitigate such consequences. Privacy concerns among users of various technology-based assessments and interventions has also been a central theme arising in research from our group (54)(55)(56). Trust may vary as a function of who is conducting the research-for example, trust in internetbased research is higher (and participants more likely to share their data) when the research is conducted by university researchers compared to private companies (55).…”