JMIR Publications

ABSTRACT

Background:

Monitoring adolescents’ digital media use offers a unique opportunity to detect risk for suicide, the second leading cause of death among youth. Adolescents communicate through digital media in high volumes, frequently expressing emotionality. In fact, disclosures of suicidality are more common online than they are in-person. Use of automated methods of digital media monitoring triggered by a natural language processing algorithm offers potential to detect suicidal risk from subtle linguistic units (e.g. negatively-valanced words, phrases, or emoticons known to be associated with suicidality) present within adolescents’ digital media content and use this information to respond with alerts of suicidal risk. Critical to the implementation of such an approach is consideration of its acceptability in the clinical care for adolescents at high-risk for suicide.

Objective:

Through data collection with recently suicidal youth, parents, and clinicians, this study examined 1) the current context of digital media monitoring for suicidal adolescents to inform the need for automated monitoring and 2) the factors that influence acceptance of automated monitoring of suicidal adolescents’ DMU within clinical care.

Methods:

Fifteen recently suicidal adolescents (ages 12-17), twelve parents, and ten clinicians participated in focus groups, qualitative interviews, and a group discussion, respectively. Data were recorded, transcribed, and analyzed using thematic analysis.

Results:

Participants described important challenges to current strategies for digital media monitoring for suicidal youth. They felt automated monitoring would have advantages above current monitoring approaches, namely by protecting online environments and aiding adolescent disclosure and support-seeking about online suicidal risk communication, which may otherwise go unnoticed. However, they identified barriers that could impede implementation within clinical care, namely adolescents’ and parents’ concerns toward unintended consequences of automated monitoring, i.e. potential for loss of privacy or false alerts, and clinicians’ concerns toward liability to respond to alerts of suicidal risk. Based on the needs and preferences of adolescents, parents, and clinicians, a model for automated digital media monitoring is presented that aims to optimize acceptability within clinical care for suicidal youth.

Conclusions:

Automated digital media monitoring offers a promising means to augment detection and response to suicidal risk within the clinical care for suicidal youth when strategies are in place that address the preferences of adolescents, parents, and clinicians.