Randomized controlled trial of an online machine learning-driven risk assessment and intervention platform for increasing the use of crisis services.

Abstract

Objective: Mental illness is a leading cause of disease burden; however, many barriers prevent people from seeking mental health services. Technological innovations may improve our ability to reach underserved populations by overcoming many existing barriers. We evaluated a brief, automated risk assessment and intervention platform designed to increase the use of crisis resources provided to those online and in crisis. Method: Participants, users of the digital mental health app Koko, were randomly assigned to treatment or control conditions upon accessing the app and were included in the study after their posts were identified by machine learning classifiers as signaling a current mental health crisis. Participants in the treatment condition received a brief Barrier Reduction Intervention (BRI) designed to increase the use of crisis service referrals provided on the app. Participants were followed up several hours later to assess the use of crisis services. Results: Only about one quarter of participants in a crisis (21.8%) reported being "very likely" to use clinical referrals provided to them, with the most commonly endorsed barriers being they "just want to chat" or their "thoughts are too intense." Among participants providing follow-up data (41.3%), receipt of the BRI was associated with a 23% increase in the use of crisis services. Conclusion: These findings suggest that a brief, automated BRI can be efficacious on digital platforms, even among individuals experiencing acute psychological distress. The potential to increase help seeking and service utilization with such procedures holds promise for those in need of psychiatric services. Trial Registration: clinicaltrials.gov identifier: NCT03633825. What is the public health significance of this article?This study provides evidence that a brief, automated barrier reduction procedure increased the rate of service utilization among individuals in acute distress on digital platforms. These findings suggest that automated procedures may have the potential to increase help-seeking behavior among those in need of mental health services on a large scale.

A digital companion for ecological momentary assessment and prevention of suicide: A case series on the use of the emma app

“…The app specifically targets suicidal behavior and proposes an interactive and proactive content that is an effective prevention strategy [8,[88][89][90]. Despite this scientific evidence, a recent literature review [60] identified very few suicide-specific apps (24) with safety planning (14) and that directly allow the user to seek support (13). Moreover, potentially harmful content that encourages self-harm and suicide [26] was identified, and many of the existing apps for suicide prevention have not been scientifically validated [48,60].…”

“…Indeed, apps are affordable and ubiquitous, and can be used in any situation, particularly during a crisis [46]. The WHO recommends them for people at risk of suicide [1] because they offer new opportunities to overcome some of the help-seeking barriers [14,[47][48][49], and enhance safety planning [43] in response to dynamic suicidal processes in real-time [24].…”

Exploring Preference to Avoid or Seek Help in Person and Online Among College Students with Suicidal Ideation

“…More research is needed to identify where suicidal individuals go to cope, whether these sites or mobile apps are efficacious or iatrogenic, develop strategies to improve the detection of suicidal individuals online, and to develop and evaluate ways to deploy rapid interventions for individuals at risk for suicide. Indeed, intervention research into nimble deployment of intervention on online platforms shows promise to encourage individuals to use crisis services (Jaroszewski, Morris, & Nock, 2019). Furthermore, both intervention and public health research is needed to increase help-seeking behavior in men, potentially targeting factors such as stigma and embarrassment as ways to increase treatment utilization.…”

What does it mean to provide decision support to a responsible and competent expert?

“…Concerning ML-based DDSSs, just like their impact on patient safety or physicians' performances, their acceptability in practice remains understudied (Peiffer-Smadja et al, 2019). Jaroszewski et al (2019) reported that, during clinical trials of their MLbased DDSS for mental illness prevention, only 28% of participants answered "very likely" to the question presented by the DDSS: "Be honest, how likely are you to try the resources I just shared?". Nadarzynski et al (2020) studied the acceptability of information systems dedicated to sexual health prevention.…”