Artificial Intelligence-Based Student Activity Monitoring for Suicide Risk: Considerations for K-12 Schools, Caregivers, Government, and Technology Developers.

In response to the widespread youth mental health crisis, some kindergarten-through-12th-grade (K-12) schools have begun employing artificial intelligence (AI)-based tools to help identify students at risk for suicide and self-harm. The adoption of AI and other types of educational technology to partially address student mental health needs has been a natural forward step for many schools during the transition to remote education. However, there is limited understanding about how such programs work, how they are implemented by schools, and how they may benefit or harm students and their families. To assist policymakers, school districts, school leaders, and others in making decisions regarding the use of these tools, the authors address these knowledge gaps by providing a preliminary examination of how AI-based suicide risk monitoring programs are implemented in K-12 schools, how stakeholders perceive the effects that the programs are having on students, and the potential benefits and risks of such tools. Using this analysis, the authors also offer recommendations for school and district leaders; state, federal, and local policymakers; and technology developers to consider as they move forward in maximizing the intended benefits and mitigating the possible risks of AI-based suicide risk monitoring programs.

Testing an Intervention to Improve Health Care Worker Well-Being During the COVID-19 Pandemic: A Cluster Randomized Clinical Trial.

Importance: Stress First Aid is an evidence-informed peer-to-peer support intervention to mitigate the effect of the COVID-19 pandemic on the well-being of health care workers (HCWs). Objective: To evaluate the effectiveness of a tailored peer-to-peer support intervention compared with usual care to support HCWs' well-being at hospitals and federally qualified health centers (FQHCs) during the COVID-19 pandemic. Design, Setting, and Participants: This cluster randomized clinical trial comprised 3 cohorts of HCWs who were enrolled from March 2021 through July 2022 at 28 hospitals and FQHCs in the US. Participating sites were matched as pairs by type, size, and COVID-19 burden and then randomized to the intervention arm or usual care arm (any programs already in place to support HCW well-being). The HCWs were surveyed before and after peer-to-peer support intervention implementation. Intention-to-treat (ITT) analysis was used to evaluate the intervention's effect on outcomes, including general psychological distress and posttraumatic stress disorder (PTSD). Intervention: The peer-to-peer support intervention was delivered to HCWs by site champions who received training and subsequently trained the HCWs at their site. Recipients of the intervention were taught to respond to their own and their peers' stress reactions. Main Outcomes and Measures: Primary outcomes were general psychological distress and PTSD. General psychological distress was measured with the Kessler 6 instrument, and PTSD was measured with the PTSD Checklist. Results: A total of 28 hospitals and FQHCs with 2077 HCWs participated. Both preintervention and postintervention surveys were completed by 2077 HCWs, for an overall response rate of 28% (41% at FQHCs and 26% at hospitals). A total of 862 individuals (696 females [80.7%]) were from sites that were randomly assigned to the intervention arm; the baseline mean (SD) psychological distress score was 5.86 (5.70) and the baseline mean (SD) PTSD score was 16.11 (16.07). A total of 1215 individuals (947 females [78.2%]) were from sites assigned to the usual care arm; the baseline mean (SD) psychological distress score was 5.98 (5.62) and the baseline mean (SD) PTSD score was 16.40 (16.43). Adherence to the intervention was 70% for FQHCs and 32% for hospitals. The ITT analyses revealed no overall treatment effect for psychological distress score (0.238 [95% CI, -0.310 to 0.785] points) or PTSD symptom score (0.189 [95% CI, -1.068 to 1.446] points). Post hoc analyses examined the heterogeneity of treatment effect by age group with consistent age effects observed across primary outcomes (psychological distress and PTSD). Among HCWs in FQHCs, there were significant and clinically meaningful treatment effects for HCWs 30 years or younger: a more than 4-point reduction for psychological distress (-4.552 [95% CI, -8.067 to -1.037]) and a nearly 7-point reduction for PTSD symptom scores (-6.771 [95% CI, -13.224 to -0.318]). Conclusions and Relevance: This trial found that this peer-to-peer support intervention did not improve well-being outcomes for HCWs overall but had a protective effect against general psychological distress and PTSD in HCWs aged 30 years or younger in FQHCs, which had higher intervention adherence. Incorporating this peer-to-peer support intervention into medical training, with ongoing support over time, may yield beneficial results in both standard care and during public health crises. Trial Registration: ClinicalTrials.gov Identifier: NCT04723576.

Equity as a Guiding Principle for the Public Health Data System.

The growing centering of equity in health has elevated a conversation about how those interests should translate within the systems and sectors that influence health. In particular, the public health data system has been relatively limited in capturing the drivers and consequences of health inequity as well as the varying dimensions of equity. This article examines what it means to use equity as a guiding principle throughout the components and functions of a modern public health data system. As with other articles in this supplement, this article builds from a literature review, environmental scan, and deliberations from the National Commission to Transform Public Health Data Systems to summarize current gaps to integrate equity throughout the system. It outlines opportunities for the technology and data science sectors specifically to engage given the access that these sectors have to information that would illuminate and frame the nuances and impacts of health inequity.

What Data Should Be Included in a Modern Public Health Data System.

The public is inundated with data, both in where data are ubiquitously collected and in how organizations are using data to drive public sector and commercial decisions. The public health data system is no exception to this flood of data, both in growing data volume and variety. However, what are collected and analyzed about the health status of the nation, how particular data and measures are prioritized for parsimony, and how those data provide a signal for where to invest to address health inequities are in dire need of a reboot. As with other articles in this supplement, this article builds from a literature review, an environmental scan, and deliberations from the National Commission to Transform Public Health Data Systems. The article summarizes what data should be included and identifies where the technology and data sectors can contribute to fill current gaps to measure equity, positive health, and well-being.

The Issues of Interoperability and Data Connectedness for Public Health.

An unprecedented amount of data is being collected across a diversity of sectors, which, if harnessed, could transform public health decision-making. Yet significant challenges stand in the way of such a vision, including the need to establish standards of data sharing and interoperability, the need for innovation in both methodological approaches and workforce models, and the need for data stewardship and governance models to ensure the protection and integrity of the public health data system. As with other articles in this supplement, this article builds from a literature review, environmental scan, and deliberations from the National Commission to Transform Public Health Data Systems. The article summarizes some of the challenges around data sharing and reuse and identifies where the technology and data sectors can contribute to fill current gaps to promote interoperability and data stewardship.

Technology and Data Implications for the Public Health Workforce.

Achieving a modern equity-oriented public health system requires the development of a public health workforce with the skills and competencies needed to generate findings and integrate knowledge using diverse data. Yet current workforce capabilities and infrastructure are misaligned with what is needed to harness both new and older forms of data and to translate them into information that is equity contextualized. As with other articles in this supplement, this article builds from a literature review, environmental scan, and deliberations from the National Commission to Transform Public Health Data Systems. The article summarizes some of the challenges around current workforce capabilities and pipeline. The article identifies where the technology and data sectors can contribute skills, expertise, and assets in support of innovative workforce models and augment the development of public health workforce competencies.