Video Abstract Video Abstract To determine if racial and ethnic subgroups of adolescents are at high risk for engagement in suicidal behaviors. Using the nationally representative school-based Youth Risk Behavior Survey from the years 1991 to 2017, we conducted logistic regression analyses to examine trends by different racial and ethnic groups, with each suicide indicator serving as a dichotomous outcome. Participants included 198 540 high school students. Across all sex and race and ethnic groups, there were significant linear decreases in self-reported suicidal ideation and suicide plans from 1991 to 2017. Female adolescents (odds ratio [OR], 0.98; P < .001) had significant decreases in attempts over time. Black adolescents had positive linear trends for suicide attempts among both boys (OR, 1.04; P < .001) and girls (OR, 1.02; P = .003). Black adolescent boys (OR, 1.04; P = .048) had a significant linear increase in injury by attempt. The results suggest that, over time, black youth have experienced an increase in suicide attempts, which is troubling because attempts are the most prominent risk factor associated with suicide death. For black boys, a significant increase in injury by attempt occurred, which suggests that black boys may be engaging in increasingly lethal means when attempting suicide. Examining trends of suicidal thoughts and behaviors over time by sex and race and ethnicity allow us to determine where to focus prevention and intervention efforts. Future research should examine the underlying reasons for these changes observed in US high school students.

Suicide is the second leading cause of death in youths aged 12 to 18 years in the US.¹ In 2019, 2090 (7.1 per 100 000) adolescents in this age group died by suicide.² Visits to hospital emergency departments due to suicidal ideation or attempts in youths aged 15 to 19 years are increasing,³ with the largest increase observed in Black, Hispanic, and female adolescents between 2008 and 2015.^4,5 Monitoring the temporal trends of suicidal behaviors is important to guide development of effective suicide prevention.^6-9 In particular, detecting changes in temporal trends in subgroups and when the risk of suicide is greater in those groups can identify high-risk populations for targeted intervention and guide hypothesis generation and testing.¹⁰

Social determinants of health (SDOH), the “conditions in which people are born, grow, live, work, and age,”^1,2 can affect health outcomes,^3-5 including mental, cognitive, and physical well-being.^6,7 Children are raised in neighborhoods with diverse SDOH profiles, including high poverty levels and unemployment; rural settings; limited access to quality health care, nutritious food, clean water, or educational opportunities; and increased exposure to crime and drug sales, and these SDOH are linked to an array of developmental problems, including mental health disorders,^7-12 suicidal behaviors,^13-15 cognitive performance,^6,7,16 and physical health issues.^10,17 Unraveling the complex relationships between SDOH and child development is crucial to understanding which SDOH combinations are associated with which developmental outcomes. Without such information, it is not possible to devise effective, targeted policies and interventions.

Background: Obesity is a leading cause of preventable death worldwide. Artificial intelligence (AI), characterized by machine learning (ML) and deep learning (DL), has become an indispensable tool in obesity research. Objective: This scoping review aimed to provide researchers and practitioners with an overview of the AI applications to obesity research, familiarize them with popular ML and DL models, and facilitate the adoption of AI applications. Methods: We conducted a scoping review in PubMed and Web of Science on the applications of AI to measure, predict, and treat obesity. We summarized and categorized the AI methodologies used in the hope of identifying synergies, patterns, and trends to inform future investigations. We also provided a high-level, beginner-friendly introduction to the core methodologies to facilitate the dissemination and adoption of various AI techniques. Results: We identified 46 studies that used diverse ML and DL models to assess obesity-related outcomes. The studies found AI models helpful in detecting clinically meaningful patterns of obesity or relationships between specific covariates and weight outcomes. The majority (18/22, 82%) of the studies comparing AI models with conventional statistical approaches found that the AI models achieved higher prediction accuracy on test data. Some (5/46, 11%) of the studies comparing the performances of different AI models revealed mixed results, indicating the high contingency of model performance on the data set and task it was applied to. An accelerating trend of adopting state-of-the-art DL models over standard ML models was observed to address challenging computer vision and natural language processing tasks. We concisely introduced the popular ML and DL models and summarized their specific applications in the studies included in the review. Conclusions: This study reviewed AI-related methodologies adopted in the obesity literature, particularly ML and DL models applied to tabular, image, and text data. The review also discussed emerging trends such as multimodal or multitask AI models, synthetic data generation, and human-in-the-loop that may witness increasing applications in obesity research.