Faculty Bibliography

Generative artificial intelligence (genAI) has potential to improve healthcare by reducing clinician burden and expanding services, among other uses. There is a significant gap between the need for mental health care and available clinicians in the United States-this makes it an attractive target for improved efficiency through genAI. Among the most sensitive mental health topics is suicide, and demand for crisis intervention has grown in recent years. We aimed to evaluate the quality of genAI tool responses to suicide-related queries. We entered 10 suicide-related queries into five genAI tools-ChatGPT 3.5, GPT-4, a version of GPT-4 safe for protected health information, Gemini, and Bing Copilot. The response to each query was coded on seven metrics including presence of a suicide hotline number, content related to evidence-based suicide interventions, supportive content, harmful content. Pooling across tools, most of the responses (79%) were supportive. Only 24% of responses included a crisis hotline number and only 4% included content consistent with evidence-based suicide prevention interventions. Harmful content was rare (5%); all such instances were delivered by Bing Copilot. Our results suggest that genAI developers have taken a very conservative approach to suicide-related content and constrained their models' responses to suggest support-seeking, but little else. Finding balance between providing much needed evidence-based mental health information without introducing excessive risk is within the capabilities of genAI developers. At this nascent stage of integrating genAI tools into healthcare systems, ensuring mental health parity should be the goal of genAI developers and healthcare organizations.

Researchers in ubiquitous computing have long promised that passive sensing will revolutionize mental health measurement by detecting individuals in a population experiencing a mental health disorder or specific symptoms. Recent work suggests that detection tools do not generalize well when trained and tested in more heterogeneous samples. In this work, we contribute a narrative review and findings from two studies with 41 mental health clinicians to understand these generalization challenges. Our findings motivate research on actionable sensing, as an alternative to detection research, studying how passive sensing can augment traditional mental health measures to support actions in clinical care. Specifically, we identify how passive sensing can support clinical actions by revealing patients' presenting problems for treatment and identifying targets for behavior change and symptom reduction, but passive data requires additional contextual information to be appropriately interpreted and used in care. We conclude by suggesting research at the intersection of actionable sensing and mental healthcare, to align technical research in ubiquitous computing with clinical actions and needs.

OBJECTIVE/UNASSIGNED:Patients' race and age have each been identified as risk factors for experiencing restraint events during psychiatric hospitalization. Restraint duration is also an important variable in determining disparities in treatment. To the authors' knowledge, no studies to date have examined the effect of the interaction of race and age on restraint use and duration in inpatient psychiatric settings. This retrospective chart review of electronic medical records of patients admitted between 2012 and 2019 sought to examine whether race and age interacted in predicting differences in the use and duration of restraints in a psychiatric inpatient setting. METHODS/UNASSIGNED:Logistic and hierarchical regression analyses were conducted on data from a sample of 29,739 adolescent (ages 12-17 years) and adult (ages ≥18 years) inpatients to determine whether the interaction of race and age group (adolescent or adult) significantly predicted a restraint event or differences in restraint duration. RESULTS/UNASSIGNED:Black (adjusted OR [AOR]=1.85) and multiracial (AOR=1.36) patients were more likely to experience a restraint event than were their White peers. Black race was also significantly (p=0.001) associated with longer restraint duration. No significant interaction was detected between race and age in predicting restraint events or duration. CONCLUSIONS/UNASSIGNED:Although the interaction between race and age did not predict restraint events or duration, the findings indicate racial disparities in the frequency and duration of restraint events among Black and multiracial individuals and may inform efforts to reduce these events.

The course of childhood-onset attention deficit hyperactivity disorder (ADHD) varies across individuals; some will experience persistent symptoms while others' symptoms fluctuate or remit. We describe the longitudinal course of ADHD symptoms and associated clinical characteristics in adolescents with childhood-onset ADHD. Participants (aged 6-12 at baseline) from the Longitudinal Assessment of Manic Symptoms (LAMS) study who met DSM criteria for ADHD prior to age 12 were evaluated annually with the Kiddie Schedule for Affective Disorders and Schizophrenia for eight years. At each timepoint, participants were categorized as meeting ADHD criteria, subthreshold criteria, or not having ADHD. Stability of course was defined by whether participants experienced consistent ADHD symptoms, fluctuating symptoms, or remission. The persistence of the symptoms was defined by symptom status at the final two follow-ups (stable ADHD, stable remission, stable partial remission, unstable). Of 685 baseline participants, 431 had childhood-onset ADHD and at least two follow-ups. Half had a consistent course of ADHD, nearly 40% had a remitting course, and the remaining participants had a fluctuating course. More than half of participants met criteria for ADHD at the end of their participation; about 30% demonstrated stable full remission, 15% had unstable symptoms, and one had stable partial remission. Participants with a persistent course and stable ADHD outcome reported the highest number of symptoms and were most impaired. This work builds on earlier studies that describe fluctuating symptoms in young people with childhood-onset ADHD. Results emphasize the importance of ongoing monitoring and detailed assessment of factors likely to influence course and outcome to help young people with childhood-onset ADHD.

Racism is a social determinant of mental health which has a disproportionally negative impact on the experiences of psychiatric inpatients of color. Distinct differences in the physical space and clinical settings of two inpatient buildings at a hospital system in the tristate (New York, New Jersey, Connecticut) area of the United States led to the present investigation of racial inequities in the assignment of patients to specific buildings and units. Archival electronic medical record data were analyzed from over 18,000 unique patients over a period of six years. Hierarchical logistic regression analyses were conducted with assigned building (old vs. new building) as the binary outcome variable. Non-Hispanic White patients were set as the reference group. Black, Hispanic/Latinx, and Asian patients were significantly less likely to be assigned to better resourced units in the new building. When limiting the analysis to only general adult units, Black and Hispanic/Latinx patients were significantly less likely to be assigned to units in the new building. These results suggest ethnoracial inequities in patient assignment to buildings which differed in clinical and physical conditions. The findings serve as a call to action for hospital systems to examine the ways in which structural racism impact clinical care.

OBJECTIVE:Globally, rates of youth suicide vary considerably. Suicidal thoughts and behaviors (STB) are consistently associated with risk of death by suicide. However, international trends in STB have not yet been compared. To address this gap, an international meta-analysis of epidemiological and school-based studies that report on STB in youth was conducted. METHOD/METHODS:Systematic searches were conducted in PubMed and PsycINFO through April 2022. Eligible studies included prevalence of active suicidal ideation (SI) or suicide attempts (SA) in community youth younger than age 22. All studies were coded by 2 authors. Mixed models accounting for shared methods and including hypothesized moderators were conducted using the metafor package in R. RESULTS:There were 371 effect sizes for SI, 94 for SI with a plan, and 316 for SA, representing 149 regions. Year of data collection ranged from 1981 to 2021. Participants were 6 to 21 years old. The prevalence of SI ranged across regions from 14.3% to 22.6%; the prevalence of SA ranged from 4.6% to 15.8%. Year was not associated with increasing STB prevalence except for studies from the United States, which showed increasing rates of SI and SA since 2007. CONCLUSION/CONCLUSIONS:This is the most comprehensive meta-analysis of STB in youth, providing valuable data about how risk factors most commonly associated with suicide vary internationally and over time. International rates of STB among youth are not improving and may be getting worse in the United States, despite efforts to reduce suicide risk. Most studies did not report rates of SI or SA separately for LGBTQIA+ (lesbian, gay, bisexual, transgender, queer, intersex, asexual, and others) youth and youth of color. A better understanding of proximal risk at the individual level will be important to informing future prevention efforts, especially for high-risk groups.