Adolescent, Parent, and Provider Perceptions of a Predictive Algorithm to Identify Adolescent Suicide Risk in Primary Care.

OBJECTIVE: To understand adolescent, parent, and provider perceptions of a machine learning algorithm for detecting adolescent suicide risk prior to its implementation primary care. METHODS: We conducted semi-structured, qualitative interviews with adolescents (n = 9), parents (n = 12), and providers (n = 10; mixture of behavioral health and primary care providers) across two major health systems. Interviews were audio recorded and transcribed with analyses supported by use of NVivo. A codebook was developed combining codes derived inductively from interview transcripts and deductively from implementation science frameworks for content analysis. RESULTS: Reactions to the algorithm were mixed. While many participants expressed privacy concerns, they believed the algorithm could be clinically useful for identifying adolescents at risk for suicide and facilitating follow-up. Parents' past experiences with their adolescents' suicidal thoughts and behaviors contributed to their openness to the algorithm. Results also aligned with several key Consolidated Framework for Implementation Research domains. For example, providers mentioned barriers inherent to the primary care setting such as time and resource constraints likely to impact algorithm implementation. Participants also cited a climate of mistrust of science and health care as potential barriers. CONCLUSIONS: Findings shed light on factors that warrant consideration to promote successful implementation of suicide predictive algorithms in pediatric primary care. By attending to perspectives of potential end users prior to the development and testing of the algorithm, we can ensure that the risk prediction methods will be well-suited to the providers who would be interacting with them and the families who could benefit.

Adolescent Depression Symptom Trajectories Detected Via Universal Screening in Pediatric Primary Care.

Unique trajectories of adolescent depression symptoms have been identified, yet less is known about whether such patterns translate to real-world clinical settings. Because annual adolescent depression screening is becoming more prevalent in primary care, we examined whether longitudinal patterns of depression symptoms documented in the developmental psychopathology literature can also be detected via routine screening in primary care and explored how membership in the identified trajectories varied based on concurrent suicide risk and sociodemographic factors. A total of 1,359 adolescents aged 12-16 years old at the first timepoint were included in the current analyses. These adolescents completed three depression screeners during their well-visits in a large pediatric primary care network between November 15, 2017 and February 1, 2020. Retrospective electronic health record data were extracted, including sociodemographic variables and depression screening results. Dynamic functional time series clustering results indicated the optimal number of clusters was five. The five depression symptom trajectories were: (1) A-Shaped (i.e., relatively low depression symptoms at Time 1, a substantial increase in symptoms at Time 2, and a return to low symptoms at Time 3), (2) Increasing, (3) Low-Stable, (4) High-Decreasing, and (5) Low-Decreasing. Cluster differences in suicide risk largely mapped onto depression symptom levels at each assessment. We found cluster differences based on practice location, insurance type, and adolescent race. The symptom trajectories observed in this study resemble those found in the developmental psychopathology literature, though some key differences were noted. Findings can inform future research and symptom monitoring in primary care.

Emerging Risk of Adolescent Depression and Suicide Detected Through Pediatric Primary Care Screening.

OBJECTIVE: The goal of the current study was to document patterns of stability and change in adolescent depression and suicide risk detected via universal depression screening in pediatric primary care and to determine who may go on to experience emerging risk. METHODS: Retrospective electronic health record information (sociodemographic data and depression screening results for 2 timepoints) was extracted for adolescents aged 12-17 who attended well-visits between November 15, 2017, and February 1, 2020, in a large pediatric primary care network. A total of 27,335 adolescents with 2 completed depression screeners were included in the current study. RESULTS: While most adolescents remained at low risk for depression and suicide across the 2 timepoints, others experienced emerging risk (i.e., low risk at time 1 but elevated risk at time 2), decreasing risk (i.e., high risk at time 1 but low risk at time 2) or stable high risk for depression or suicide. Odds of experiencing emerging depression and suicide risk were higher among adolescents who were female (compared to males), Black (compared to White), and had Medicaid insurance (compared to private insurance). Odds of experiencing emerging depression risk were also higher among older adolescents (compared to younger adolescents) as well as adolescents who identified as Hispanic/Latino (compared to non-Hispanic/Latino). CONCLUSIONS: Findings can inform symptom monitoring and opportunities for prevention in primary care.