Predicting short-term suicidal thoughts in adolescents using machine learning: developing decision tools to identify daily level risk after hospitalization.

BACKGROUND: Mobile technology offers unique opportunities for monitoring short-term suicide risk in daily life. In this study of suicidal adolescent inpatients, theoretically informed risk factors were assessed daily following discharge to predict near-term suicidal ideation and inform decision algorithms for identifying elevations in daily level risk, with implications for real-time suicide-focused interventions. METHODS: Adolescents (N = 78; 67.9% female) completed brief surveys texted daily for 4 weeks after discharge (n = 1621 observations). Using multi-level classification and regression trees (CARTSs) with repeated 5-fold cross-validation, we tested (a) a simple prediction model incorporating previous-day scores for each of 10 risk factors, and (b) a more complex model incorporating, for each of these factors, a time-varying person-specific mean over prior days together with deviation from that mean. Models also incorporated missingness and contextual (study week, day of the week) indicators. The outcome was the presence/absence of next-day suicidal ideation. RESULTS: The best-performing model (cross-validated AUC = 0.86) was a complex model that included ideation duration, hopelessness, burdensomeness, and self-efficacy to refrain from suicidal action. An equivalent model that excluded ideation duration had acceptable overall performance (cross-validated AUC = 0.78). Models incorporating only previous-day scores, with and without ideation duration (cross-validated AUC of 0.82 and 0.75, respectively), showed relatively weaker performance. CONCLUSIONS: Results suggest that specific combinations of dynamic risk factors assessed in adolescents' daily life have promising utility in predicting next-day suicidal thoughts. Findings represent an important step in the development of decision tools identifying short-term risk as well as guiding timely interventions sensitive to proximal elevations in suicide risk in daily life.

Ecological assessment of daily suicidal thoughts and attempts among suicidal teens after psychiatric hospitalization: Lessons about feasibility and acceptability.

Despite its potential to yield information about the dynamic course of suicidal ideation/behavior in individuals' natural environment, Ecological Momentary Assessment (EMA) has been strikingly underutilized among suicidal teens. This study reports on feasibility and acceptability of ecological assessment of daily suicide risk-related outcomes ("daily diaries," a special case of EMA) among adolescent inpatients in the critical post-discharge period. Thirty-four adolescents (76% female; ages 13-17) responded to daily electronic surveys for four weeks after discharge. Survey adherence was 69% (n = 650 days) and decreased each week. Adherence was half as likely among adolescents without attempt history (OR = 0.50, CI = 0.27-0.95). Mid- and end-point study responses indicated high acceptability of daily diaries. Most adolescents reported no change or more positive change in their thoughts/mood after daily surveys. Suicidal ideation was reported on 24.4% (n = 159) of the days. In the month post discharge, more teens reported suicidal thoughts using daily surveys (70.6%) compared to end-of-study assessment (45.2%) (Chi-square = 4.24, p = .039). Two participants (5.9%) reported an attempt. Ideation frequency and duration varied across time, suggesting utility of frequent assessments in this context. EMA data collection with high-risk adolescents offers a feasible approach to examining real-time suicidal ideation/behavior, yielding nuanced information that is critical to advancing suicide prevention efforts.

When the party continues: Impulsivity and the effect of employment on young adults' post-college alcohol use.

BACKGROUND: The transition from college to work is both an exciting and potentially high risk time for young adults. As students transition from academic settings to full-time employment, they must navigate new social demands, work demands, and adjust their drinking behaviors accordingly. Research has shown that there are both protective factors and risk factors associated with starting a new job when it comes to alcohol use, and individual differences can moderate these factors. METHOD: 1361 students were recruited from 4 geographically diverse universities and followed 1month pre- and 1month post-graduation. Drinking frequency, quantity, consequences, and impulsivity were assessed. RESULTS: Full-time employment was related to increased drinking quantity but not related to changes in other drinking outcomes. However, impulsivity moderated the relationship between employment and drinking. For those reporting higher levels of impulsivity at baseline, full-time employment was associated with an increase in drinking variables (quantity and frequency), whereas drinking was unaffected by full-time employment status among those reporting lower levels of impulsivity. Implications for future research are discussed.

A "SMART" design for building individualized treatment sequences.

Interventions often involve a sequence of decisions. For example, clinicians frequently adapt the intervention to an individual's outcomes. Altering the intensity and type of intervention over time is crucial for many reasons, such as to obtain improvement if the individual is not responding or to reduce costs and burden when intensive treatment is no longer necessary. Adaptive interventions utilize individual variables (severity, preferences) to adapt the intervention and then dynamically utilize individual outcomes (response to treatment, adherence) to readapt the intervention. The Sequential Multiple Assignment Randomized Trial (SMART) provides high-quality data that can be used to construct adaptive interventions. We review the SMART and highlight its advantages in constructing and revising adaptive interventions as compared to alternative experimental designs. Selected examples of SMART studies are described and compared. A data analysis method is provided and illustrated using data from the Extending Treatment Effectiveness of Naltrexone SMART study.