Predictive modeling of service discontinuation in transitional age youth with recent behavioral health service use.

OBJECTIVE: To develop and test predictive models of discontinuation of behavioral health service use within 12 months in transitional age youth with recent behavioral health service use. DATA SOURCES: Administrative claims for Medicaid beneficiaries aged 15-26 years in Connecticut. STUDY DESIGN: We compared the performance of a decision tree, random forest, and gradient boosting machine learning algorithms to logistic regression in predicting service discontinuation within 12 months among beneficiaries using behavioral health services. DATA EXTRACTION: We identified 33,532 transitional age youth with ≥1 claim for a primary behavioral health diagnosis in 2016 and Medicaid enrollment of ≥11 months in 2016 and ≥11 months in 2017. PRINCIPAL FINDINGS: Classification accuracy for identifying youth who discontinued behavioral health service use was highest for gradient boosting (80%, AUC = 0.86), decision tree (79%, AUC = 0.84), and random forest (79%, AUC = 0.86), as compared with logistic regression (71%, AUC = 0.71). CONCLUSIONS: Predictive models based on Medicaid claims can assist in identifying transitional age youth who are at risk of discontinuing from behavioral health care within 12 months, thus allowing for proactive assessment and outreach to promote continuity of care for younger persons who have behavioral health needs.

Predictors of Behavioral Health Service Utilization in a Medicaid Enrolled Sample of Emerging Adults.

Emerging adults (EA), individuals between the ages of 15-26, face many challenges in their transition to a new developmental stage, especially those with behavioral health concerns who do not receive the supports they need. Many EA drop out of services at 18, which is likely due in part to the need to transition to the adult service system and the lack of available transition support services in child/adolescent service systems. Though this is a clear disparity, research on EA service utilization, especially those enrolled in Medicaid and with co-occurring conditions, is rare. This paper begins to address this gap by examining variables at age 17 that predict the service utilization of continuously Medicaid enrolled EA at age 18. Data came from an administrative dataset. The sample had 4,548 EA and 53% were female, 50% identified with a minority group, and 19% were child-welfare involved. Exploratory logistic regression analyses were used. Minority EA had lower odds of utilizing services at age 18. EA involved with child welfare had greater odds of utilizing services at age 18. EA with at least one Substance Use Disorder (SUD) and at least one mental health disorder at 17 had a higher likelihood of service utilization at 18, the opposite was true for EA with only SUDs. These findings identified predictors of service utilization for an understudied sample-EA enrolled in Medicaid. Results provided preliminary evidence that EA with SUD diagnoses access behavioral health services differently than those without a SUD diagnosis, and that it is fruitful to examine subgroups of EA when seeking to understand their service utilization patterns. Identifying predictors of service utilization during the transition period from the child to the adult system can help inform systems interventions to retain EA in services.

Impact of Mobile Crisis Services on Emergency Department Use Among Youths With Behavioral Health Service Needs.

OBJECTIVE: Youths are using emergency departments (EDs) for behavioral health services in record numbers, even though EDs are suboptimal settings for service delivery. In this article, the authors evaluated a mobile crisis service intervention implemented in Connecticut with the aim of examining whether the intervention was associated with reduced behavioral health ED use among those in need of services. METHODS: The authors examined two cohorts of youths: 2,532 youths who used mobile crisis services and a comparison sample of 3,961 youths who used behavioral health ED services (but not mobile crisis services) during the same fiscal year. Propensity scores were created to balance the two groups, and outcome analyses were used to examine subsequent ED use (any behavioral health ED admissions and number of behavioral health ED admissions) in an 18-month follow-up period. RESULTS: A pooled odds ratio of 0.75 (95% confidence interval [CI]=0.66-0.84) indicated that youths who received mobile crisis services had a significant reduction in odds of a subsequent behavioral health ED visit compared with youths in the comparison sample. The comparable result for the continuous outcome of number of behavioral health ED visits yielded an incidence risk ratio of 0.78 (95% CI=0.71-0.87). CONCLUSIONS: Using comparison groups, the authors provided evidence suggesting that community-based mobile crisis services, such as Mobile Crisis, reduce ED use among youths with behavioral health service needs. Replication in other years and locations is needed. Nevertheless, these results are quite promising in light of current trends in ED use.

Caseworker assessment of child risk and functioning and their relation to service use in the child welfare system.

Children within the child welfare system are more likely to experience emotional and behavioral problems than children not involved with the system. Many states have adopted standardized risk and assessment measures to inform decision-making on appropriate levels of care related to placement or service intensity for children within the system. This study examined the relationship of caseworker ratings of risk across multiple domains to youth functioning and service use for a sample of children open to the child welfare system. The study identified a stratified random sample of youth who were between the ages of five and 21 and open to the child welfare system (n = 184). Stratification was based on current placement (i.e., in-home, foster home, congregate care, and juvenile justice placements). Administrative data was used to access caseworker ratings of risk across child, parent, and family domains using a standardized risk assessment tool. Children's caseworkers (n = 103) completed a standardized measure of child functioning and reported on youth utilization of services across multiple sectors including specialty mental health, school-based, juvenile justice, and medical settings. Regression analyses using variance-corrected estimation for clustered data (by caseworker) revealed higher levels of child risk were associated with poorer child functioning, which, in turn, were associated with higher rates of multi-sector service use. Recommendations and future directions are discussed.

Who Supports the Successful Implementation and Sustainability of Evidence-Based Practices? Defining and Understanding the Roles of Intermediary and Purveyor Organizations.

Research on implementation science has increased significantly over the past decade. In particular, psychologists have looked closely at the value and importance of bridging the gap between science and practice. As evidence-based practices (EBPs) become more prevalent, concrete mechanisms are needed to bring these scientifically supported treatments and interventions to community-based settings. Intermediary and purveyor organizations (IPOs) have emerged in recent years that specialize in bringing research to practice. Using a framework developed by Franks (), this descriptive study surveyed respondents that self-identified as IPOs and focused on identifying shared definitions, functions, and activities. Results indicated that seven descriptive roles previously identified were supported by this survey and many common shared activities, goals, and functions across these organizations were observed. Further, these organizations appear to be influenced by the growing field of implementation science. Limitations and implications of this study are discussed.

Relationship of risk assessment to placement characteristics in a statewide child welfare population.

Risk assessments allow child and youth services to identify children who are at risk for maltreatment (e.g., abuse, neglect) and help determine the restrictiveness of placements or need for services among youth entering a child welfare system. Despite the use of instruments by many agencies within the U.S. to determine the appropriate placements for youth, research has shown that placement decisions are often influenced by factors such as gender, age, and severity of social-emotional and behavior problems. This study examined ratings of risk across multiple domains using a structured assessment tool used by caseworkers in the Rhode Island child welfare system. The relationship between ratings of risk and placement restrictiveness was also examined. Risk levels varied across placement settings. Multivariate analyses revealed that lower caseworker ratings of parent risk and higher ratings of youth risk were associated with more restrictive placements for youth. Implications for the child welfare system are discussed.