Adolescent, parent, and provider attitudes toward a machine learning based clinical decision support system for selecting treatment for youth depression.

BACKGROUND: Machine learning based clinical decision support systems (CDSSs) have been proposed as a means of advancing personalized treatment planning for disorders, such as depression, that have a multifaceted etiology, course, and symptom profile. However, machine learning based models for treatment selection are rare in the field of psychiatry. They have also not yet been translated for use in clinical practice. Understanding key stakeholder attitudes toward machine learning based CDSSs is critical for developing plans for their implementation that promote uptake by both providers and families. METHODS: In Study 1, a prototype machine learning based Clinical Decision Support System for Youth Depression (CDSS-YD) was demonstrated to focus groups of adolescents with a diagnosis of depression (n = 9), parents (n = 11), and behavioral health providers (n = 8). Qualitative analysis was used to assess their attitudes towards the CDSS-YD. In Study 2, behavioral health providers were trained in the use of the CDSS-YD and they utilized the CDSS-YD in a clinical encounter with 6 adolescents and their parents as part of their treatment planning discussion. Following the appointment, providers, parents, and adolescents completed a survey about their attitudes regarding the use of the CDSS-YD. RESULTS: All stakeholder groups viewed the CDSS-YD as an easy to understand and useful tool for making personalized treatment decisions, and families and providers were able to successfully use the CDSS-YD in clinical encounters. Parents and adolescents viewed their providers as having a critical role in the use the CDSS-YD, and this had implications for the perceived trustworthiness of the CDSS-YD. Providers reported that clinic productivity metrics would be the primary barrier to CDSS-YD implementation, with the creation of protected time for training, preparation, and use as a key facilitator. CONCLUSIONS: Machine learning based CDSSs, if proven effective, have the potential to be widely accepted tools for personalized treatment planning. Successful implementation will require addressing the system-level barrier of having sufficient time and energy to integrate it into practice.

Adolescent, parent, and provider attitudes toward a machine-learning based clinical decision support system for selecting treatment for youth depression.

Background: Machine-learning based clinical decision support systems (CDSSs) have been proposed as a means of advancing personalized treatment planning for disorders, such as depression, that have a multifaceted etiology, course, and symptom profile. However, machine-learning based models for treatment selection are rare in the field of psychiatry. They have also not yet been translated for use in clinical practice. Understanding key stakeholder attitudes toward machine learning-based CDSSs is critical for developing plans for their implementation that promote uptake by both providers and families. Methods: In Study 1, a machine-learning based Clinical Decision Support System for Youth Depression (CDSS-YD) was demonstrated to focus groups of adolescents with a diagnosis of depression (n = 9), parents (n = 11), and behavioral health providers (n = 8). Qualitative analysis was used to assess their attitudes towards the CDSS-YD. In Study 2, behavioral health providers were trained in the use of the CDSS-YD and they utilized the CDSS-YD in a clinical encounter with 6 adolescents and their parents as part of their treatment planning discussion. Following the appointment, providers, parents, and adolescents completed a survey about their attitudes regarding the use of the CDSS-YD. Results: All stakeholder groups viewed the CDSS-YD as an easy to understand and useful tool for making personalized treatment decisions, and families and providers were able to successfully use the CDSS-YD in clinical encounters. Parents and adolescents viewed their providers as having a critical role in the use the CDSS-YD, and this had implications for the perceived trustworthiness of the CDSS-YD. Providers reported that clinic productivity metrics would be the primary barrier to CDSS-YD implementation, with the creation of protected time for training, preparation, and use as a key facilitator. Conclusions: The CDSS-YD has the potential to be a widely accepted and useful tool for personalized treatment planning. Successful implementation will require addressing the system-level barrier of having sufficient time and energy to integrate it into practice.

Parent and Child Risk Profiles as Predictors of Response to a Conduct Problem Preventive Intervention.

Current evidence-based prevention programming targeting child externalizing problems demonstrates modest overall effect sizes and is largely ineffective for a sizable proportion of youth who participate. However, our understanding of the youth and family characteristics associated with response to specific programming is quite limited. The current study used child and family risk profiles as predictors of response trajectories to the Early Risers conduct problem preventive intervention. A sample of 240 kindergarten-aged youth displaying elevated school-based aggression were randomized by school to either the Early Risers intervention or a control condition. Using a number of child and family risk variables, a latent profile analysis produced a solution consisting of five unique risk profiles. Three low and mixed risk profiles were associated with a limited response to the intervention. One high-risk profile characterized by maladaptive parenting and elevated child externalizing demonstrated notably improved trajectories of externalizing behavior over a 3-year period relative to the control condition. Another high-risk profile characterized by inconsistent discipline, high parental distress, and elevated child internalizing and externalizing symptoms seemed to have positive developmental trends disrupted by the intervention relative to the control condition, potentially consistent with an iatrogenic effect relative to the control condition. The study results support continued efforts to use broader risk profiles to examine heterogeneity in response to preventive interventions and, with replication, will have implications for intervention tailoring.

Bidirectional Relations Between Parenting Practices and Child Externalizing Behaviors in Formerly Homeless Families: A Random-Intercept Cross-Lagged Panel Analysis.

OBJECTIVE: This study examined the bidirectional relation between effective parenting practices and externalizing problems in children in homeless families. DESIGN: The sample comprised 223 children (M = 8.12 years) in 137 families living in temporary supportive housing, who participated in the Early Risers conduct problems prevention program lasting 2 years. Video-recorded observations of parent-child interactions were collected and rated by trained observers to assess effective parenting practices. Child externalizing problems were reported by their school teachers. Both variables were assessed at baseline prior to intervention and at 1- and 2-year post-baseline. RESULTS: Child externalizing problems at baseline were negatively associated with effective parenting from baseline to year 1 as well as from year 1 to year 2. Observed effective parenting practices at year 1 were negatively associated with child externalizing problems from year 1 to year 2. CONCLUSIONS: These findings underscore the presence of bidirectional influence processes between parents and children in high-risk families. Implications for intervention programs for high-risk families are discussed.

Self-Regulatory Profiles and Conduct Problems in Youth Referred to Juvenile Diversion.

The current study utilized a person-centered approach to explore how self-regulatory profiles relate to conduct problems in an ethnically diverse sample of 197 adolescents referred to juvenile diversion programming. Utilizing a multidomain, multimethod battery of self-regulation indicators, three common profiles emerged in a latent profile analysis. The profiles represented an Adaptive group, a Cognitively Inflexible group, and an Emotionally Dysregulated group. Group membership was associated with severity and type of conduct problems as well as callous and unemotional traits. The Adaptive group demonstrated lower severity conduct problems when compared to the other groups. The Emotionally Dysregulated group was more likely to commit violent offenses and demonstrated higher levels of some callous and unemotional traits than youth characterized by cognitive inflexibility.

Does Giving Parents Their Choice of Interventions for Child Behavior Problems Improve Child Outcomes?

Empowering consumers to be active decision-makers in their own care is a core tenet of personalized, or precision medicine. Nonetheless, there is a dearth of research on intervention preferences in families seeking interventions for a child with behavior problems. Specifically, the evidence is inconclusive as to whether providing parents with choice of intervention improves child/youth outcomes (i.e., reduces externalizing problems). In this study, 129 families presenting to community mental health clinics for child conduct problems were enrolled in a doubly randomized preference study and initially randomized to choice or no-choice conditions. Families assigned to the choice condition were offered their choice of intervention from among three different formats of the Parent Management Training-Oregon Model/PMTO (group, individual clinic, home based) and services-as-usual (child-focused therapy). Those assigned to the no-choice condition were again randomized, to one of the four intervention conditions. Intent-to-treat analyses revealed partial support for the effect of parental choice on child intervention outcomes. Assignment to the choice condition predicted teacher-reported improved child hyperactivity/inattention outcomes at 6 months post-treatment completion. No main effect of choice on parent reported child outcomes was found. Moderation analyses indicated that among parents who selected PMTO, teacher report of hyperactivity/inattention was significantly improved compared with parents selecting SAU, and compared with those assigned to PMTO within the no-choice condition. Contrary to hypotheses, teacher report of hyperactivity/inattention was also significantly improved for families assigned to SAU within the no-choice condition, indicating that within the no-choice condition, SAU outperformed the parenting interventions. Implications for prevention research are discussed.

Adaptive Recruitment and Parenting Interventions for Immigrant Latino Families with Adolescents.

Parenting programs are an effective strategy to prevent multiple risky outcomes during adolescence. However, these programs usually enroll one caregiver and have low attendance. This study evaluated the preliminary results, cost, and satisfaction of adaptive recruitment and parenting interventions for immigrant Latino families. A mixed methods study was conducted integrating a pre-post design with embedded qualitative and process evaluations. Fifteen immigrant Latino families with an adolescent child aged 10-14 were recruited. Two-caregiver families received a home visit to increase enrollment of both caregivers. All families participated in an adaptive parenting program that included group sessions and a one-to-one component (online videos plus follow-up telephone calls) for those who did not attend the group sessions. The intervention addressed positive parenting practices using a strengths-based framework. Primary outcomes were the proportion of two-parent families recruited and intervention participation. Secondary outcomes were change in parenting self-efficacy, practices, fidelity, costs, and satisfaction. Participants completed questionnaires and interaction tasks before and after participating in the intervention. In addition, participants and program facilitators completed individual interviews to assess satisfaction with the program components. Overall, 23 parents participated in the intervention; 73% of two-parent families enrolled with both parents. Most participants completed 75% or more of the intervention. Fathers were more likely to use the one-to-one component of the intervention than mothers (p = .038). Participants were satisfied with program modifications. In sum, adaptive recruitment and parenting interventions achieved high father enrollment and high participation. These findings warrant further evaluation in randomized trials.

Moving Toward a Precision-Based, Personalized Framework for Prevention Science: Introduction to the Special Issue.

The goal of this Special Issue is to introduce prevention scientists to an emerging form of healthcare, called precision medicine. This approach integrates investigation of the mechanisms of disease and health-compromising behaviors with prevention, treatment, and cure resolved at the level of the individual. Precision Medicine and its derivative personalized prevention represents a promising paradigm for prevention science as it accounts for response heterogeneity and guides development of targeted interventions that may enhance program effect sizes. If successfully integrated into prevention science research, personalized prevention is an approach that can inform the development of decision support tools (screening measures, prescriptive algorithms) and enhance the utility of mobile health technologies that will enable practitioners to use personalized consumer data to inform decisions about the best type and/or intensity of a prevention strategy for particular individuals or subgroups of individuals. In this special issue, we present conceptual articles that provide a heuristic framework for precision-based, personalization prevention research and empirical studies that address research questions exemplary of a new generation of precision-based personalized preventive interventions focused on children's mental health, behavioral health, and education.

Getting "SMART" about implementing multi-tiered systems of support to promote school mental health.

With the growing adoption and implementation of multi-tiered systems of support (MTSS) in school settings, there is increasing need for rigorous evaluations of adaptive-sequential interventions. That is, MTSS specify universal, selected, and indicated interventions to be delivered at each tier of support, yet few investigations have empirically examined the continuum of supports that are provided to students both within and across tiers. This need is compounded by a variety of prevention approaches that have been developed with distinct theoretical foundations (e.g., Positive Behavioral Interventions and Supports, Social-Emotional Learning) that are available within and across tiers. As evidence-based interventions continue to flourish, school-based practitioners greatly need evaluations regarding optimal treatment sequencing. To this end, we describe adaptive treatment strategies as a natural fit within the MTSS framework. Specifically, sequential multiple assignment randomized trials (SMART) offer a promising empirical approach to rigorously develop and compare adaptive treatment regimens within this framework.

Do Parent Preferences for Child Conduct Problem Interventions Impact Parenting Outcomes? A Pilot Study in Community Children's Mental Health Settings.

A pilot, doubly randomized preference trial was conducted to investigate the impact of providing parents preferences on parenting outcomes. Families with children having conduct problems were randomly assigned to a choice group in which they received their preferred treatment among the four intervention options or a no-choice group in which they were randomized assigned to one of the four options. Results of mixed-effects models showed that parents in the choice group who selected Parent Management Training-Oregon Model (PMTO) had better parenting outcomes over time compared to parents in the choice group who selected child therapy. It highlights the importance of incorporating parent preferences in the delivery of evidence-based treatments.

A Pilot Study of Stress System Activation in Children Enrolled in a Targeted Prevention Program: Implications for Personalization.

Empirically validated interventions addressing childhood psychological problems are now readily available, but success likely depends in part on accurately identifying which children will benefit from which intervention. This pilot study examined the stress activation and response system, first as a way to differentiate high versus low-risk children, and second to explore indicators of the stress system associated with favorable intervention response. METHOD: Participants (N = 43, 58% male) were school-aged children who qualified for inclusion in the Early Risers "Skills for Success" Prevention Program based on their elevated levels of aggressive and/or socially withdrawn behavior and a normally developing comparison group. Compared to the normally developing group, children who were participants in the intervention exhibited a more blunted cortisol response to the stress paradigm. However, for the children in the intervention group, elevated cortisol levels at the start of the stress paradigm were concurrently associated with internalizing problems and predictive of improvement in internalizing problems over time. These findings provide preliminary evidence that hypothalamic pituitary adrenal (HPA) axis biological variables may be helpful tools for identifying children who would benefit from intervention and personalizing interventions.

Stressful life events and perceived parental control in formerly homeless families: Impact on child-internalizing symptoms.

Research has neglected the potential role of perceived parental control as a moderator between stressful life events (SLEs) and child-internalizing symptoms. Using secondary data from the Early Risers "Skills for Success" Program (August, Realmuto, Hektner, & Bloomquist, 2001), this study examined the impact of perceived parental control on the association between SLEs and child internalizing symptoms in formerly homeless families. The sample consisted of 137 families with 223 children between 4 and 12 years of age (M = 8.1, SD = 2.3) living in supportive housing sites in Minneapolis, Minnesota. Participants completed measures assessing the number of SLEs experienced (e.g., unemployment of parent, death of loved one, serious illness, homelessness), perceived parental control, and child-internalizing symptoms. In this sample, 65% of children (n = 144) experienced at least 1 SLE with an average experience of 2 SLEs (M = 2.0, SD = 1.9, range = 0-7). A regression analysis found that experiencing more SLEs and a perceived absence of parental control over child behavior were positively associated with child-internalizing symptoms. A significant interaction between SLEs and perceived absence of parental control over child behavior in predicting child internalizing symptoms was also found. These findings suggest that children of parents who model appropriate control are more likely to experience fewer internalizing symptoms in response to SLEs. (PsycINFO Database Record

A randomized preference trial to inform personalization of a parent training program implemented in community mental health clinics.

Incorporating participant preferences into intervention decision-making may optimize health outcomes by improving participant engagement. We describe the rationale for a preference-based approach to the personalization of community-based interventions. Compensating for the limitations of traditional randomized controlled trials (RCTs) and partially randomized preference trials (PRPTs), we employed a doubly randomized preference trial in the present study. Families (N = 129) presenting to community mental health clinics for child conduct problems were randomized to choice or no-choice conditions. Within each condition, parents were again randomized, or offered choices between home- and clinic-based, individual and group versions of a parent training program or services-as-usual. Participants were assessed at baseline, and treatment retention data were gathered. Families assigned to the choice condition were significantly less likely to drop out of treatment than those in the no-choice condition. In the choice condition, in-home treatment was the preferred modality, and across conditions, families were less likely to be retained in group and clinic modalities. Research on preferences may boost participant engagement and inform shared decision-making.

Application of environmental sensitivity theories in personalized prevention for youth substance abuse: a transdisciplinary translational perspective.

Preventive interventions that target high-risk youth, via one-size-fits-all approaches, have demonstrated modest effects in reducing rates of substance use. Recently, substance use researchers have recommended personalized intervention strategies. Central to these approaches is matching preventatives to characteristics of an individual that have been shown to predict outcomes. One compelling body of literature on person × environment interactions is that of environmental sensitivity theories, including differential susceptibility theory and vantage sensitivity. Recent experimental evidence has demonstrated that environmental sensitivity (ES) factors moderate substance abuse outcomes. We propose that ES factors may augment current personalization strategies such as matching based on risk factors/severity of problem behaviors (risk severity (RS)). Specifically, individuals most sensitive to environmental influence may be those most responsive to intervention in general and thus need only a brief-type or lower-intensity program to show gains, while those least sensitive may require more comprehensive or intensive programming for optimal responsiveness. We provide an example from ongoing research to illustrate how ES factors can be incorporated into prevention trials aimed at high-risk adolescents.

Being "SMART" About Adolescent Conduct Problems Prevention: Executing a SMART Pilot Study in a Juvenile Diversion Agency.

The development of adaptive treatment strategies (ATS) represents the next step in innovating conduct problems prevention programs within a juvenile diversion context. Toward this goal, we present the theoretical rationale, associated methods, and anticipated challenges for a feasibility pilot study in preparation for implementing a full-scale SMART (i.e., sequential, multiple assignment, randomized trial) for conduct problems prevention. The role of a SMART design in constructing ATS is presented. The SMART feasibility pilot study includes a sample of 100 youth (13-17 years of age) identified by law enforcement as early stage offenders and referred for precourt juvenile diversion programming. Prior data on the sample population detail a high level of ethnic diversity and approximately equal representations of both genders. Within the SMART, youth and their families are first randomly assigned to one of two different brief-type evidence-based prevention programs, featuring parent-focused behavioral management or youth-focused strengths-building components. Youth who do not respond sufficiently to brief first-stage programming will be randomly assigned a second time to either an extended parent- or youth-focused second-stage programming. Measures of proximal intervention response and measures of potential candidate tailoring variables for developing ATS within this sample are detailed. Results of the described pilot study will include information regarding feasibility and acceptability of the SMART design. This information will be used to refine a subsequent full-scale SMART. The use of a SMART to develop ATS for prevention will increase the efficiency and effectiveness of prevention programing for youth with developing conduct problems.

Two-year outcomes of the Early Risers prevention trial with formerly homeless families residing in supportive housing.

This article reports 2-year outcomes from a cluster randomized, controlled trial of the Early Risers (ER) program implemented as a selective preventive intervention in supportive housing settings for homeless families. Based on the goals of this comprehensive prevention program, we predicted that intervention participants receiving ER services would show improvement in parenting and child outcomes relative to families in treatment-as-usual sites. The sample included 270 children in 161 families, residing in 15 supportive housing sites; multimethod, multi-informant assessments conducted at baseline and yearly thereafter included parent and teacher report of child adjustment, parent report of parenting self-efficacy, and parent-child observations that yielded scores of effective parenting practices. Data were modeled in HLM7 (4-level model accounting for nesting of children within families and families within housing sites). Two years' postbaseline, intent-to-treat (ITT) analyses indicated that parents in the ER group showed significantly improved parenting self-efficacy, and parent report indicated significant reductions in ER group children's depression. No main effects of ITT were shown for observed parenting effectiveness. However, over time, average levels of parenting self-efficacy predicted observed effective parenting practices, and observed effective parenting practices predicted improvements in both teacher- and parent-report of child adjustment. This is the first study to our knowledge to demonstrate prevention effects of a program for homeless families residing in family supportive housing.

The Association Between Attention-Deficit Hyperactivity Disorder and Nicotine Use Among Adolescents and Young Adults.

Previous research indicates that youth with ADHD are more susceptible to nicotine use compared to those without ADHD and one explanation for this association is the self-medication theory. The present study examines nicotine use in a prospective sample derived from a community sampling procedure rather than a clinical setting. Nicotine use was measured through young adulthood (mean ages: 18, 20 and 22) and three groups were compared based on childhood status: ADHD-only, ADHD-extemalizers and control groups. Results indicated that at all three data points, individuals with childhood ADHD plus an externalizing disorder reported higher nicotine use on all variables compared to the ADHD group absent of an externalizing disorder and the comparison group of non-ADHD youth. The group differences were significant even after controlling for possible confounding variables (age, gender, and current treatment with psychostimulant medication). Study results are discussed in light of the self-medication hypothesis and of the importance of including nicotine prevention programs for adolescents and young adults with ADHD and externalizing problems.

Moderating effects of parental well-being on parenting efficacy outcomes by intervention delivery model of the early risers conduct problems prevention program.

Parent-focused preventive interventions for youth conduct problems are efficacious when offered in different models of delivery (e.g., individual in-home, group center-based). However, we know little about the characteristics of parents associated with a positive response to a particular model of delivery. We randomly assigned the parents of an ethnically diverse sample of kindergarten through second grade students (n = 246) displaying elevated levels of aggression to parent-focused program delivery models emphasizing receiving services in a community center largely with groups (Center; n = 121) or receiving services via an individualized in-home strategy (Outreach; n = 125). In both delivery models, parents received parent skills training and goal setting/case management/referrals over an average of 16 months. Structural equation modeling revealed a significant interaction between parental well-being at baseline and intervention delivery model in predicting parenting efficacy at year 2, while controlling for baseline levels of parenting efficacy. Within the Outreach model, parents with lower levels of well-being as reported at baseline appeared to show greater improvements in parenting efficacy than parents with higher levels of well-being. Within the Center model, parental well-being did not predict parenting efficacy outcomes. The strong response of low well-being parents within the Outreach model suggests that this may be the preferred model for these parents. These findings provide support for further investigation into tailoring delivery model of parent-focused preventive interventions using parental well-being in order to improve parenting outcomes.

A longitudinal study of childhood ADHD and substance dependence disorders in early adulthood.

Attention deficit hyperactivity disorder (ADHD) is a childhood disorder that is associated with many behavioral and social problems. These problems may continue when an individual continues to meet criteria for ADHD as an adult. In this study, we describe the outcome patterns for three different groups: individuals who had ADHD as children, but no longer meet criteria as adults (Childhood-Limited ADHD, n = 71); individuals who met ADHD criteria as children and continue to meet criteria as young adults (Persistent ADHD n = 79); and a control group of individuals who did not meet ADHD diagnostic criteria in childhood or adulthood (n = 69). Groups were compared with examine differences in change in rates of alcohol, marijuana, and nicotine dependence over 3 time points in young adulthood (mean ages 18, 20, and 22 years). The method used is notable as this longitudinal study followed participants from childhood into young adulthood instead of relying on retrospective self-reports from adult participants. Results indicated that there were no significant group differences in change in rates of substance dependence over time. However, individuals whose ADHD persisted into adulthood were significantly more likely to meet DSM-IV criteria for alcohol, marijuana, and nicotine dependence across the 3 time points after controlling for age, sex, childhood stimulant medication use, and childhood conduct problems. Implications of these findings, as well as recommendations for future research, are discussed.

A 10-year randomized controlled trial of the Early Risers conduct problems preventive intervention: effects on externalizing and internalizing in late high school.

OBJECTIVE: The purpose of this study was to examine the long-term effects of the Early Risers "Skills for Success" Conduct Problems Prevention Program (ER; August, Bloomquist, Realmuto, & Hektner, 2007), a multifaceted program targeting social, emotional, behavioral, and academic risk and protective factors to promote adaptive psychological development. METHOD: Based on the random assignment of their school, 245 kindergartners (mean age = 6.6 years, SD = 0.57; 68.6% male) with elevated teacher-rated aggressive behavior either participated in ER for 3 intensive years plus 2 booster years or served as controls. Participants were assessed annually during the intervention with teacher and parent reports and at 2 follow-up points. In the current study, 129 of the original participants were reassessed with diagnostic interviews in late high school (mean age = 16.3, SD = 0.52), and multiple imputation was used to deal appropriately with missing data. RESULTS: Program participants had significantly fewer symptoms of conduct disorder, oppositional defiant disorder, and major depressive disorder than did controls. The program's effect on increasing social skills and parent discipline effectiveness by Grade 3 mediated these effects. CONCLUSIONS: The results of this study provide further evidence of the long-term positive effects of multicomponent, elementary-age, targeted conduct problems prevention programs. Training children in social skills and parents in effective discipline are possible mechanisms to divert maladaptive developmental cascades.