Adolescent Well-Being, Mental Health Wellness
Conditions
Brief summary
The purpose of this study is to test the effectiveness of a new clinical decision support tool, Placement Success Predictor (PSP), in a naturalistic setting. PSP will provide placement-specific predictions about the likelihood of a youth having a good outcome in each placement type at a behavioral health center using machine learning algorithms. The primary hypothesis is that clients in at least one placement within one standard deviation of the placement with the highest predicted likelihood of success will have better outcomes than the clients who were not. The secondary hypothesis is that clients' level of improvement over time will be positively correlated with the number of days they are in at least one placement within one standard deviation of the placement with the highest predicted likelihood of success.
Detailed description
In 2017, a total of 669,799 children were confirmed victims of maltreatment in the United States; of the 442,733 children in foster care, 34% have been in more than one placement and 11% are in a group home or institution. Stakes are extremely high for making the best out-of-home placement choice per child because some placement types and multiple placements are associated with poor outcomes. In the past few years, legislation has been created to guide placement decisions for children. Federal law 42 U.S. Code 675 requires that children in the care of the state are placed "in a safe setting that is the least restrictive (most family like)." In addition, the Family First Prevention Services Act signed into law by the U.S. Congress in 2018 includes measures to reduce the number of children in long-term residential settings. This effectiveness study is to assess and improve the usage of PSP in a behavioral health setting. Sample. Clients at Children's Hope Alliance (CHA) who completed the TOP, CHA's standard behavioral health assessment. The target recruitment goal is 700 clients. Methods. PSP results will be available for all clients with recent behavioral health assessment data.
Interventions
PSP is a machine-learning based clinical decision support tool that is designed to assist clinical team members in making placement decisions for youth. PSP provides site-specific placement success prediction scores \[i.e., client's likelihood of success per placement based on machine learning models\] for each youth.
Sponsors
Outcome Referrals, Inc.
Children's Hope Alliance
National Institute of Mental Health (NIMH)
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Healthy volunteers
No
Inclusion criteria
* Completed TOP CS assessment
Exclusion criteria
* None
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Mean Difference in Average Domain Z-scores Across Raters Within Two Weeks on the Clinical Scale of the Treatment Outcome Package (TOP-CS) Between a) Baseline and b) Follow-up | At baseline (within 2 weeks of study start) and approximately 60-120 days later | The Child Treatment Outcome Package (TOP-CS) is a 48-item scale for children (ages 3 - 18) that assesses 13 domains. The Adolescent TOP-CS is a 58-item scale for adolescents (ages 11 - 21) that assesses 12 domains. TOP-CS assesses the client's past 2-week experience on domains including Depression, Violence, and Suicidality (scores are risk-adjusted for case mix variables assessed via 37 items on the companion TOP-Case Mix form regarding stressful life events, comorbidity). Participants answer "All" to "None of the Time" for each item on a 6-point Likert scale. A domain z-score of 0 represents the general population mean. Domain z-scores are averaged into a summary score per participant. Higher (more positive) average z-scores indicate greater symptom severity and lower behavioral well-being (a worse outcome). The value reported is the mean difference in this average z-score between baseline and follow-up; a negative mean difference indicates improvement (reduced severity). |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Mean Difference Between the Average Risk-adjusted Predicted TOP-CS Total Score Across Raters at Study Baseline and the Actual Average TOP-CS Total Score Across Raters at Follow-up | At baseline (within 2 weeks of study start) and approximately 60-120 days later | The Child Treatment Outcome Package (TOP-CS) is a 48-item scale for children (ages 3 - 18) that assesses 13 domains. The Adolescent TOP-CS is a 58-item scale for adolescents (ages 11 - 21) that assesses 12 behavioral health domains. Participants answer "All" to "None of the Time" for each item on a 6-point Likert scale. The TOP-CS Total Score is computed by averaging item responses. The range is 48 to 288 for the Child TOP-CS and 56 to 336 for the Adolescent TOP-CS. Higher Total Scores represent better behavioral well-being (a better outcome). Total Scores are averaged across raters per participant. The value reported is the mean difference between each participant's model-predicted, risk-adjusted Total Score (the outcome expected given their baseline profile) and their actual observed Total Score at follow-up. A positive mean difference indicates that the actual follow-up outcome exceeded the model-predicted outcome (i.e., the participant did better than predicted). |
Countries
United States
Participant flow
Recruitment details
Data were collected from all clients as part of standard clinical practice.
Baseline characteristics
| Characteristic | — |
|---|---|
| Age, Continuous | 12.28 years STANDARD_DEVIATION 3.67 |
| Ethnicity (NIH/OMB) Hispanic or Latino | 11 Participants |
| Ethnicity (NIH/OMB) Not Hispanic or Latino | 55 Participants |
| Ethnicity (NIH/OMB) Unknown or Not Reported | 0 Participants |
| Race (NIH/OMB) American Indian or Alaska Native | 5 Participants |
| Race (NIH/OMB) Asian | 3 Participants |
| Race (NIH/OMB) Black or African American | 104 Participants |
| Race (NIH/OMB) More than one race | 16 Participants |
| Race (NIH/OMB) Native Hawaiian or Other Pacific Islander | 0 Participants |
| Race (NIH/OMB) Unknown or Not Reported | 14 Participants |
| Race (NIH/OMB) White | 218 Participants |
| Sex/Gender, Customized Female | 63 Participants |
| Sex/Gender, Customized Male | 38 Participants |
| Sex/Gender, Customized Unknown/Not reported | 16 Participants |
Adverse events
| Event type | EG000 affected / at risk | EG001 affected / at risk | EG002 affected / at risk | EG003 affected / at risk |
|---|---|---|---|---|
| deaths Total, all-cause mortality | 0 / 66 | 0 / 129 | 0 / 39 | 0 / 169 |
| other Total, other adverse events | 0 / 66 | 0 / 129 | 0 / 39 | 0 / 169 |
| serious Total, serious adverse events | 0 / 66 | 0 / 129 | 0 / 39 | 0 / 169 |
Outcome results
None listed