Predicting Successful Placements for Youth in Child Welfare with Machine Learning.

Out-of-home placement decisions have extremely high stakes for the present and future well-being of children in care because some placement types, and multiple placements, are associated with poor outcomes. We propose that a clinical decision support system (CDSS) using existing data about children and their previous placement success could inform future placement decision-making for their peers. The objective of this study was to test the feasibility of developing machine learning models to predict the best level of care placement (i.e., the placement with the highest likelihood of doing well in treatment) based on each youth's behavioral health needs and characteristics. We developed machine learning models to predict the probability of each youth's treatment success in psychiatric residential care (i.e., Psychiatric Residential Treatment Facility [PRTF]) versus any other placement (AUROCs > 0.70) using data collected in standard care at a behavioral health organization. Placement recommendations based on these machine learning models distinguished between youth who did well in residential care versus non-residential care (e.g., 80% of those who received care in the recommended setting with the highest predicted likelihood of success had above average risk-adjusted outcomes). Then we developed and validated machine learning models to predict the probability of each youth's treatment success across specific placement types in a state-wide system, achieving an average AUROC score of greater than 0.75. Machine learning models based on risk-adjusted behavioral health and functional data show promise in predicting positive placement outcomes and informing future placement decisions for youth in care. Related ethical considerations are discussed.

Revisiting our approach to behavioral health referrals.

This system of matching referrals to behavioral health practitioners' historical effectiveness seeks to strengthen patient outcomes.

Burden of Schizophrenia or Psychosis-Related Symptoms in Adults Undergoing Substance Abuse Evaluation.

This study evaluated the biopsychosocial characteristics of adults undergoing substance abuse evaluation with potential schizophrenia/psychotic disorder, or possible schizophrenia/psychosis-like symptoms, compared with those with no schizophrenia/psychosis-like symptoms. A cross-sectional, observational study examined 170,201 adults, aged 18 to 30, who completed the Addiction Severity Index-Multimedia Version (ASI-MV). Approximately 10% were classified as having possible schizophrenia/psychosis-like symptoms or potential schizophrenia/psychotic disorder. These patients were more likely to exhibit moderate to extreme severity on employment, medical, legal, substance use, social, and psychiatric status than nonsymptomatic patients. The potential schizophrenia or psychotic disorder cohort was also more likely to have ever experienced physical abuse (odds ratio [OR] = 4.30, 95% confidence interval [CI] = 4.12-4.48) and/or sexual abuse (OR = 4.32, 95% CI = 4.15-4.51) versus the no schizophrenia/psychosis-like symptoms cohort. Findings support a recommendation for routine screening for mental health issues, particularly schizophrenia/psychosis-like symptoms, for adults entering substance use disorder treatment settings. This may increase the likelihood of appropriate and earlier intervention.

The natural history of prescription opioid abuse: A pilot study exploring change in routes of administration and motivation for changes.

OBJECTIVE: The purpose of this retrospective, observational pilot study was to explore change in route of administration (RoA) and motivation for changing RoA during the course of opioid abuse. DESIGN: This retrospective pilot study involved collecting and analyzing semistructured interview data. SETTING: Interviews were conducted with patients undergoing outpatient substance abuse treatment at a buprenorphine clinic. PARTICIPANTS: Twenty adult patients (50 percent male) participated in the interviews. MAIN OUTCOME MEASURES: Interview data were qualitatively and quantitatively analyzed to evaluate trends and motivations for changing RoA. RESULTS: In this sample, RoA varied over time. Most patients (75.0 percent) began abusing prescription opioids by swallowing intact pills, and 53.3 percent of patients eventually progressed to chewing. All patients who initiated abuse through chewing or insufflation (ie, intranasal use) progressed to injection. However, several patients (20.0 percent) did not exhibit a linear progression from RoAs with lesser to greater risk for serious adverse events. Of the eight motivations for changing RoA identified in the current study, the most frequently cited (38.2 percent) motivation was to achieve a desired effect (eg, euphoria). CONCLUSIONS: This pilot study is one of the first to investigate natural history of RoA in prescription opioid abuse and motivations for changing RoA. Results suggest that a defined pathway of RoA progression may not exist, and that achieving a desired effect is a common motivation for changing RoA. Although these findings need to be replicated in a larger sample, this research may help support the development of opioid risk mitigation strategies.

A Randomized Controlled Trial of the Effects of Online Pain Management Education on Primary Care Providers.

Objective: To improve pain management practices, we developed an online interactive continuing education (CE) program for primary care providers (PCPs). This program follows the flow of clinical decision-making through simulated cases at critical pain treatment points along the pain treatment continuum. Design: A randomized controlled trial was conducted to test the efficacy of this program. Participants were randomized to either the experimental condition or the control condition (online, text-based CE program). Subjects: A total of 238 primary care providers were recruited through hospitals, professional newsletters, and pain conferences. Results: Participants in both conditions reported significantly improved scores on knowledge (KNOW-PAIN 50), attitudes (CAOS), and pain practice behaviors (PPBS) scales over the four-month study. The experimental condition showed significantly greater change over time on the tamper-resistant formulations (TRFs) of opioids and dosing CAOS subscale compared with the control condition. Post hoc comparisons suggested that participants in the experimental condition were less likely to endorse use of opioid TRFs over time compared with the control condition. Exploratory analyses for potential moderators indicated a significant three-way interaction with time, condition, and discipline (i.e., physician vs other) for the impediments and concerns attitudes subscale and the early refill behaviors subscale. Post hoc comparisons indicated that physicians in the experimental condition exhibited the greatest change in attitudes and the nonphysicians exhibited the greatest change in reported behaviors in response to requests for early refills. Conclusions: Findings suggest online CE programs may positively impact PCPs' knowledge, attitudes, and pain practice behaviors but provide minimal evidence for the value of including interactivity.

A randomized controlled trial of an online self-management program for adults with arthritis pain.

The objective of this RCT was to assess the efficacy of an online pain self-management program with adults who had a self-reported doctor diagnosis of arthritis pain (N = 228). Participants were recruited via flyers and online postings then randomized to the experimental condition or the wait-list control condition. Individuals in the experimental condition reported significantly (1) increased arthritis self-efficacy and (2) reduced pain catastrophizing from baseline to follow up compared to those in the control condition. High user engagement (>204.5 min on the website) was also significantly associated with improved self-management outcomes. These findings suggest that use of an online self-management program may positively impact self-efficacy and catastrophizing among adults with arthritis pain at 6 month follow up. Nonsignificant findings for hypothesized variables such as pain intensity and health behaviors are also discussed. Future longitudinal research is needed to assess if cognitive changes associated with participation in an online self-management program leads to reduced pain.

Mediators and moderators of chronic pain outcomes in an online self-management program.

OBJECTIVES: Little is known about the moderators and mediators of change in online pain interventions based on cognitive-behavior therapy (CBT). We hypothesized that the effects of painACTION.com, an online pain self-management program, on pain-related outcomes would be mediated by changes in depression, anxiety, and stress, as well as the use of coping strategies. We also examined potential moderators of change. METHODS: First, the efficacy of painACTION.com and moderators of the intervention effects were evaluated using a pooled sample from previous back, neuropathic, and arthritis pain studies. Next, we explored whether the intervention effect on the primary outcomes, pain severity, and patient global impression of change (PGIC), was mediated by coping strategies or emotional functioning. RESULTS: Compared with controls, experimental participants evidenced significant improvement in pain, emotional functioning, and coping strategies from baseline to follow-up. There were no clear moderators of intervention effects. Changes in emotional factors, particularly stress levels, mediated the relationship between the intervention and outcome (pain severity) over time. DISCUSSION: This study supports the effectiveness of online interventions when CBT and self-management targets pain levels, emotional factors, and wellness-focused coping. The importance of stress as a mediator of pain severity is discussed. The absence of moderators may indicate that the intervention is effective for a wide variety of patients with chronic pain.

Development of a Community Readiness Survey for Coalitions to Address Prescription Opioid Misuse.

A community readiness survey for coalitions to address the growing epidemic of prescription opioid misuse was developed in this four-part study. A total of 70 coalition members participated. 1) We conducted 30-minute phone interviews with coalition members (n=30) and a literature review to develop an item list. 2) Coalition members rated these 60 items for three criteria: importance, confidence in own answer, confidence in others' answer. 3) Highly rated items were included in a revised survey that was tested with coalition members (n=10) using in-person cognitive interviewing to assess how coalition members were interpreting the questions. 4) Lastly, pre-testing and satisfaction testing with additional coalition members (n=30). Most (83%) of the respondents reported positive overall impressions of the survey.

Associations between public health indicators and injecting prescription opioids by prescription opioid abusers in substance abuse treatment.

OBJECTIVE: To determine what, if any, public health and societal impacts are associated specifically with injection of prescription opioids. DESIGN: Cross-sectional observational study. SETTING: Five hundred forty treatment facilities in 35 states across the United States performing Addiction Severity Index-Multimedia Version (ASI-MV) assessments. PARTICIPANTS: Adult patients (29,459) who reported past 30-day abuse of any prescription opioid on the ASI-MV assessment between January 2007 and January 2011. MAIN OUTCOME MEASURES: The public health indicators selected for this study were liver disease, HIV/AIDS status, recent visit to an emergency room, treatment for pain, treatment for overdosing, homelessness, residence with alcohol/substance abuser, and unemployment. RESULTS: Prescription opioid injection was significantly associated with health problems, psychosocial problems, and utilization of medical services. CONCLUSIONS: This study demonstrates an approach to measure the potential impact of injecting prescription opioids on public health indicators. Findings indicate a positive association between injection of prescription opioids and public health indicators suggesting a need for prescription opioid formulations that may inhibit injection of these medications.

Interactive computer-based interventions for weight loss or weight maintenance in overweight or obese people.

BACKGROUND: The World Health Organization (WHO) estimates that the number of obese or overweight individuals worldwide will increase to 1.5 billion by 2015. Chronic diseases associated with overweight or obesity include diabetes, heart disease, hypertension and stroke. OBJECTIVES: To assess the effects of interactive computer-based interventions for weight loss or weight maintenance in overweight or obese people. SEARCH METHODS: We searched several electronic databases, including CENTRAL, MEDLINE, EMBASE, CINAHL, LILACS and PsycINFO, through 25 May 2011. We also searched clinical trials registries to identify studies. We scanned reference lists of included studies and relevant systematic reviews. SELECTION CRITERIA: Studies were included if they were randomized controlled trials or quasi-randomized controlled trials that evaluated interactive computer-based weight loss or weight maintenance programs in adults with overweight or obesity. We excluded trials if the duration of the intervention was less than four weeks or the loss to follow-up was greater than 20% overall. DATA COLLECTION AND ANALYSIS: Two authors independently extracted study data and assessed risk of bias. Where interventions, control conditions, outcomes and time frames were similar between studies, we combined study data using meta-analysis. MAIN RESULTS: We included 14 weight loss studies with a total of 2537 participants, and four weight maintenance studies with a total of 1603 participants. Treatment duration was between four weeks and 30 months. At six months, computer-based interventions led to greater weight loss than minimal interventions (mean difference (MD) -1.5 kg; 95% confidence interval (CI) -2.1 to -0.9; two trials) but less weight loss than in-person treatment (MD 2.1 kg; 95% CI 0.8 to 3.4; one trial). At six months, computer-based interventions were superior to a minimal control intervention in limiting weight regain (MD -0.7 kg; 95% CI -1.2 to -0.2; two trials), but not superior to infrequent in-person treatment (MD 0.5 kg; 95% -0.5 to 1.6; two trials). We did not observe consistent differences in dietary or physical activity behaviors between intervention and control groups in either weight loss or weight maintenance trials. Three weight loss studies estimated the costs of computer-based interventions compared to usual care, however two of the studies were 11 and 28 years old, and recent advances in technology render these estimates unlikely to be applicable to current or future interventions, while the third study was conducted in active duty military personnel, and it is unclear whether the costs are relevant to other settings. One weight loss study reported the cost-effectiveness ratio for a weekly in-person weight loss intervention relative to a computer-based intervention as USD 7177 (EUR 5678) per life year gained (80% CI USD 3055 to USD 60,291 (EUR 2417 to EUR 47,702)). It is unclear whether this could be extrapolated to other studies. No data were identified on adverse events, morbidity, complications or health-related quality of life. AUTHORS' CONCLUSIONS: Compared to no intervention or minimal interventions (pamphlets, usual care), interactive computer-based interventions are an effective intervention for weight loss and weight maintenance. Compared to in-person interventions, interactive computer-based interventions result in smaller weight losses and lower levels of weight maintenance. The amount of additional weight loss, however, is relatively small and of brief duration, making the clinical significance of these differences unclear.

Technology in Treatment: Are Adolescents and Counselors Interested in Online Relapse Prevention?

BACKGROUND: Approximately 75% of adolescents who receive substance abuse treatment relapse within one year; therefore, it is important to have effective, easily accessible aftercare resources to support them while they are in recovery. OBJECTIVE: The goal of this study was twofold: 1) to find out from adolescents and counselors if an online relapse prevention program was feasible and of interest and 2) to solicit ideas for content for this program regarding peer relationships during early recovery. METHODS: Sixteen counselors were interviewed about peer relationship-related content and features this program should include then asked to sort and rate the responses using an online concept mapping program. The development of an interactive prototype of the proposed program was informed by these results. This prototype was shown to the 16 counselors and 24 adolescents in substance abuse treatment (M age=15.8 years) for feedback. Then the adolescents participated in focus groups in which they discussed their use of technology and peer relationship-related challenges in recovery. RESULTS: The concepts that were rated highest by counselors were Setting Boundaries in Peer Relationships (M = 4.38), How to Follow Through with Decisions (M = 4.23), and Figuring Out What You Really Want (M = 4.18). Pre-established criteria for satisfaction were exceeded with both adolescents (M = 84%) and counselors (M = 86%). In the focus groups, adolescents said that they would be interested in using technology to meet challenges in recovery. CONCLUSIONS: The online relapse prevention program concept has feasibility according to these key stakeholders.

Identifying primary care skills and competencies in opioid risk management.

INTRODUCTION: Primary care physicians (PCPs) treat a high proportion of chronic pain patients but often lack training about how to assess and address issues associated with prescribing opioids when they are an appropriate component of therapy. The result may be that they may avoid treating these patients, which can lead to an undertreatment of pain. The objective of this study was to identify which skills and competencies are most critical for PCPs in order to effectively manage opioid risk in patients treated for chronic pain. METHODS: We conducted 1-hour interviews with 16 nationally known experts in primary care, pain management, and addiction. Eight were trained as PCPs, and 8 were trained as specialists. Their responses were collated and then presented online to the participants for independent sorting and rating. These data were analyzed using an online concept mapping program, which offers an innovative method of summarizing and prioritizing qualitative data. RESULTS: Based on this analysis, items were organized into 10 clusters representing the most critical categories of skills (the "best fit" for these data). The cluster that received the highest average statement rating was "How to Manage Pain Patients With Comorbid Conditions." Follow-up analyses indicated that specialists rated this cluster, and 5 others, significantly higher than the PCPs, suggesting that the specialists perceive these competencies as more important in opioid risk management. DISCUSSION: Using a relatively small sample and cost-effective technique (ie, concept mapping), key PCP competencies can be identified for potential inclusion in continuing education and training in opioid risk management.

Identifying the educational needs of menopausal women: a feasibility study.

BACKGROUND: The goal of this project was to identify the educational needs of menopausal women and test the feasibility of an online self management program based on social learning theory. METHODS: The four stages included 1) a needs assessment using a) focus groups with 24 women ages 40 to 55 and b) phone interviews with eight health experts; 2) the use of concept mapping methodology for quantifying qualitative data from stage 1 to identify the core programmatic concepts; 3) development of a demonstration program; and 4) a pilot study with 35 women and 9 health experts to assess knowledge gained and program satisfaction. RESULTS: Results show that women desire more information about normalcy of menopause and symptom management and found the program to meet a need for menopausal education otherwise perceived as unavailable. The women significantly increased their menopausal knowledge after brief exposure (t(34) = 3.64; p = .001). CONCLUSION: This project provides support for an online health education program for menopausal women and content ideas for inclusion in women's health education curriculum.

CHAT: development and validation of a computer-delivered, self-report, substance use assessment for adolescents.

The current study was conducted to construct and validate a computer-delivered, multimedia, substance use self-assessment for adolescents. Reliability and validity of six problem dimensions were evaluated in two studies, conducted from 2003 to 2008. Study 1 included 192 adolescents from five treatment settings throughout the United States (N = 142) and two high schools from Greater Boston, Massachusetts (N = 50). Study 2 included 356 adolescents (treatment: N = 260; school: N = 94). The final version of Comprehensive Health Assessment for Teens (CHAT) demonstrated relatively strong psychometric properties. The limitations and implications of this study are noted. This study was supported by an SBIR grant.

What arthritis pain practitioners and patients want in an online self-management programme.

OBJECTIVE: Self-management of pain is a critical component of arthritis care; however, limited mobility can restrict access to resources. Although the internet has become a primary source of health information, few studies address what patients want and need from a self-management website. METHODS: Thirty-two people diagnosed with arthritis and 12 practitioners a) participated in individual one-hour interviews and b) sorted and rated a list of 88 unique statements that were derived from the interviews. Qualitative data were analysed using concept mapping procedures. RESULTS: The six-cluster map provided the best discrimination between statements. Follow-up analyses suggested that although patients with arthritis and practitioners generally agree on the categories of content on a self-management website about arthritis, they appear to disagree on the importance of each category. CONCLUSIONS: These findings about patient and provider desired content can be used by health educators to develop a curriculum for health education of patients with arthritis pain.

Developing a database of behavioural medicine interventions.

OBJECTIVE: To describe the development of the Cochrane Behavioral Medicine Field database of interventions and its contribution to the knowledge base of this field. METHODS: A list of behavioural medicine interventions was solicited from content experts. The resulting list of index terms was used to generate a comprehensive search strategy to retrieve relevant records, and a thesaurus of terms with which to index them. The records are included in a register. A subset of records have been coded for study design, health condition, intervention, study participants, setting and provider and made available in a public online database. RESULTS: The Cochrane Behavioral Medicine Field database consists of over 3500 records of systematic reviews, meta-analyses and randomized controlled trials for public educational use. CONCLUSIONS: The register provides a comprehensive listing of studies relating to behavioural medicine interventions. The public online database enables easy access to the evidence base and provides enhanced details of the studies included on it. These databases are a valuable resource for the behavioural medicine community. Other fields are encouraged to duplicate these methods in the design of content-specific databases.

Hospitalization cost offset of a hostility intervention for coronary heart disease patients.

The authors evaluated hospitalization cost offset of hostility management group therapy for patients with coronary heart disease (CHD) from a previously published randomized controlled trial (Y. Gidron, K. Davidson, & I. Bata, 1999). Twenty-six male patients with myocardial infarction or unstable angina were randomized to either 2 months of cognitive-behavioral group therapy or an information (control) session. Therapy patients had a shorter average length of hospital stay (n = 13, M = 0.38 days, SD = 0.96) than did control patients (n = 13, M = 2.15 days, SD = 2.6), t(15.2) = -2.29, p = .04, over 6 months following therapy. The average hospitalization costs were significantly lower for therapy patients (M = 245(dollars), SD = 627(dollars)) than for control patients (M = 1,333(dollars), SD = 1,609(dollars)), t(15.6) = -2.27, p = .04. The cost-offset ratio is calculated by dividing the 1,088(dollars) of hospitalization savings by the 560(dollars) of therapy expense (1.00:1.94(dollars)), indicating that for every 1.00(dollars) spent on therapy, there is an approximate savings of 2.00(dollars) in hospitalization costs in the following 6 months. These findings support the hospitalization cost offset of hostility-reduction in CHD patients.

Gender as a health determinant and implications for health education.

Gender is a health determinant, but gender itself is influenced, in part, by biological and psychological variables. Understanding gender's influence on health therefore requires an understanding of the determinants of the construct gender. A review of certain gender determinants is presented. The authors consider the modifiability of these determinants and present recommendations about which of these determinants should be targeted for health promotion and policy creation activities. In concluding, they argue that gender is a multidetermined construct that encompasses many factors that may be modifiable through intervention, and consideration of all of these factors should be vigorously pursued.

Invitation to a dialogue between researchers and clinicians about evidence-based behavioral medicine.

BACKGROUND: Evidence-based behavioral medicine (EBBM) aims to improve the process through which best scientific research evidence can be obtained and translated into best clinical decisions regarding behavioral treatments to improve health. PURPOSE: The objective was to examine some legitimate concerns raised by both clinicians and researchers about the evidence-based movement. METHODS: This article begins with a discussion of clinicians' fears that EBBM devalues clinical judgment and the therapist-patient relationship, will be used to restrict practice, is unnecessary, and is based on research that is irrelevant to clinical decision making. Next we consider researchers' worries that EBBM neglects evidence not based on randomized controlled trials and ignores causal mechanisms. RESULTS: We find that these fears, although understandable, largely reflect misinterpretations of the evidence-based movement. Further, it is suggested that behavioral medicine is in a unique position to enhance the evidence-based movement by encouraging increased attention to treatment mechanisms and to knowledge translation. CONCLUSIONS: Clinicians, researchers, and, importantly, the public will benefit from the evidence-based movement by having a health care system that is built on solid grounds of evidence in determining which treatments should constitute the standard of care. A full partnership between clinicians and researchers is called for to generate the practical, rigorous evidence base needed to take behavioral health treatments to the next level of scientific support and implementation.

A primer on current evidence-based review systems and their implications for behavioral medicine.

BACKGROUND: Multiple review systems have been established within medicine and psychology to evaluate and disseminate research findings to clinical practice. PURPOSE: Within this article, five evidence-based review systems are reviewed to inform the development or the use of an evidence review system for the behavioral medicine field. METHODS: Each review system is described on several dimensions: history of the review system, the review process, and details about translation/sustainability efforts. RESULTS: Various factors from each system have been identified that would benefit a behavioral medicine evidence review system, such as a discussion of clinical features that influence the generalizability of review findings (i.e., the American Psychiatric Association) and the use of pre-review protocols (i.e., the Cochrane Collaboration). CONCLUSIONS: Although each review system has limitations, it is important for behavioral medicine to join one system because (a) systematic reviews are the only feasible means to evaluate and judge the usefulness of our interventions, and (b) reviews can inform policy, and, with effort, influence patient well-being. This group of behavioral medicine experts recommends that the Cochrane Collaboration review behavioral medicine interventions.