Utilization of electronic portal referrals to a community agency for children presenting with an asthma exacerbation to a pediatric emergency department.

PURPOSE: To evaluate referral rates and factors associated with referrals to a community agency for children evaluated for an asthma exacerbation at a pediatric emergency department (PED) and compare PED visits for asthma the following year between those referred and not referred. METHODS: We reviewed electronic health records of children 2-18 years evaluated in our PED from 01/01/2019 to 12/31/2019 with an ICD-10 diagnostic code for asthma (J45x) following the introduction of a portal where clinicians could refer children to a community agency focused on improving health outcomes for asthma. We abstracted data on demographics, PED visits, and hospitalizations and used multivariate logistic regression to evaluate factors associated with referrals. RESULTS: Of the 2262 charts analyzed, the majority of patients were male (61%), Black (76%), and held public insurance (71%). Only a minority of patients (n = 140, 6%) were referred. Age [6-12 years (AOR: 1.93, 95% CI: 1.21-3.08, p = .006), 13-18 years (AOR: 10.61, 95% CI: 6.53-17.24, p = .001)] and lifetime number of PED asthma visits [≥3 visits (AOR: 1.91, 95% CI, 1.01-3.62, p = .05)] were associated with referral. There was no significant difference in the mean number of PED visits in one year [referred: 0.59 (SD1.2) vs. not referred: 0.79 (SD1.3), t = 1.70, p = .09] between the two groups. CONCLUSION: The referral rate to community agency from PED for asthma is low. There was no difference in short-term PED utilization for asthma between those referred and not referred.

Evaluating barriers and facilitators to healthcare providers' use of an emergency department electronic referral portal for high-risk children with asthma using the Theoretical Domains Framework.

OBJECTIVE: Urban children with asthma are at risk for frequent emergency department (ED) visits and suboptimal asthma management. ED visits provide an opportunity for referrals to community-based asthma management services. Electronic medical record-based referral portals have been shown to improve quality of care but use of these portals by healthcare providers (HCPs) is variable. The purpose of the study was to investigate facilitators, barriers, and recommendations to improve the use of an electronic referral portal to connect children presenting with asthma exacerbations in an urban pediatric ED to community-based education and case management services. METHODS: The study was grounded in the Theoretical Domains Framework, an implementation provided the theoretical basis of the study. All ED HCPs were invited to complete qualitative interviews; twenty-three HCPs participated. Interviews were coded using directed content analysis. RESULTS: Facilitators to portal use included its relative ease of use and HCP beliefs regarding the importance of such referrals for preventive asthma care. Barriers included insufficient time to make referrals, lack of information regarding the community agency and challenges communicating the value of the referral to patients and/or their caregivers. CONCLUSIONS: Successfully engaging HCPs working in ED settings to use electronic portals to refer children with asthma to community agencies for health services may involve helping providers increase their comfort and knowledge of the external provider agency, ensuring organizational leaders support the need for preventive asthma care and provision of feedback to HCPs on the success of such referrals in meeting the needs of those families served.

Diabetes distress in urban Black youth with type 1 diabetes and their caregivers: associations with glycemic control, depression, and health behaviors.

OBJECTIVES: Adolescents with type 1 diabetes (T1D) and their caregivers endorse high diabetes distress (DD). Limited studies have documented the impact of DD on Black youth. The aims of the present study were to (1) describe DD among a sample of Black adolescents with T1D and their caregivers, (2) compare their DD levels with published normative samples, and (3) determine how DD relates to glycemic outcomes, diabetes self-management, parental monitoring of diabetes, and youth depressive symptoms. METHODS: Baseline data from a multicenter clinical trial were used. Participants (N = 155) were recruited from 7 Midwestern pediatric diabetes clinics. Hemoglobin A1c (HbA1c) and measures of DD, parental monitoring of diabetes care, youth depression and diabetes management behaviors were obtained. The sample was split into (1) adolescents (ages 13-14; N = 95) and (2) preadolescents (ages 10-12; N = 60). Analyses utilized Cohen's d effect sizes, Pearson correlations, t-tests, and multiple regression. RESULTS: DD levels in youth and caregivers were high, with 45%-58% exceeding either clinical cutoff scores or validation study sample means. Higher DD in youth and caregivers was associated with higher HbA1c, lower diabetes self-management, and elevated depressive symptoms, but not with parental monitoring of diabetes management. CONCLUSIONS: Screening for DD in Black youth with T1D and caregivers is recommended, as are culturally informed interventions that can reduce distress levels and lead to improved health outcomes. More research is needed on how systemic inequities contribute to higher DD in Black youth and the strategies/policy changes needed to reduce these inequities.

The moderating role of diabetes distress on the effect of a randomized eHealth intervention on glycemic control in Black adolescents with type 1 diabetes.

OBJECTIVE: Due to systemic inequities, Black adolescents with type 1 diabetes are more likely to have suboptimal glycemic control and high rates of diabetes distress, but tailored interventions for this population are lacking. In primary outcomes of a randomized clinical trial, a family-based eHealth intervention improved glycemic control in Black adolescents with type 1 diabetes and elevated depressive symptoms. The present study is a secondary analysis of these clinical trial data examining the moderating effect of diabetes distress on the efficacy of the intervention. METHODS: Using secondary data from a multicenter randomized clinical trial (Clinicaltrials.gov [NCT03168867]), caregiver-adolescent dyads were randomly assigned to either up to three sessions of an eHealth parenting intervention (n = 75) or a standard medical care control group (n = 74). Black adolescents (10 years, 0 months to 14 years, 11 months old) with type 1 diabetes and a caregiver willing to participate were eligible. Adolescents reported their diabetes distress at baseline, and hemoglobin A1c (HbA1c) data were collected at baseline, 6-, 13-, and 18-month follow-up. RESULTS: No between-group contrasts emerged in a linear mixed-effects regression (p's > .09). Within-group contrasts emerged such that adolescents assigned to the intervention who reported high diabetes distress had lower HbA1c at the 18-month follow-up relative to baseline (p = .004); the 18-month decrease in HbA1c was -1.03%. CONCLUSIONS: Black adolescents with type 1 diabetes and high levels of diabetes distress showed significant decreases in HbA1c following a family-based eHealth intervention, suggesting diabetes distress may be a key moderator of intervention efficacy within this population.

Tailored Motivational Interviewing (TMI): A Pilot Implementation-Effectiveness Trial to Promote MI Competence in Adolescent HIV Clinics.

This brief report describes results of piloted Tailored Motivational Interviewing (TMI). Tailoring focused on site-specific training needs, target patient behaviors, and implementation facilitators and barriers that staff anticipated. Participating staff (N = 31) at two adolescent HIV clinics completed a pre-training qualitative interview (N = 27), and MI competency assessments based on three pre- and six post-training standard patient role-plays (N = 27). Results included pre- to post-training MI competence improvement (t (153) = - 4.13, p ≤ 0.001) and change in competency category distribution (X2 = (2, N = 155) = 15.72, p ≤ 0.001), providing initial support for the implementation of TMI in adolescent HIV clinic settings.

Using the Exploration-Preparation-Implementation-Sustainment (EPIS) Framework to prepare for the implementation of evidence-based practices into adolescent HIV settings.

Despite advances in evidence-based practices (EBP) to support HIV prevention and treatment, youth ages 13-24 experience significant disparities in HIV risk and outcomes. An important factor in this disparity is poor EBP implementation, yet implementation research is limited, particularly in youth-serving settings. This study used the Exploration, Preparation, Implementation, Sustainment (EPIS) framework to guide the implementation of four Motivational Interviewing (MI) and MI-framed interventions into youth-serving HIV prevention and treatment settings. Key stakeholders (n = 153) across 13 sites completed pre-implementation interviews. Stakeholders' comments identified two critical factors for effective implementation: fit with the patient population and provider receptivity, including concerns about scope of practice, buy-in, and time. Stakeholders recommended strategies for structuring training, fidelity monitoring, and facilitating implementation including engaging informal leaders, collaboratively developing the implementation strategy, and site-wide implementation. Results highlight the importance of pre-implementation contextual assessment and strategic planning for identifying provider concerns and developing responsive implementation strategies.

RESUMEN: A pesar de los avances en las prácticas basadas en evidencia (EBP, por sus siglas en inglés) para apoyar la prevención y el tratamiento del VIH, los jóvenes de 13 a 24 años atraviesan disparidades significativas en el riesgo y los desenlaces del VIH. Un factor importante en esta disparidad es la implementación deficiente de las EBP, aunque la investigación sobre la implementación es limitada, particularmente en entornos que atienden a jóvenes. Este estudio utilizó el marco de Exploración, Preparación, Implementación, Mantenimiento (EPIS) para guiar la implementación de cuatro entrevistas motivacionales (MI) e intervenciones enmarcadas en MI en entornos de prevención y tratamiento del VIH que atienden a jóvenes. Las partes interesadas clave (n = 153) en 13 sitios completaron las entrevistas previas a la implementación. Los comentarios de las partes interesadas identificaron dos factores críticos para una implementación efectiva: idoneidad para la población de pacientes y receptividad de los proveedores, incluidas las preocupaciones sobre el alcance de la práctica, la aceptación y el tiempo. Las partes interesadas recomendaron estrategias para estructurar la capacitación, monitorear la fidelidad, y facilitar la implementación, incluyendo la participación de líderes informales, el desarrollo colaborativo de la estrategia de implementación y la implementación en todo el sitio. Los resultados destacan la importancia de la evaluación contextual previa a la implementación y la planificación estratégica para identificar las preocupaciones de los proveedores y desarrollar estrategias de implementación que respondan a ellas.

Technology-Delivered Adaptations of Motivational Interviewing for the Prevention and Management of Chronic Diseases: Scoping Review.

BACKGROUND: Motivational interviewing (MI) can increase health-promoting behaviors and decrease health-damaging behaviors. However, MI is often resource intensive, precluding its use with people with limited financial or time resources. Mobile health-based versions of MI interventions or technology-delivered adaptations of MI (TAMIs) might increase reach. OBJECTIVE: We aimed to understand the characteristics of existing TAMIs. We were particularly interested in the inclusion of people from marginalized sociodemographic groups, whether the TAMI addressed sociocontextual factors, and how behavioral and health outcomes were reported. METHODS: We employed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines for scoping reviews to conduct our scoping review. We searched PubMed, CINAHL, and PsycInfo from January 1, 1996, to April 6, 2022, to identify studies that described interventions incorporating MI into a mobile or electronic health platform. For inclusion, the study was required to (1) describe methods/outcomes of an MI intervention, (2) feature an intervention delivered automatically via a mobile or electronic health platform, and (3) report a behavioral or health outcome. The exclusion criteria were (1) publication in a language other than English and (2) description of only in-person intervention delivery (ie, no TAMI). We charted results using Excel (Microsoft Corp). RESULTS: Thirty-four studies reported the use of TAMIs. Sample sizes ranged from 10 to 2069 participants aged 13 to 70 years. Most studies (n=27) directed interventions toward individuals engaging in behaviors that increased chronic disease risk. Most studies (n=22) oversampled individuals from marginalized sociodemographic groups, but few (n=3) were designed specifically with marginalized groups in mind. TAMIs used text messaging (n=8), web-based intervention (n=22), app + text messaging (n=1), and web-based intervention + text messaging (n=3) as delivery platforms. Of the 34 studies, 30 (88%) were randomized controlled trials reporting behavioral and health-related outcomes, 23 of which reported statistically significant improvements in targeted behaviors with TAMI use. TAMIs improved targeted health behaviors in the remaining 4 studies. Moreover, 11 (32%) studies assessed TAMI feasibility, acceptability, or satisfaction, and all rated TAMIs highly in this regard. Among 20 studies with a disproportionately high number of people from marginalized racial or ethnic groups compared with the general US population, 16 (80%) reported increased engagement in health behaviors or better health outcomes. However, no TAMIs included elements that addressed sociocontextual influences on behavior or health outcomes. CONCLUSIONS: Our findings suggest that TAMIs may improve some health promotion and disease management behaviors. However, few TAMIs were designed specifically for people from marginalized sociodemographic groups, and none included elements to help address sociocontextual challenges. Research is needed to determine how TAMIs affect individual health outcomes and how to incorporate elements that address sociocontextual factors, and to identify the best practices for implementing TAMIs into clinical practice.

Effects of family and neighborhood risks on glycemic control among young black adolescents with type 1 diabetes: Findings from a multi-center study.

While individual and family risk factors that contribute to health disparities in children with type 1 diabetes have been identified, studies on the effects of neighborhood risk factors on glycemic control are limited, particularly in minority samples. This cross-sectional study tested associations between family conflict, neighborhood adversity and glycemic outcomes (HbA1c) in a sample of urban, young Black adolescents with type 1 diabetes(mean age = 13.4 ± 1.7), as well as whether neighborhood adversity moderated the relationship between family conflict and HbA1c. Participants (N = 128) were recruited from five pediatric diabetes clinics in two major metropolitan US cities. Diabetes-related family conflict was measured via self-report questionnaire (Diabetes Family Conflict Scale; DFCS). Neighborhood adversity was calculated at the census block group level based on US census data. Indictors of adversity were used to calculate a neighborhood adversity index (NAI) for each participant. Median family income was $25,000, suggesting a low SES sample. In multiple regression analyses, DFCS and NAI both had significant, independent effects on glycemic control (ß = 0.174, P = 0.034 and ß = 0.226 P = 0.013, respectively) after controlling for child age, family socioeconomic status and insulin management regimen. Tests of effects of the NAI and DFCS interaction on HbA1c found no significant moderating effects of neighborhood adversity. Even within contexts of significant socioeconomic disadvantage, variability in degree of neighborhood adversity predicts diabetes-related health outcomes in young Black adolescents with type 1 diabetes. Providers should assess social determinants of health such as neighborhood resources that may impact adolescents' ability to maintain optimal glycemic control.

Optimizing Recruitment of Black Adolescents into Behavioral Research: A Multi-Center Study.

OBJECTIVES: Adolescents of color are underrepresented in behavioral health research. Study aims were to quantify the amount and types of outreach effort needed to recruit young Black adolescents with type 1 diabetes and their primary caregiver into a clinical trial evaluating a parenting intervention and to determine if degree of recruitment difficulty was related to demographic, diabetes-related, or family characteristics. METHODS: Data were drawn from a multi-center clinical trial. Participants (N = 155) were recruited from seven pediatric diabetes clinics. Contact log data were used to quantify both number/type of contacts prior to study enrollment as well as length of time to enrollment. Families were coded as having expedited recruitment (ER) or prolonged recruitment (PR). Baseline study data were used to compare ER and PR families on sociodemographic factors, adolescent diabetes management and health status and family characteristics such as household organization and family conflict. RESULTS: Mean length of time to recruit was 6.6 months and mean number of recruitment contacts was 10.3. Thirty-nine percent of the sample were characterized as PR. These families required even higher levels of effort (mean of 9.9 months to recruit and 15.4 contacts). There were no significant between-group differences on any baseline variable for ER and PR families, with the exception of family income. CONCLUSIONS: Researchers need to make persistent efforts in order to successfully enroll adolescents of color and their caregivers into clinical trials. Social determinants of health such as family resources may differentiate families with prolonged recruitment within such samples.

Provider behaviors that predict motivational statements in adolescents and young adults with HIV: a study of clinical communication using the Motivational Interviewing framework.

Medical care providers' use of Motivational Interviewing (MI) is linked to improved medication adherence, viral load, and associated behaviors in adolescents and young adults living with HIV. Mastering MI is difficult for busy providers; however, tailoring MI training to the specific MI communication strategies most relevant for HIV treatment context may be a strategy to increase proficiency. The present study aimed to identify communication strategies likely to elicit motivational statements among adolescent-young adult patients living with HIV. Language used by MI-exposed providers during 80 HIV medical clinic visits was transcribed and coded to characterize patient-provider communication within the MI framework. Sequential analysis, an approach to establish empirical support for the order of behavioral events, found patients were more likely to express motivational statements after provider questions phrased to elicit motivation, reflections of motivational statements, and statements emphasizing patients' decision-making autonomy. Patients were more likely to express amotivational statements when providers asked questions phrased to elicit amotivational statements or reflected amotivational language. Training providers to strategically phrase their questions and reflections to elicit change language and to emphasize patients' autonomy may be critical skills for working with adolescents and young adults living with HIV.

Outcomes From a Sequential Multiple Assignment Randomized Trial of Weight Loss Strategies for African American Adolescents With Obesity.

BACKGROUND: Minority adolescents are at highest risk for obesity and extreme obesity; yet, there are few clinical trials targeting African American adolescents with obesity. PURPOSE: The purpose of the study was to develop an adaptive family-based behavioral obesity treatment for African American adolescents using a sequential multiple assignment randomized trial (SMART) design. METHODS: Fit Families was a SMART where 181 African American adolescents (67% female) aged 12-17 were first randomized to office-based versus home-based behavioral skills treatment delivered from a Motivational Interviewing foundation. After 3 months, nonresponders to first phase treatment were rerandomized to continued home-based behavioral skills treatment or contingency management with voucher-based reinforcement for adolescent weight loss and for caregiver adherence to the program. All interventions were delivered by community health workers. The primary outcome was treatment retention and percent overweight. RESULTS: All adolescents reduced percent overweight by -3.20%; there were no significant differences in percent overweight based on treatment sequence. Adolescents receiving home-based delivery in Phase 1 and contingency management in Phase 2 completed significantly more sessions than those receiving office-based treatment and continued skills without CM (M = 8.03, SD = 3.24 and M = 6.62, SD = 2.95, respectively). The effect of contingency management was strongest among older and those with lower baseline confidence. Younger adolescents experienced greater weight reductions when receiving continued skills (-4.90% compared with -.02%). CONCLUSIONS: Behavioral skills training can be successfully delivered to African American adolescents with obesity and their caregivers by community health workers when using a home-based service model with incentives. More potent interventions are needed to increase reductions in percent overweight and may need to be developmentally tailored for younger and older adolescents.

Efficacy of mindfulness-based stress reduction in emerging adults with poorly controlled, type 1 diabetes: A pilot randomized controlled trial.

BACKGROUND/OBJECTIVE: The negative effects of stress on persons with type 1 diabetes (T1D) are well-established, but effective interventions to reduce stress among emerging adults with T1D are limited. The study objective was to conduct a pilot randomized controlled trial (RCT) to obtain preliminary data on the efficacy of mindfulness-based stress reduction (MBSR) to reduce stress and improve diabetes health outcomes in a population of high-risk, urban emerging adults with poorly controlled diabetes. METHODS: Forty-eight participants aged 16 to 20 years of age with T1D (mean duration = 8 years) were randomly assigned to one of three conditions: MSBR, cognitive-behavioral stress management (CBSM), or a diabetes support group. Data were collected at baseline, end of treatment, and 3 months after treatment completion. Measures of self-reported stress and depressive symptoms, diabetes management, and glycemic control were obtained. RESULTS: MBSR was found to reduce self-reported stress at end of treatment (P = 0.03, d = -0.49) and 3-month follow-up (P = 0.01, d = -0.67), but no effects on diabetes management or glycemic control were found. Diabetes support group participants had improved glycemic control at the end of treatment (P = 0.01, d = -0.62) as well as reduced depressive symptoms at 3-month follow-up (P = 0.01, d = -0.71). CONCLUSIONS: Results provide preliminary support for the efficacy of MBSR to improve psychosocial adjustment in emerging adults with poorly controlled T1D but require replication in adequately powered studies. Findings also support the value of peer support in improving health outcomes in this age group.

Adaptation of an Evidence-Based Diabetes Management Intervention for Delivery in Community Settings: Findings From a Pilot Randomized Effectiveness Trial.

Objective: To adapt an evidence-based intervention targeting diabetes management in adolescents with poorly controlled type 1 diabetes for use in a community setting by community health workers (CHWs) and to conduct pilot testing of the new intervention, REACH for Control (RFC). The study was conducted as a collaboration between university researchers and a federally qualified health center. Methods In a pilot effectiveness trial, feasibility and acceptability of RFC were evaluated based on participant enrollment, treatment dose, and consumer satisfaction. RFC effects on adolescent adherence, health outcomes, and quality of life were also assessed. The trial used a parallel group design. Families were randomized to 6 months of RFC plus standard medical care (n = 26) or standard care (SC) only (n = 24). Data were collected at baseline and 7-month posttest. A mixed-methods approach was used to analyze data. Results: Qualitative analyses suggested that caregivers viewed RFC and delivery of a home-based intervention by CHWs positively. Furthermore, adolescents who received RFC had statistically significant (p = .05) and clinically meaningful improvements in hemoglobin A1c (HbA1c) (0.7%) and reported significant improvements in quality of life from baseline to follow-up (p = .001). No significant changes were found for adolescents in standard medical care. However, while dose of primary intervention session delivered was acceptable, dose of follow-up sessions used for skills practice was low. Conclusions: Results provide preliminary support for RFC's acceptability and effectiveness to improve health status and quality of life when used in community settings serving high-risk, low-income families. Additional testing in a full-scale effectiveness trial appears warranted.

Developing Machine Learning Models for Behavioral Coding.

OBJECTIVE: The goal of this research is to develop a machine learning supervised classification model to automatically code clinical encounter transcripts using a behavioral code scheme. METHODS: We first evaluated the efficacy of eight state-of-the-art machine learning classification models to recognize patient-provider communication behaviors operationalized by the motivational interviewing framework. Data were collected during the course of a single weight loss intervention session with 37 African American adolescents and their caregivers. We then tested the transferability of the model to a novel treatment context, 80 patient-provider interactions during routine human immunodeficiency virus (HIV) clinic visits. RESULTS: Of the eight models tested, the support vector machine model demonstrated the best performance, achieving a .680 F1-score (a function of model precision and recall) in adolescent and .639 in caregiver sessions. Adding semantic and contextual features improved accuracy with 75.1% of utterances in adolescent and 73.8% in caregiver sessions correctly coded. With no modification, the model correctly classified 72.0% of patient-provider utterances in HIV clinical encounters with reliability comparable to human coders (k = .639). CONCLUSIONS: The development of a validated approach for automatic behavioral coding offers an efficient alternative to traditional, resource-intensive methods with the potential to dramatically accelerate the pace of outcomes-oriented behavioral research. The knowledge gained from computer-driven behavioral research can inform clinical practice by providing clinicians with empirically supported communication strategies to tailor their conversations with patients. Lastly, automatic behavioral coding is a critical first step toward fully automated eHealth/mHealth (electronic/mobile Health) behavioral interventions.

Building Motivation in African American Caregivers of Adolescents With Obesity: Application of Sequential Analysis.

Objective: We sought to examine communication between counselors and caregivers of adolescents with obesity to determine what types of counselor behaviors increased caregivers' motivational statements regarding supporting their child's weight loss. Methods: We coded 20-min Motivational Interviewing sessions with 37 caregivers of African American 12-16-year-olds using the Minority Youth Sequential Coding for Observing Process Exchanges. We used sequential analysis to determine which counselor communication codes predicted caregiver motivational statements. Results: Counselors' questions to elicit motivational statements and emphasis on autonomy increased the likelihood of both caregiver change talk and commitment language statements. Counselors' reflections of change talk predicted further change talk, and reflections of commitment language predicted more commitment language. Conclusions: When working to increase motivation among caregivers of adolescents with overweight or obesity, providers should strive to reflect motivational statements, ask questions to elicit motivational statements, and emphasize caregivers' autonomy.

Brief Computer-Delivered Intervention to Increase Parental Monitoring in Families of African American Adolescents with Type 1 Diabetes: A Randomized Controlled Trial.

BACKGROUND: African American adolescents with type 1 diabetes (T1D) are at elevated risk for poor diabetes management and metabolic control. Parental supervision and monitoring of adolescent diabetes management have been shown to promote better diabetes management among adolescents, but parents typically decrease their oversight during the transition to independent diabetes care. INTRODUCTION: The purpose of the study was to conduct a randomized clinical trial to test the feasibility and efficacy of a three-session, computer-delivered motivational intervention (The 3Ms) to promote increased parental monitoring among primary caregivers of young African American adolescents with T1D. The intervention was brief and optimized for delivery during routine diabetes clinic visits. MATERIALS AND METHODS: Sixty-seven adolescents with T1D aged 11-14 and their primary caregiver were randomly assigned to one of three arms: adolescent and parent motivational intervention (Arm 1), adolescent control and parent motivational intervention (Arm 2), or adolescent and parent control (Arm 3). Intervention effects were assessed 1 month after intervention completion. RESULTS: Parents in Arm 1 and Arm 2 had significant increases in knowledge of the importance of monitoring adolescents' diabetes care. Parents in Arm 2 also had trend to significant increases in direct observation and monitoring of adolescent diabetes care, and adolescents in Arm 2 had significant improvements in glycemic control. DISCUSSION AND CONCLUSIONS: Findings from the present study provide preliminary support for the efficacy of a brief, computer-delivered parenting intervention for improving family management practices and adolescent health outcomes among African American adolescents with T1D and their caregivers.

A study of the effectiveness of machine learning methods for classification of clinical interview fragments into a large number of categories.

This study examines the effectiveness of state-of-the-art supervised machine learning methods in conjunction with different feature types for the task of automatic annotation of fragments of clinical text based on codebooks with a large number of categories. We used a collection of motivational interview transcripts consisting of 11,353 utterances, which were manually annotated by two human coders as the gold standard, and experimented with state-of-art classifiers, including Naïve Bayes, J48 Decision Tree, Support Vector Machine (SVM), Random Forest (RF), AdaBoost, DiscLDA, Conditional Random Fields (CRF) and Convolutional Neural Network (CNN) in conjunction with lexical, contextual (label of the previous utterance) and semantic (distribution of words in the utterance across the Linguistic Inquiry and Word Count dictionaries) features. We found out that, when the number of classes is large, the performance of CNN and CRF is inferior to SVM. When only lexical features were used, interview transcripts were automatically annotated by SVM with the highest classification accuracy among all classifiers of 70.8%, 61% and 53.7% based on the codebooks consisting of 17, 20 and 41 codes, respectively. Using contextual and semantic features, as well as their combination, in addition to lexical ones, improved the accuracy of SVM for annotation of utterances in motivational interview transcripts with a codebook consisting of 17 classes to 71.5%, 74.2%, and 75.1%, respectively. Our results demonstrate the potential of using machine learning methods in conjunction with lexical, semantic and contextual features for automatic annotation of clinical interview transcripts with near-human accuracy.

Sequential Multiple Assignment Randomized Trial (SMART) to Construct Weight Loss Interventions for African American Adolescents.

The purpose of this study was to develop an adaptive behavioral treatment for African American adolescents with obesity. In a sequential multiple assignment randomized trial, 181 youth ages 12-16 years with primary obesity and their caregiver were first randomized to 3 months of home-based versus office-based delivery of motivational interviewing plus skills building. After 3 months, nonresponders to first phase treatment were rerandomized to continued home-based skills or contingency management. Primary outcome was percent overweight and hypothesized moderators were adolescent executive functioning and depression. There were no significant differences in primary outcome between home-based or office-based delivery or between continued home-based skills or contingency management for nonresponders to first-phase treatment. However, families receiving home-based treatment initially attended significantly more sessions in both phases of the trial, and families receiving contingency management attended more sessions in the second phase. Overall, participants demonstrated decreases in percent overweight over the course of the trial (3%), and adolescent executive functioning moderated this effect such that those with higher functioning lost more weight. More potent behavioral treatments to address the obesity epidemic are necessary, targeting new areas such as executive functioning. Delivering treatment in the home with contingency management may increase session attendance for this population.

Multisystemic Therapy Improves the Patient-Provider Relationship in Families of Adolescents with Poorly Controlled Insulin Dependent Diabetes.

The purpose of this study was to determine if multisystemic therapy (MST), an intensive, home and community-based family treatment, significantly improved patient-provider relationships in families where youth had chronic poor glycemic control. One hundred forty-six adolescents with type 1 or 2 diabetes in chronic poor glycemic control (HbA1c ≥8 %) and their primary caregivers were randomly assigned to MST or a telephone support condition. Caregiver perceptions of their relationship with the diabetes multidisciplinary medical team were assessed at baseline and treatment termination with the Measure of Process of Care-20. At treatment termination, MST families reported significant improvement on the Coordinated and Comprehensive Care scale and marginally significant improvement on the Respectful and Supportive Care scale. Improvements on the Enabling and Partnership and Providing Specific Information scales were not significant. Results suggest MST improves the ability of the families and the diabetes treatment providers to work together.

Neural Conversational Agent for Weight Loss Counseling: Protocol for an Implementation and Feasibility Study.

BACKGROUND: Obesity is a common, serious and costly chronic disease. Current clinical practice guidelines recommend that providers augment the longitudinal care of people living with obesity with consistent support for the development of self-efficacy and motivation to modify their lifestyle behaviors. Lifestyle behavior change aligns with the goals of motivational interviewing (MI), a client-centered yet directive counseling modality. However, training health care providers to be proficient in MI is expensive and time-consuming, resulting in a lack of trained counselors and limiting the widespread adoption of MI in clinical practice. Artificial intelligence (AI) counselors accessible via the internet can help circumvent these barriers. OBJECTIVE: The primary objective is to explore the feasibility of conducting unscripted MI-consistent counseling using Neural Agent for Obesity Motivational Interviewing (NAOMI), a large language model (LLM)-based web app for weight loss counseling. The secondary objectives are to test the acceptability and usability of NAOMI's counseling and examine its ability to shift motivational precursors in a sample of patients with overweight and obesity recruited from primary care clinics. METHODS: NAOMI will be developed based on recent advances in deep learning in four stages. In stages 1 and 2, NAOMI will be implemented using an open-source foundation LLM and (1) few-shot learning based on a prompt with task-specific instructions and (2) domain adaptation strategy based on fine-tuning LLM using a large corpus of general psychotherapy and MI treatment transcripts. In stages 3 and 4, we will refine the best of these 2 approaches. Each NAOMI version will be evaluated using a mixed methods approach in which 10 adults (18-65 years) meeting the criteria for overweight or obesity (25.0≥BMI≤39.9) interact with NAOMI and provide feedback. NAOMI's fidelity to the MI framework will be assessed using the Motivational Interviewing Treatment Integrity scale. Participants' general perceptions of AI conversational agents and NAOMI specifically will be assessed via Pre- and Post-Interaction Questionnaires. Motivational precursors, such as participants' confidence, importance, and readiness for changing lifestyle behaviors (eg, diet and activity), will be measured before and after the interaction, and 1 week later. A qualitative analysis of changes in the measures of perceptions of AI agents and counselors and motivational precursors will be performed. Participants will rate NAOMI's usability and empathic skills post interaction via questionnaire-based assessments along with providing feedback about their experience with NAOMI via a qualitative interview. RESULTS: NAOMI (version 1.0) has been developed. Participant recruitment will commence in September 2024. Data collection activities are expected to conclude in May 2025. CONCLUSIONS: If proven effective, LLM-based counseling agents can become a cost-effective approach for addressing the obesity epidemic at a public health level. They can also have a broad, transformative impact on the delivery of MI and other psychotherapeutic treatment modalities extending their reach and broadening access. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/60361.