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.

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.

Tailored motivational interviewing (TMI): Translating basic science in skills acquisition into a behavioral intervention to improve community health worker motivational interviewing competence for youth living with HIV.

Objective: Interventions to promote evidence-based practices are particularly needed for paraprofessional staff working with minority youth with HIV who have higher rates of HIV infection but lower rates of linkage and retention in care compared to older adults. Utilizing the ORBIT model for behavioral intervention development, we defined and refined a behavioral intervention for providers, Tailored Motivational Interviewing (TMI), to improve provider competence in previous studies (Phase 1a and 1b). The current study focuses on ORBIT Phase 2a-proof of concept. We hypothesized that TMI would be acceptable and feasible and would show a signal of efficacy of improving and maintaining community health worker (CHW) MI competence scores using an innovative statistical method for small N proof-of-concept studies. Method: Longitudinal data were collected from 19 CHWs at 16 youth HIV agencies. CHWs from 8 sites were assigned to the TMI group per the cofunders request. The remaining 8 sites were randomly assigned to TMI or services as usual. MI competence was assessed at baseline and up to 15 times over 2 years. Random coefficient models were utilized to examine time trajectories of competence scores and the impact of the intervention on competence trajectories. Semistructured interviews were conducted to determine barriers and facilitators of TMI. Results: Competence scores in the TMI group significantly increased while the scores of the control group significantly decreased. Further analysis of the intervention group demonstrated that scores significantly increased during the first 3 months after initial workshop and was sustained through the end of the study. Qualitative findings revealed insufficient time and competing priorities as perceived barriers whereas integrating MI into routine agency practices and ongoing training might facilitate implementation. Conclusions: Following a successful proof-of-concept, the next step is a fully randomized pilot study of TMI relative to a control condition in preparation for a stepped-wedge cluster randomized full scale trial. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

African-American Adolescents' Weight Loss Skills Utilization: Effects on Weight Change in a Sequential Multiple Assignment Randomized Trial.

OBJECTIVE: Successful weight loss interventions for African-Americans adolescents are lacking. Cognitive-behavioral interventions seek to develop weight loss skills (e.g., counting calories, goal setting, managing one's environment). Little is known about how well adolescents implement such skills in their daily lives. Study aims were to (1) examine weight loss skills utilization at midpoint and end of a 6-month cognitive-behavioral/motivational interviewing weight loss sequential multiple assignment randomized trial (SMART), and (2) determine if greater skill utilization predicted weight loss at treatment end and 3 months post-treatment. METHOD: One hundred and eighty six African-Americans adolescents with obesity and their caregiver were first randomly assigned to complete 3 months of cognitive-behavioral and motivational interviewing family-based weight loss treatment in their home or in the research office (Phase 1). Nonresponders (i.e., those who lost < 3% of initial weight, n = 161) were rerandomized to 3 months of continued skills training (n = 83) or contingency management (n = 78) for Phase 2; responders were allocated to 3 months of relapse prevention (n = 20). Adolescents' frequency of weight loss skills utilization was assessed via questionnaire at treatment midpoint and end. RESULTS: Higher treatment attendance was associated with better skill utilization. Higher skill utilization was associated with more weight loss at treatment end, whereas higher baseline confidence was associated with more weight loss at follow-up. CONCLUSIONS: This study indicates the importance of attending weight loss intervention sessions to develop and strengthen weight loss skills in African-American adolescents with obesity, and strengthening confidence to use such skills for continued weight loss.

From the Classroom to Entrustment - The Development of Motivational Interviewing Skills as an Entrustable Professional Activity.

This article was migrated. The article was marked as recommended. Introduction The move towards value-based care and population health has highlighted the prominent role of social and behavioral factors in determining health outcomes. Patient-centered behavioral guidance to improve patient self-management is recognized as an evidence-based intervention for a variety of chronic conditions but has yet to be adopted as a core competency or core entrustable professional activity (EPA). Motivational Interviewing (MI) is an evidence-based behavioral intervention involving an integrated set of competencies, featuring reflective listening, affirmation, evocation, and collaborative planning. An MI encounter is an observable, discrete task that can be framed as an EPA. Successful implementation of EPAs in the workplace requires institutional engagement, a thoughtful curricular approach, faculty development, and feasible, valid workplace-based assessment (WBA). Methods We implemented competency-based MI training and assessed competency outcomes for students and faculty. After joining the Association of American Medical Colleges Core EPA Pilot, we applied an iterative group process to develop an EPA and workplace-based assessment based on established MI competencies. Results Drawing upon nine years of developing MI curriculum, we present competency data for a student training study and a faculty coaching study, describe how we transitioned training from the classroom to the clinical setting employing an EPA framework, and present a one-page schematic and related WBA for an EPA based on MI. Conclusion We propose that MI is a core EPA for future physicians practicing value-based care, and offer a roadmap for curriculum implementation.

A comparison of snack serving sizes to USDA guidelines in healthy weight and overweight minority preschool children enrolled in Head Start.

BACKGROUND: Obesity disproportionately affects children from low-income families and those from racial and ethnic minorities. The relationship between snacking and weight status remains unclear, although snacking is known to be an important eating episode for energy and nutrient intake particularly in young children. The purpose of this pilot study was to examine the snack intake of minority preschool children enrolled in the Head Start Program in four centers in Detroit, Michigan, and investigate differences by child weight status. METHODS: This secondary data analysis used snack time food observation and anthropometric data from a convenience sample of 55 African American children (44 % girls, mean age = 3.8 years). Snack intake data was obtained over a mean of 5 days through direct observation of children by dietetic interns, and later converted into food group servings according to the United States Department of Agriculture (USDA) meal patterns and averaged for each child. Height and weight measurements were systematically collected and BMI-for-age percentiles were used to classify children into weight categories. One sample, paired samples and independent samples t-tests were performed to test for differences within and between means. RESULTS: Based on BMI-for-age percentiles, 72.7 % of the sample was under/healthy weight and 27.3 % was overweight/obese. Average (mean ± SD) intake of milk (0.76 ± 0.34) and overall fruits/vegetables (0.77 ± 0.34) was significantly lower than one USDA serving, while average intake of grains and breads (2.04 ± 0.89), meat/meat alternates (2.20 ± 1.89) and other foods (1.43 ± 1.08) was significantly higher than one USDA serving (p ≤ 0.05). Children ate more when offered canned versus fresh fruits (0.93 ± 0.57 vs. 0.65 ± 0.37, p = 0.007). Except for a significantly higher milk intake in the overweight/obese group compared to the under/healthy weight group (0.86 ± 0.48 vs. 0.72 ± 0.27, p = 0.021], no relationship was found between snack food intake and weight category. Only in the overweight/obese group was the intake of milk and fresh fruits not significantly different than one USDA serving. CONCLUSIONS: Findings suggest that regardless of weight status low-income minority preschool children are consuming larger serving sizes when offered less healthy versus healthier snack foods. Continued efforts should be made to provide healthful snack foods at preschool settings to prevent obesity and promote healthier food habits.

Exploring ambivalence in motivational interviewing with obese African American adolescents and their caregivers: A mixed methods analysis.

OBJECTIVE: We conducted an exploratory mixed methods study to describe the ambivalence African-American adolescents and their caregivers expressed during motivational interviewing sessions targeting weight loss. METHODS: We extracted ambivalence statements from 37 previously coded counseling sessions. We used directed content analysis to categorize ambivalence related to the target behaviors of nutrition, activity, or weight. We compared adolescent-caregiver dyads' ambivalence using the paired sample t-test and Wilcoxon signed-rank test. We then used conventional content analysis to compare the specific content of adolescents' and caregivers' ambivalence statements. RESULTS: Adolescents and caregivers expressed the same number of ambivalence statements overall, related to activity and weight, but caregivers expressed more statements about nutrition. Content analysis revealed convergences and divergences in caregivers' and adolescents' ambivalence about weight loss. CONCLUSION: Understanding divergences in adolescent-caregiver ambivalence about the specific behaviors to target may partially explain the limited success of family-based weight loss interventions targeting African American families and provides a unique opportunity for providers to enhance family communication, foster teamwork, and build self-efficacy to promote behavior change. PRACTICE IMPLICATIONS: Clinicians working in family contexts should explore how adolescents and caregivers converge and diverge in their ambivalence in order to recommend weight loss strategies that best meet families' needs.

Effective Patient-Provider Communication in Pediatric Obesity.

Effective patient-provider communication is not a primary focus of medical school curricula. Motivational interviewing (MI) is a patient-centered, directive communication framework appropriate for in health care. Research on MI's causal mechanisms has established patient change talk as a mediator of behavior change. Current MI research focuses on identifying which provider communication skills are responsible for evoking change talk. MI recommends informing, asking, and listening. Research provides evidence that asking for and reflecting patient change talk are effective communication strategies, but cautions providers to inform judiciously. Supporting a patient's decision making autonomy is an important strategy to promote health behaviors.

Advanced Patient-Centered Communication for Health Behavior Change: Motivational Interviewing Workshops for Medical Learners.

INTRODUCTION: Medical settings are critical access points for behavior change counseling, and lifestyle behavior change is considered a key component of chronic disease management. The Association of American Medical Colleges recommends that future physicians be competent in shared decision making and patient-centered behavioral guidance to prevent illness and improve patient self-management of chronic disease. Motivational interviewing (MI) is a patient-centered, directive method of communication to enhance behavior change. Specific teachable strategies underlie the collaborative MI communication style that aims to reduce discord and build motivation for change. METHODS: We present our three-session 12-hour MI curriculum as an advanced form of patient-centered communication. Each session includes presession assignment, large-group interactive lecture, and small-group activities for practice. An interdisciplinary team consisting of medical educators and health behavior change research-educators who are also members of the Motivational Interviewing Network of Trainers created the submission. The purpose of this resource is to provide medical educators with a short curriculum that incorporates materials and learning activities to promote skill in MI. RESULTS: In addition to positive feedback from student evaluations including the areas of relevance to training and self-rated skills improvement, preliminary pre- and posttraining scores from the medical students show significant improvement in expression of empathy and the ratio of reflections to questions. DISCUSSION: Implementation of the curriculum allows learners the opportunity to practice evidence-based communication that promotes intrinsic motivation for health behavior change in patients, a key treatment focus in chronic disease management.