Jason M. Satterfield

Background: Smoking continues to be a leading cause of preventable morbidity and mortality, and more than 480,000 Americans die annually due to smoking-related illness attributable to smoking and secondhand smoke. More advanced, responsive, and tailored digital interventions using machine learning and artificial intelligence may be a valuable tool for successful smoking cessation referrals. Objective: This study used the dynamic systems development method to incorporate patient and consumer sources of conversational data to develop a technology-assisted motivational interviewing (TAMI) chatbot, a digital agent using machine learning models to deliver motivational interviewing (MI) for tobacco cessation. Methods: During the functional model iteration phase, user-centered design interviews with smokers (n=3) informed the creation of TAMI. The design and build phase involved the use of existing datasets to guide the incorporation of MI-consistent utterances, language recognition, and topic classification to guide a discussion about smoking, and providing a tailored quit plan if indicated. During the implementation phase, user experience interviews with randomly selected participants (n=9) in a pilot trial discussed their experiences with TAMI. Results: User-centered design interviews indicated a desire for a chatbot that was engaging and adaptable to personal interests in quitting smoking. Inductive analysis of user experience interviews revealed that anonymity, regular reminders, and a humanized experience facilitated engagement with TAMI, but technical glitches, chatbot misunderstandings, and issues with rapport were barriers to engagement. Conclusions: Informed by user input and patient and consumer datasets, TAMI can use MI skills to elicit change talk and/or accurately evaluate readiness for tobacco cessation. Further development will enhance TAMI’s ability to seamlessly engage with users when discussing behavior change and assist underserved populations achieve improvements in a variety of health behavior goals.

Chronic pain (CP) disproportionately affects underserved populations who often experience barriers to evidence-based nonpharmacologic treatments. Digital health interventions can address these barriers by providing scalable and accessible CP management resources. However, culturally and linguistically tailored digital interventions are rare, which may limit engagement and effectiveness. The Integrating Nonpharmacologic Strategies for Pain with Inclusion, Respect, and Equity (INSPIRE) intervention combines a tailored mobile app with culturally and linguistically concordant health coaching to deliver cognitive behavioral therapy (CBT), mindfulness-based interventions (MBI), and movement-focused interventions (MFI) for CP management. This manuscript describes the process of linguistically and culturally tailoring the INSPIRE app for three target adult populations—African American/Black, Spanish-speaking Latinx, and Cantonese-speaking Chinese.Iterative tailoring was driven by multiple rounds of stakeholder focus groups followed by generative artificial intelligence (GenAI) and expert review to ensure accuracy and cultural congruence while optimizing limited resources. After initial GenAI content generation in English, the adaptation process began with surface-level adjustments in language translation and cultural representation in visual and audio elements. Deep-level adaptations incorporating culturally rooted values and beliefs about CP were made to address culturally specifically experiences with stigma and bias relevant to CP.This study highlights a replicable, efficient framework for adapting digital health interventions to improve equity and inclusion in CP management by combining AI-driven tools with human expertise to achieve optimal cultural and linguistic adaptations. Future research will evaluate the effectiveness of the INSPIRE intervention in a randomized controlled trial to assess engagement, acceptability, and improved pain outcomes across diverse populations.

Background: Chronic pain (CP) is among the most common medical conditions, is the leading cause of disability, and is often refractory to medical treatment. The CDC and the American College of Physicians recommend nonopioid and nonpharmacologic treatment as first-line strategies, including cognitive-behavioral therapy (CBT), mindfulness-based interventions (MBI), and movement-focused interventions (MFI); however, only 3% of people with chronic pain (CP) have access to these evidence-based treatments. Patients from historically minoritized populations and those speaking languages other than English are particularly underserved and may go untreated. Stigma regarding CP and interventions to manage it present additional obstacles. Methods: The Integrating Nonpharmacologic Strategies for Pain with Inclusion, Respect, and Equity (INSPIRE) study evaluates a blend of these non-pharmacologic, evidence-based interventions using a pragmatic, parallel, two-arm RCT comparing intervention participants with wait-list controls. The INSPIRE intervention includes a 12-week curriculum delivered via a multilingual mobile app paired with weekly telehealth coaching. The primary outcome will be the “Pain, Enjoyment, and General Activity (PEG)” scores at 3 months. Secondary outcomes include PEG scores at 6 and 12 months, physical functioning, quality of life, sleep, depression, anxiety, and global satisfaction with treatment at 3, 6, and 12 months. Primary mediators to be examined include pain cognitions and health behaviors. Secondary mediators may include stigma and isolation, trust in healthcare providers, and both engagement and satisfaction with the INSPIRE intervention. The intention-to-treat primary analysis will be conducted with covariates including baseline measures of pain, anxiety, and physical function. Discussion: The full RCT protocol and intervention details are provided following the SPIRIT guidelines. Implications for improving treatment access via culturally and linguistically tailored digital health interventions are discussed along with the potential for health coaching to drive mobile app engagement. Trial registration: ClinicalTrials.gov ID NCT06183281. Trial registration data set can be found here: https://clinicaltrials.gov/study/NCT06183281 and in Additional file 1.

BACKGROUND Interactions based in Motivational Interviewing (MI)1, driven by machine learning, may provide an efficient way to facilitate smoking cessation in diversified target populations. OBJECTIVE This study used the Dynamic Systems Development Method to incorporate patient and consumer sources of conversational data to develop a Technology Assisted Motivational Interviewing chatbot (TAMI), a digital agent employing machine learning models to deliver Motivational Interviewing (MI; Miller & Rollnick, 2013) for tobacco cessation. METHODS During the Functional Model Iteration Phase, user-centered design interviews with smokers (n=3) informed the creation of TAMI. The Design and Build Phase involved utilization of existing datasets to guide incorporation of MI-Consistent utterances, language recognition and topic classification to guide a discussion about smoking and providing a tailored quit plan if indicated. During the Implementation Phase, user experience interviews with randomly selected participants (n=9) in a pilot trial discussed their experiences with TAMI. RESULTS User-centered design interviews indicated a desire for a chatbot that was engaging and adaptable to personal interest in quitting smoking. Inductive analysis of user experience interviews revealed that anonymity, regular reminders, and a humanized experience facilitated engagement with TAMI, but technical glitches, chatbot misunderstandings, and issues with rapport were barriers to engagement. CONCLUSIONS Informed by user input and patient and consumer datasets, TAMI can employ MI skills to elicit change talk and or accurately evaluate readiness for tobacco cessation. Potential improvements will enhance TAMI’s ability to seamlessly engage with users when discussing behavior change and assist underserved populations achieve improvements in a variety of health behavior goals. CLINICALTRIAL N/A

UNSTRUCTURED Interactions based in Motivational Interviewing (MI) [1], driven by machine learning, may provide an efficient way to evaluate readiness to quit, elicit behavior change preferences, and scalable flexibility to extend reach to more diversified target populations. This study used patient and public sources of conversational data to develop a Technology Assisted Motivational Interviewing chatbot (TAMI), a digital agent employing machine learning models to deliver MI for tobacco cessation. Consistent with the four tasks of MI (engagement, focusing, evocation, and planning), the creation of TAMI involved 1) utilization of existing de-identified datasets to identify specific smoking topics of interest; 2) incorporation of MI-Consistent utterances to enhance relational connection to TAMI and elicit language expressing interest in quitting (change talk); 3) instilling change talk recognition and topic classification to guide discussion with TAMI and 4) providing tailored treatment options if indicated. Informed by patient, provider, and public discussions about smoking, TAMI can explore motivation associated with tobacco use, and privately employ interventions to elicit change talk, or accurately evaluate readiness for tobacco cessation. TAMI is also scalable technology, which opens the possibility of having more tools for clinical assessment, delivering MI, and tailoring cessation referrals to underserved populations or those with other target behavior goals.

Health professions curricula are created to prepare learners to effectively address health issues affecting individ uals and their communities. Ideally, curricula emphasize the predominant biopsychosocial influences impacting the health of diverse populations. However, despite decades of investment and advances in educational research and design, we have failed to create a health professional workforce capable of equitably meeting the health care needs of the public. Particular communities, geographic regions, and patients with stigmatized diagnoses continue to be underserved, and the potential contributions of multidisciplinary health professionals and advanced practice providers continue to be unrealized within a predominantly physician-centric health care model. Genuine educational transformation requires multidimensional, iterative strategies used to meaningfully evolve traditional classroom curricula, break from the implicit and “hidden” curricula, and enrich the educational ecosystem in which all operate. This manuscript elaborates the construct and process of “educational ecosystem transformation” as a tool for the evolution of the educational ecosystem and its situated curriculum that will eventually drive the enrichment of the healthcare workforce. Drawing from traditional models of curriculum development, recent work on transforming the hidden curriculum, the clinical learning environment, and change management strategies, this new approach uses a health equity and structural competence lens to interrogate and deconstruct a learning system in order to identify opportunities to change, strengthen, and deepen a learner's experience around a specific topic. This process requires an in-depth, multidimensional assessment followed by the identification of key change targets and a stepwise, iterative plan for improvement and transformation. The topic area of substance use disorders (SUD) is used to illustrate how this complex process might be employed to improve the quality of care, realize and amplify the contributions of the entire healthcare team, stimulate interest in addiction medicine as a career, and reduce the stigma and disparities patients with SUDs often experience.

Purpose: To estimate the effectiveness of a multimodal educational intervention to increase use of shared decision-making (SDM) behaviors by inpatient pediatric and internal medicine hospitalists and trainees at teaching hospitals at Stanford University and the University of California, San Francisco. Method: The 8-week Patient Engagement Project Study intervention, delivered at four services between November 2014 and January 2015, included workshops, campaign messaging, report cards, and coaching. For 12-week pre- and postintervention periods, clinician peers used the nine-point Rochester Participatory Decision-Making Scale (RPAD) to evaluate rounding teams’ SDM behaviors with patients during ward rounds. Eligible teams included a hospitalist and at least one trainee (resident, intern, medical student), in addition to nonphysicians. Random-effects models were used to estimate intervention effects based on RPAD scores that sum points on nine SDM behaviors per patient encounter. Results: In total, 527 patient encounters were scored during 175 rounds led by 49 hospitalists. Patient and team characteristics were similar across pre- and postintervention periods. Improvement was observed on all nine SDM behaviors. Adjusted for the hierarchical study design and covariates, the mean RPAD score improvement was 1.68 points (95% CI, 1.33–2.03; P < .001; Cohen d = 0.82), with intervention effects ranging from 0.7 to 2.5 points per service. Improvements were associated with longer patient encounters and a higher percentage of trainees per team. Conclusions: The intervention increased behaviors supporting SDM during ward rounds on four independent services. The findings recommend use of clinician-focused interventions to promote SDM adoption in the inpatient setting.

Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Primary care settings are uniquely positioned to reach individuals at-risk of alcohol use disorder through technology-delivered behavioral health interventions. Despite emerging effectiveness data, few efforts have been made to summarize the collective findings from these delivery approaches. Objective: The purpose of this study was to review recent literature on the use of technology to deliver, enhance, or support the implementation of alcohol-related interventions in primary care. We focused on addressing questions related to (1) categorization and target, (2) descriptive characteristics and context of delivery, (3) reported efficacy, and (4) factors influencing efficacy. Methods: We conducted a comprehensive search and systematic review of completed studies at the intersection of primary care, technology, and alcohol-related problems published from January 2000 to December 2018 within EBSCO databases, ProQuest Dissertations, and Cochrane Reviews. Of 2307 initial records, 42 were included and coded independently by two investigators. Results: Compared to the years of 2000-2009, published studies on technology-based alcohol interventions in primary care nearly tripled during the years of 2010-2018. Of the 42 studies, 28 (64%) were randomized controlled trials. Further, studies were rated on risk of bias and found to be predominantly low risk (n=18), followed by moderate risk (n=16), and high risk (n=8). The majority (71%) of studies reported reduced drinking or harm in all primary and secondary efficacy outcomes. Furthermore, 42% of studies reported that at least half of the primary and secondary efficacy outcomes of the technology-based interventions were superior to treatment as usual. High efficacy was associated with provider involvement and the reported use of an implementation strategy to deliver the technology-based intervention. Conclusions: Our systematic review highlights a pattern of growth in the number of studies evaluating technology-based alcohol interventions in primary care. While these interventions appear largely beneficial in primary care, outcomes may be enhanced by provider involvement and implementation strategy use. This review enables better understanding of the typologies and efficacy of these interventions and informs recommendations for those developing and implementing technology-based alcohol interventions in primary care settings.

BACKGROUND Primary care settings are uniquely positioned to reach individuals at risk of alcohol use disorder through technology-delivered behavioral health interventions. Despite emerging effectiveness data, few efforts have been made to summarize the collective findings from these delivery approaches. OBJECTIVE The aim of this study was to review recent literature on the use of technology to deliver, enhance, or support the implementation of alcohol-related interventions in primary care. We focused on addressing questions related to (1) categorization or target of the intervention, (2) descriptive characteristics and context of delivery, (3) reported efficacy, and (4) factors influencing efficacy. METHODS We conducted a comprehensive search and systematic review of completed studies at the intersection of primary care, technology, and alcohol-related problems published from January 2000 to December 2018 within EBSCO databases, ProQuest Dissertations, and Cochrane Reviews. Of 2307 initial records, 42 were included and coded independently by 2 investigators. RESULTS Compared with the years of 2000 to 2009, published studies on technology-based alcohol interventions in primary care nearly tripled during the years of 2010 to 2018. Of the 42 included studies, 28 (64%) were randomized controlled trials. Furthermore, studies were rated on risk of bias and found to be predominantly low risk (n=18), followed by moderate risk (n=16), and high risk (n=8). Of the 24 studies with primary or secondary efficacy outcomes related to drinking and drinking-related harms, 17 (71%) reported reduced drinking or harm in all primary and secondary efficacy outcomes. Furthermore, of the 31 studies with direct comparisons with treatment as usual (TAU), 13 (42%) reported that at least half of the primary and secondary efficacy outcomes of the technology-based interventions were superior to TAU. High efficacy was associated with provider involvement and the reported use of an implementation strategy to deliver the technology-based intervention. CONCLUSIONS Our systematic review has highlighted a pattern of growth in the number of studies evaluating technology-based alcohol interventions in primary care. Although these interventions appear to be largely beneficial in primary care, outcomes may be enhanced by provider involvement and implementation strategy use. This review enables better understanding of the typologies and efficacy of these interventions and informs recommendations for those developing and implementing technology-based alcohol interventions in primary care settings.