BackgroundGoals for Eating and Moving (GEM) is a technology-assisted health coaching intervention to improve weight management in primary care at the Veterans Health Administration (VHA) that we designed through prior rigorous formative studies. GEM is integrated within the patient-centered medical home and utilizes student health coach volunteers to counsel patients and encourage participation in VHA’s intensive weight management program, MOVE!. The primary aim of this study was to determine the feasibility and acceptability of GEM when compared to Enhanced Usual Care (EUC). Our secondary aim was to test the impact of GEM on weight, diet and physical activity when compared to EUC.MethodsVeterans with a Body Mass Index ≥30 kg/m2 or 25–29.9 kg/m2 with comorbidities (n = 45) were recruited in two phases and randomized to GEM (n = 22) or EUC (n = 23). We collected process measures (e.g. number of coaching calls completed, number and types of lifestyle goals, counseling documentation) and qualitative feedback on quality of counseling and acceptability of call duration. We also measured weight and behavioral outcomes.ResultsGEM participants reported receiving high quality counseling from health coaches and that call duration and frequency were acceptable. They received 5.9 (SD = 3.7) of 12 coaching calls on average, and number of coaching calls completed was associated with greater weight loss at 6-months in GEM participants (Spearman Coefficient = 0.71, p < 0.001). Four participants from GEM and two from EUC attended the MOVE! program. PCPs completed clinical reminders in 12% of PCP visits with GEM participants. Trends show that GEM participants (n = 21) tended to lose more weight at 3-, 6-, and 12-months as compared to EUC, but this was not statistically significant. There were no significant differences in diet or physical activity.ConclusionsWe found that a technology assisted health coaching intervention delivered within primary care using student health coaches was feasible and acceptable to Veteran patients. This pilot study helped elucidate challenges such as low provider engagement, difficulties with health coach continuity, and low patient attendance in MOVE! which we have addressed and plan to test in future studies.Trial registrationNCT03006328 Retrospectively registered on December 30, 2016.Electronic supplementary materialThe online version of this article (10.1186/s40608-018-0226-0) contains supplementary material, which is available to authorized users.

Background Although there is considerable interest in machine learning (ML) and artificial intelligence (AI) in critical care, the implementation of effective algorithms into practice has been limited. Objective We sought to understand physician perspectives of a novel intubation prediction tool. Further, we sought to understand health care provider and nonprovider perspectives on the use of ML in health care. We aim to use the data gathered to elucidate implementation barriers and determinants of this intubation prediction tool, as well as ML/AI-based algorithms in critical care and health care in general. Methods We developed 2 anonymous surveys in Qualtrics, 1 single-center survey distributed to 99 critical care physicians via email, and 1 social media survey distributed via Facebook and Twitter with branching logic to tailor questions for providers and nonproviders. The surveys included a mixture of categorical, Likert scale, and free-text items. Likert scale means with SD were reported from 1 to 5. We used student t tests to examine the differences between groups. In addition, Likert scale responses were converted into 3 categories, and percentage values were reported in order to demonstrate the distribution of responses. Qualitative free-text responses were reviewed by a member of the study team to determine validity, and content analysis was performed to determine common themes in responses. Results Out of 99 critical care physicians, 47 (48%) completed the single-center survey. Perceived knowledge of ML was low with a mean Likert score of 2.4 out of 5 (SD 0.96), with 7.5% of respondents rating their knowledge as a 4 or 5. The willingness to use the ML-based algorithm was 3.32 out of 5 (SD 0.95), with 75% of respondents answering 3 out of 5. The social media survey had 770 total responses with 605 (79%) providers and 165 (21%) nonproviders. We found no difference in providers’ perceived knowledge based on level of experience in either survey. We found that nonproviders had significantly less perceived knowledge of ML (mean 3.04 out of 5, SD 1.53 vs mean 3.43, SD 0.941; P<.001) and comfort with ML (mean 3.28 out of 5, SD 1.02 vs mean 3.53, SD 0.935; P=.004) than providers. Free-text responses revealed multiple shared concerns, including accuracy/reliability, data bias, patient safety, and privacy/security risks. Conclusions These data suggest that providers and nonproviders have positive perceptions of ML-based tools, and that a tool to predict the need for intubation would be of interest to critical care providers. There were many shared concerns about ML/AI in health care elucidated by the surveys. These results provide a baseline evaluation of implementation barriers and determinants of ML/AI-based tools that will be important in their optimal implementation and adoption in the critical care setting and health care in general.

Background Research centers and programs focused on dissemination and implementation science (DIS) training, mentorship, and capacity building have proliferated in recent years. There has yet to be a comprehensive inventory of DIS capacity building program (CBP) cataloging information about activities, infrastructure, and priorities as well as opportunities for shared resources, collaboration, and growth. The purpose of this systematic review is to provide the first inventory of DIS CBPs and describe their key features and offerings. Methods We defined DIS CBPs as organizations or groups with an explicit focus on building practical knowledge and skills to conduct DIS for health promotion. CBPs were included if they had at least one capacity building activity other than educational coursework or training alone. A multi-method strategy was used to identify DIS CBPs. Data about the characteristics of DIS CBPs were abstracted from each program’s website. In addition, a survey instrument was developed and fielded to gather in-depth information about the structure, activities, and resources of each CBP. Results In total, 165 DIS CBPs met our inclusion criteria and were included in the final CBP inventory. Of these, 68% are affiliated with a United States (US) institution and 32% are internationally based. There was one CBP identified in a low- and middle-income country (LMIC). Of the US-affiliated CBPs, 55% are embedded within a Clinical and Translational Science Award program. Eighty-seven CBPs (53%) responded to a follow-up survey. Of those who completed a survey, the majority used multiple DIS capacity building activities with the most popular being Training and Education (n=69, 79%) followed by Mentorship (n=58, 67%), provision of DIS Resources and Tools (n=57, 66%), Consultation (n=58, 67%), Professional Networking (n=54, 62%), Technical Assistance (n=46, 52%), and Grant Development Support (n=45, 52%). Conclusions To our knowledge, this is the first study to catalog DIS programs and synthesize learnings into a set of priorities and sustainment strategies to support DIS capacity building efforts. There is a need for formal certification, accessible options for learners in LMICs, opportunities for practitioners, and opportunities for mid/later stage researchers. Similarly, harmonized measures of reporting and evaluation would facilitate targeted cross-program comparison and collaboration.

Digital Therapeutics (DTx) are increasingly seen as a promising way to provide safe, effective, accessible, sustainable, scalable, and equitable approaches to advance individual and population health. Developing DTx is inherently complex in that DTx may include multiple interacting components, such as tools to support activities like medication adherence, health behavior goal-setting or self-monitoring, and algorithms that adapt the provision of these according to individual needs. As recommended in a recent worldwide review of regulatory approaches for DTx, a way to address this complexity is to base the design, development, testing, and iterative improvements of DTx on real-world evidence (RWE). Notably, that review highlights the need for improved guidance on when and how to use RWE for DTx. In this paper, we propose the DTx RWE Framework to provide a pragmatic, iterative, milestone-driven approach for producing RWE for DTx regulation. The DTx RWE Framework is based on best practices from human-centered design, optimization trials for behavioral interventions, behavioral health research, and implementation science. It maps these onto the traditional four phase development model for pharmaceuticals but includes key adaptations relevant to RWE production for DTx, such as including early and ongoing partnerships between developers of DTx and their intended users in clinical and/or community settings. Adoption of our DTx RWE Framework may help address known problems with current DTx, including questionable marketing claims, lack of evidence-based guidance for patients, providers, and health care leaders and the need to improve economic incentives that advance the adoption and use of DTx.

Purpose Preventive health care, delivered through well child care visits, serves as a universal and primary entry point for promoting child wellbeing, yet children with lower socioeconomic status and children of color receive less consistent and lower quality preventive health care. Currently, limited research exists comparing models for delivering preventive care to children and their impact on longstanding racial/ethnic and socioeconomic inequities. Description Practice-based research networks can help to advance health equity by more rapidly studying and scaling innovative, local models of care to reduce racial/ethnic and socioeconomic inequities in primary care and preventive care utilization. This paper outlines a framework of community engagement that can be utilized by practice-based research networks to advance health equity and details the application of the framework using the GROWBABY Research Network (GROup Wellness Visits for BABies and FamilY Research Network). Assessment The GROWBABY Research Network launched in 2020, engaged clinical practices utilizing this unique model of group well childcare - CenteringParenting® - with the following goals: to promote collaboration among researchers, clinicians, patients, and community members; facilitate practice-based research; and increase the use of shared assessment measures and protocols. As a research collaborative, the GROWBABY Research Network connects clinical partners facing similar challenges and creates opportunities to draw upon the assets and strengths of the collective to identify solutions to the barriers to research participation. Conclusion Primary care, practice-based research networks like the GROWBABY Research Network that intentionally integrate community engagement principles and community-based participatory research methods can advance equitable health care systems and improve child wellbeing.