Background: Telehealth can provide innovative models of care for people living in congregate care communities (CCC), but lack of consistent workflow is a barrier for administrators and staff. We propose a framework for CCC to implement workflows for age-inclusive telehealth. Methods: As part of an infection control initiative with a focus on telehealth optimization, Virginia Infection Mitigation, Prevention and Control Through Technology developed relationships with administrators and staff of CCC across the Commonwealth of Virginia. Partners in this community of practice completed a statewide survey that we conducted on anticipated and experienced barriers to telehealth implementation. Through survey responses, virtual meetings with organizational leadership, and on-site facility visits, our team assessed the strengths, needs, and goals for telehealth capability. Working with administrative and clinical teams, we developed a consultation report to define short- and long-term implementation steps. Results: We collaborated with a nonprofit organization supporting a community of people with neurodevelopmental disabilities and a rural Program of All-Inclusive Care for the Elderly. We developed a framework for telehealth optimization with four tiers: Initiate, Integrate, Incentivize, and Inspire. Each stage included an overall goal with corresponding interventions to guide program implementation. Discussion: The "Four I" Framework can be used to outline telehealth readiness and implement workflows for CCC. We aim to further develop an iterative process and to collaborate with additional organizations to optimize telehealth programs.

By consistently taking medication, people with HIV (PWH) can attain viral suppression, improving their health and reducing transmission risk. PositiveLinks (PL) is a clinic-deployed mobile platform designed to improve engagement in care for PWH by enabling them to track their medications, connect with peers, and communicate with providers. This project investigated the experience of PL users who had recent periods of viral non-suppression to understand how these high-risk episodes can be predicted and prevented. Fifteen participants completed mental health measures and in-depth interviews. Two members of the study team independently coded interview transcripts and resolved any discrepancies. The codebook was developed iteratively until thematic saturation and intercoder reliability were achieved. Participants revealed mental health and substance use concerns. Frequent stressors highlighted were relationship challenges, financial difficulties, and unstable living situations. Relationship challenges were a common barrier to care, along with competing priorities, transportation and finances. In contrast, positive relationships, motivation, positive interactions with clinic staff, and social programs facilitated regaining viral suppression. Participants highlighted the importance of strong patient-provider relationships and social support in overcoming barriers to care. We identified factors that impact medication adherence, which will inform efforts to mitigate and prevent viral non-suppression and thus improve health outcomes.

Effective patient-provider communication is crucial in clinical care, directly impacting patient outcomes and quality of life. Traditional evaluation methods, such as human ratings, patient feedback, and provider self-assessments, are often limited by high costs and scalability issues. Although existing natural language processing (NLP) techniques show promise, they struggle with the nuances of clinical communication and require sensitive clinical data for training, reducing their effectiveness in real-world applications. Emerging large language models (LLMs) offer a new approach to assessing complex communication metrics, with the potential to advance the field through integration into passive sensing and just-in-time intervention systems. This study explores LLMs as evaluators of palliative care communication quality, leveraging their linguistic, in-context learning, and reasoning capabilities. Specifically, using simulated scripts crafted and labeled by healthcare professionals, we test proprietary models (e.g., GPT-4) and fine-tune open-source LLMs (e.g., LLaMA2) with a synthetic dataset generated by GPT-4 to evaluate clinical conversations, to identify key metrics such as ‘understanding’ and ‘empathy’. Our findings demonstrated LLMs’ superior performance in evaluating clinical communication, providing actionable feedback with reasoning, and demonstrating the feasibility and practical viability of developing in-house LLMs. This research highlights LLMs’ potential to enhance patient-provider interactions and lays the groundwork for downstream steps in developing LLM-empowered clinical health systems.

Anal squamous cell carcinoma disproportionally affects people with HIV (PWH); however, engagement in anal cancer screening is low in many settings. This study was conducted to assess knowledge and perceptions of anal cancer screening to identify factors in the engagement and retention in prevention services among PWH. Semistructured interviews were conducted among adult PWH eligible for anal cancer screening in our Ryan White HIV/AIDS Program clinic. Descriptive statistics were tabulated; thematic analyses were performed to identify emerging motivators, facilitators, and barriers. Among 26 PWH, 9 had not been screened, 8 had undergone Papanicolaou (Pap) testing alone, and 9 had undergone anoscopy. The median age of the cohort was 55.2 years; 54% identified as men who have sex with men, and 54% identified as Black. In the unscreened cohort, participants were motivated by investing in their health and positive attitudes toward cancer prevention however were deterred by a lack of referral and low awareness about screening. Among those who had Pap testing, trust in healthcare providers and abnormal testing results were motivators to engagement, whereas lack of perceived risk of anal cancer and worry about pain of an anoscopy were prominent barriers. Among those who had anoscopy, perceived risk, positive experience with the procedure, and use of anxiolytics prior to anoscopy were motivators, whereas anxiety around a new cancer diagnosis and negative experience with anoscopy were barriers. Clinics seeking to build or strengthen their anal cancer screening programs can address the barriers described in this study to promote access to anal cancer screening among PWH.

In HIV care, a strong rapport between patient and provider is essential for strengthening trust, enhancing therapy adherence, and ultimately leading to improved health outcomes. As the adoption of digital interactions in HIV care via mobile health (mHealth) tools is emerging, maintaining rapport in these asynchronous text-based communications becomes a critical yet challenging task. In this paper, we analyze 1,740 messages from an mHealth platform, categorized by experienced clinicians as either ‘rapport-building’ or ‘information-only.’ We utilize linguistic analysis to uncover key attributes of rapport-building communication. This led to a set of machine learning (ML) models and Large Language Models (LLMs) capable of classifying these communication styles. Further, we propose the application of LLMs not only to identify but also to actively rewrite ‘information only’ messages into versions that enhance rapport building without compromising information integrity. Our research demonstrates potential advancements in HIV mHealth communication by integrating linguistic analysis with language models, leading to more effective patient-provider interactions.

Background:Evaluating implementation of digital health interventions (DHIs) in practice settings is complex, involving diverse users and multistep processes. Proactive planning can ensure desired implementation determinants and outcomes are captured for hybrid studies, but operational guidance for DHI studies is limited. Methods:We planned a cluster randomized, type II hybrid effectiveness-implementation trial testing PositiveLinks, a smartphone application for HIV care, compared to usual care (n = 6 sites per arm), among HIV outpatient sites in the DC Cohort Longitudinal HIV Study in Washington, DC. Our process included: 1) Defining components of the DHI and associated implementation strategy, 2) Selecting implementation science frameworks to accomplish evaluation aims, 3) Mapping framework dimensions, domains, and constructs to implementation strategy steps, 4) Modifying/creating instruments to collect data for implementation outcome measures and determinants and 5) Developing a compatible implementation science data collection and management plan. Results:Specification of components of the DHI and implementation strategy identified relevant platform usage data and necessary implementer actions, toward planning measurement of program reach and adoption. A priori mapping of implementation strategy steps to the Reach Effectiveness Adoption Implementation Maintenance (RE-AIM) framework identified how data would be collected for each step/corresponding outcome measure. The multi-site cohort study provided infrastructure for prospective, scaled implementation research, including site research assistants (RAs) coordinating implementation. Existing cohort tools (periodic site assessments, patient consent logs) were adapted for the evaluation to further capture representativeness and reach/adoption 'denominators.' New survey instruments allowed for framework-guided evaluation of provider adaptations/dose/fidelity to planned implementation across a large number of participants and multiple timepoints. Some aspects of real-world implementation were challenging to mirror within the planned hybrid trial (e.g. RAs selected as de facto site implementation leads) or were modified to preserve internal validity of effectiveness measurement (e.g. PositiveLinks 'community of practice'). Conclusions:Challenges and opportunities arose in planning the implementation evaluation for PositiveLinks within a hybrid trial in a cohort population. Prospective hybrid trial planning must balance generalizability of implementation processes to 'real world' conditions, with rigorous trial procedures to measure intervention effectiveness. Rapid, scalable tools require further study to enable evaluations within large, multi-site hybrid studies.

Effective patient-provider communication is crucial in clinical care, directly impacting patient outcomes and quality of life. Traditional evaluation methods, such as human ratings, patient feedback, and provider self-assessments, are often limited by high costs and scalability issues. Although existing natural language processing (NLP) techniques show promise, they struggle with the nuances of clinical communication and require sensitive clinical data for training, reducing their effectiveness in real-world applications. Emerging large language models (LLMs) offer a new approach to assessing complex communication metrics, with the potential to advance the field through integration into passive sensing and just-in-time intervention systems. This study explores LLMs as evaluators of palliative care communication quality, leveraging their linguistic, in-context learning, and reasoning capabilities. Specifically, using simulated scripts crafted and labeled by healthcare professionals, we test proprietary models (e.g., GPT-4) and fine-tune open-source LLMs (e.g., LLaMA2) with a synthetic dataset generated by GPT-4 to evaluate clinical conversations, to identify key metrics such as ‘understanding’ and ‘empathy’. Our findings demonstrated LLMs’ superior performance in evaluating clinical communication, providing actionable feedback with reasoning, and demonstrating the feasibility and practical viability of developing in-house LLMs. This research highlights LLMs’ potential to enhance patient-provider interactions and lays the groundwork for downstream steps in developing LLM-empowered clinical health systems.

Quality patient-provider communication is critical to improve clinical care and patient outcomes. While progress has been made with communication skills training for clinicians, significant gaps exist in how to best monitor, measure, and evaluate the implementation of communication skills in the actual clinical setting. Advancements in ubiquitous technology and natural language processing make it possible to realize more objective, real-time assessment of clinical interactions and in turn provide more timely feedback to clinicians about their communication effectiveness. In this paper, we propose CommSense, a computational sensing framework that combines smartwatch audio and transcripts with natural language processing methods to measure selected "best-practice'' communication metrics captured by wearable devices in the context of palliative care interactions, including understanding, empathy, presence, emotion, and clarity. We conducted a pilot study involving N=40 clinician participants, to test the technical feasibility and acceptability of CommSense in a simulated clinical setting. Our findings demonstrate that CommSense effectively captures most communication metrics and is well-received by both practicing clinicians and student trainees. Our study also highlights the potential for digital technology to enhance communication skills training for healthcare providers and students, ultimately resulting in more equitable delivery of healthcare and accessible, lower cost tools for training with the potential to improve patient outcomes.

During the COVID pandemic, telehealth demonstrated the potential to help provide care to residents of long term care facilities (LTCF). Among patients in LTCF in the US, research has demonstrated that urinary tract infections (UTIs) are among the most common infections diagnosed, approximately 20-30% of all reported infections. Moving forward, telemedicine could be utilized to improve diagnosis of UTIs, but there has been limited research examining the current evidence to support the efficacy of telemedicine in diagnosing UTIs. This project consisted of a literature search, focused on research regarding validated criteria for UTI diagnosis and best practices for assessing history and physical examination via telemedicine.

The COVID-19 public health emergency (PHE) raised important questions of how best to apply telehealth to enable delivery of timely, high-quality health care to medically vulnerable individuals who reside in long-term care facilities. Looking back to the PHE, there have been multiple studies that demonstrate how telehealth can be a tool to improve patient outcomes, for COVID-19 infection, as well as for many other medical conditions. 1 Shaver J. The state of telehealth before and after the COVID-19 Pandemic. PrimaryCare. 2022; 49: 517-530 Google Scholar , 2 Doraiswamy S. Abraham A. Mamtani R. Cheema S. Use of telehealth during the COVID-19 pandemic: scoping review. J Med Internet Res. 2020; 22e24087 Crossref PubMed Scopus (347) Google Scholar , 3 Weiner J.P. Bandeian S. Hatef E. Lans D. Liu A. Lemke K.W. In-person and telehealth ambulatory contacts and costs in a large US insured cohort before and during the COVID-19 pandemic. JAMA Netw Open. 2021; 4e212618 Crossref Scopus (119) Google Scholar , 4 Ulyte A. Mehrotra A. Wilcock A.D. SteelFisher G.K. Grabowski D.C. Barnett M.L. Telemedicine Visits in US skilled nursing facilities. JAMA Netw Open. 2023; 6e2329895 Crossref Scopus (1) Google Scholar , 5 Harris D.A. Archbald-Pannone L. Kaur J. et al. Rapid telehealth-centered Response to COVID-19 Outbreaks in Postacute and long-term care facilities. Telemed J e Health. 2021; 27: 102-106 Crossref PubMed Scopus (34) Google Scholar Telehealth has been shown to decrease unnecessary transfers and decrease overall medical costs. 6 Chess D. Whitman J.J. Croll D. Stefanacci R. Impact of after-hours telemedicine on hospitalizations in a skilled nursing facility. Am J Managed Care. 2018; 24: 385-388 PubMed Google Scholar ,7 Groom L.L. McCarthy M.M. Stimpfel A.W. Brody A.A. Telemedicine and telehealth in nursing homes: an integrative review. J Am Med Dir Assoc. 2021; 22: 1784-1801.e7 Abstract Full Text Full Text PDF PubMed Scopus (61) Google Scholar However, telehealth implementation and sustainability has remained challenging for many long-term care facilities. 8 Seifert A. Batsis J.A. Smith A.C. Telemedicine in long-term care facilities during and beyond COVID-19: challenges caused by the digital divide. Front Public Health. 2020; 8601595 Crossref PubMed Scopus (50) Google Scholar ,9 Konttila J. Siira H. Kyngäs H. et al. Healthcare professionals' competence in digitalisation: a systematic review. J Clin Nurs. 2019; 28: 745-761 Crossref Scopus (171) Google Scholar Therefore, our research team aimed to assess telehealth usage in the Commonwealth of Virginia before, during, and after the PHE, as well as the view of the anticipated and observed benefits and barriers of telehealth use among staff in congregate care facilities. The survey solicited information on anticipated (for those who did not use telehealth) and experienced (for those who used telehealth) benefits and barriers of telehealth.

BackgroundHIV viral suppression and retention in care continue to be challenging goals for people with HIV in Washington, District of Columbia (DC). The PositiveLinks mobile app is associated with increased retention in care and viral load suppression in nonurban settings. The app includes features such as daily medication reminders, mood and stress check-ins, an anonymized community board for peer-to-peer social support, secure messaging to care teams, and resources for general and clinic-specific information, among other features. PositiveLinks has not been tailored or tested for this distinct urban population of people with HIV. ObjectiveThis study aimed to inform the tailoring of a mobile health app to the needs of people with HIV and their providers in Washington, DC. MethodsWe conducted a 3-part formative study to guide the tailoring of PositiveLinks for patients in the DC Cohort, a longitudinal cohort of >12,000 people with HIV receiving care in Washington, DC. The study included in-depth interviews with providers (n=28) at study clinics, focus groups with people with HIV enrolled in the DC Cohort (n=32), and a focus group with members of the DC Regional Planning Commission on Health and HIV (COHAH; n=35). Qualitative analysis used a constant comparison iterative approach; thematic saturation and intercoder agreement were achieved. Emerging themes were identified and grouped to inform an adaptation of PositiveLinks tailored for patients and providers. ResultsEmerging themes for patients, clinic providers, and COHAH providers included population needs and concerns, facilitators and barriers to engagement in care and viral suppression, technology use, anticipated benefits, questions and concerns, and suggestions. DC Cohort clinic and COHAH provider interviews generated an additional theme: clinic processes. For patients, the most commonly discussed potential benefits included improved health knowledge and literacy (mentioned n=10 times), self-monitoring (n=7 times), and connection to peers (n=6 times). For providers, the most common anticipated benefits were improved communication with the clinic team (n=21), connection to peers (n=14), and facilitation of self-monitoring (n=11). Following data review, site principal investigators selected core PositiveLinks features, including daily medication adherence, mood and stress check-ins, resources, frequently asked questions, and the community board. Principal investigators wanted English and Spanish versions depending on the site. Two additional app features (messaging and documents) were selected as optional for each clinic site. Overall, 3 features were not deployed as not all participating clinics supported them. ConclusionsPatient and provider perspectives of PositiveLinks had some overlap, but some themes were unique to each group. Beta testing of the tailored app was conducted (August 2022). This formative work prepared the team for a cluster randomized controlled trial of PositiveLinks’ efficacy. Randomization of clinics to PositiveLinks or usual care occurred in August 2022, and the randomized controlled trial launched in November 2022. International Registered Report Identifier (IRRID)RR2-10.2196/37748

While progress has been made on communication skills training for clinicians, gaps exist in how to best monitor, measure, and evaluate the implementation of communication skills in the actual clinical setting and provide timely feedback about effectiveness and quality. This 1-year, multi-phase, proof-of-concept study aims to design and pilot test ‘CommSense,’ a novel wearable sensing system and associated natural language processing algorithms. Our team leverages disciplinary expertise from nursing, engineering, medicine, and library science. CommSense will be deployed on mobile devices (e.g., smartwatches) with the goal to reliably extract key markers of communication quality from real-time patient-clinician palliative care interactions. In Phase 1 (completed) we conducted a thorough review of the literature to develop an evidence-based list of quality communication metrics and determined how these metrics could be best operationalized. Phases 2 and 3 (in-progress) will involve design of the CommSense system and pilot testing with simulated clinical scenarios to assess fidelity of data capture and extraction of desired metrics. We identified 96 articles from relevant databases in consultation with a health sciences librarian; 18 articles were added based on expert opinion. After screening article titles and abstracts (n=114) for relevance, 72 articles were selected for full-text extraction and independently reviewed by 2 members of our clinical team. We used a ‘talk-aloud’ thematic analysis approach to develop a list of 7 core communication metrics (5 verbal; 2 non-verbal) with associated strategies for operationalization. Clinician-patient communication is complex and determining appropriate metrics for evaluation is challenging. We propose a core set of communication ‘best practices’ that can be extracted from conversations using the CommSense technology. The long-term goal of this research is to deploy CommSense in a variety of healthcare contexts to provide real-time feedback to end-users to improve communication and patient-centered health outcomes.

Background : To provide just equity in academic exchange, as well as to reduce prohibitive travel cost and address environmental concerns, the past paradigm of international student exchange has fundamentally shifted from one directional travel to mutually beneficial bidirectional remote communication between students all over the globe. Current analysis aims to quantify cultural competency and evaluate academic outcomes. Methods : Sixty students half from the US and half from Rwanda grouped in teams of 4 engaged in a nine-month project-focused relationship. Cultural competency was evaluated prior to project initiation and six months after completion of the project. Student perspective of project development was analyzed weekly and final academic outcome was evaluated. Results : Change in cultural competency was not significant; however, students did identify satisfaction in team interaction and academic outcomes were achieved. Conclusion : A single remote exchange between students in two countries may not be transformative but it can provide cultural enrichment and successful academic project outcome and may serve to enhance cultural curiosity.

Background Sexual health disparities exist for Black men who have sex with men (BMSM) in New Orleans, Louisiana. Rates of sexually transmitted infections (STIs) are high for both BMSM and those taking HIV pre-exposure prophylaxis (PrEP). Objective In this study, we introduced an existing PrEP adherence app to new potential users—BMSM engaged in PrEP care in New Orleans—to guide app adaptation with STI prevention features and tailoring for the local context. Methods Using a user-centered design, we conducted 4 focus group discussions (FGDs), with interim app adaptations from December 2020 to March 2021. During the FGDs, a video of the app, app website, and mock-ups were shown to participants. We asked about facilitators of and barriers to STI prevention in general, current app use, impressions of the existing app, new app features to potentially facilitate STI prevention, and how the app should be tailored for BMSM. We used applied qualitative thematic analysis to identify themes and needs of the population. Results Overall, 4 FGDs were conducted with 24 BMSM taking PrEP. We grouped themes into 4 categories: STI prevention, current app use and preferences, preexisting features and impressions of the prep’d app, and new features and modifications for BMSM. Participants noted concern about STIs and shared that anxiety about some STIs was higher than that for others; some participants shared that since the emergence of PrEP, little thought is given to STIs. However, participants desired STI prevention strategies and suggested prevention methods to implement through the app, including access to resources, educational content, and sex diaries to follow their sexual activity. When discussing app preferences, they emphasized the need for an app to offer relevant features and be easy to use and expressed that some notifications were important to keep users engaged but that they should be limited to avoid notification fatigue. Participants thought that the current app was useful and generally liked the existing features, including the ability to communicate with providers, staff, and each other through the community forum. They had suggestions for modifications for STI prevention, such as the ability to comment on sexual encounters, and for tailoring to the local context, such as depictions of iconic sights from the area. Mental health emerged as an important need to be addressed through the app during discussion of almost all features. Participants also stressed the importance of ensuring privacy and reducing stigma through the app. Conclusions A PrEP adherence app was iteratively adapted with feedback from BMSM, resulting in a new app modified for the New Orleans context and with STI prevention features. Participants gave the app a new name, PCheck, to be more discreet. Next steps will assess PCheck use and STI prevention outcomes.

Background Quality patient–clinician communication is paramount to achieving safe and compassionate healthcare, but evaluating communication performance during real clinical encounters is challenging. Technology offers novel opportunities to provide clinicians with actionable feedback to enhance their communication skills. Methods This pilot study evaluated the acceptability and feasibility of CommSense, a novel natural language processing (NLP) application designed to record and extract key metrics of communication performance and provide real-time feedback to clinicians. Metrics of communication performance were established from a review of the literature and technical feasibility verified. CommSense was deployed on a wearable (smartwatch), and participants were recruited from an academic medical center to test the technology. Participants completed a survey about their experience; results were exported to SPSS (v.28.0) for descriptive analysis. Results Forty ( n = 40) healthcare participants (nursing students, medical students, nurses, and physicians) pilot tested CommSense. Over 90% of participants “strongly agreed” or “agreed” that CommSense could improve compassionate communication ( n = 38, 95%) and help healthcare organizations deliver high-quality care ( n = 39, 97.5%). Most participants ( n = 37, 92.5%) “strongly agreed” or “agreed” they would be willing to use CommSense in the future; 100% ( n = 40) “strongly agreed” or “agreed” they were interested in seeing information analyzed by CommSense about their communication performance. Metrics of most interest were medical jargon, interruptions, and speech dominance. Conclusion Participants perceived significant benefits of CommSense to track and improve communication skills. Future work will deploy CommSense in the clinical setting with a more diverse group of participants, validate data fidelity, and explore optimal ways to share data analyzed by CommSense with end-users.