Artificial intelligence-generated feedback on social signals in patient-provider communication: technical performance, feedback usability, and impact.

Objectives: Implicit bias perpetuates health care inequities and manifests in patient-provider interactions, particularly nonverbal social cues like dominance. We investigated the use of artificial intelligence (AI) for automated communication assessment and feedback during primary care visits to raise clinician awareness of bias in patient interactions.

Materials And Methods: (1) Assessed the technical performance of our AI models by building a machine-learning pipeline that automatically detects social signals in patient-provider interactions from 145 primary care visits.

Attitudes toward and preparedness for lung transplantation among individuals with cystic fibrosis in the era of highly effective modulators.

Background: Outcomes for individuals with cystic fibrosis (CF) have improved due to highly effective modulator therapy (HEMT). However, lung transplant (LTx) remains an important treatment for people with advanced lung disease. This study assessed attitudes and knowledge about LTx in the HEMT era.

Designing Communication Feedback Systems To Reduce Healthcare Providers' Implicit Biases In Patient Encounters.

Healthcare providers' implicit bias, based on patients' physical characteristics and perceived identities, negatively impacts healthcare access, care quality, and outcomes. Feedback tools are needed to help providers identify and learn from their biases. To incorporate providers' perspectives on the most effective ways to present such feedback, we conducted semi-structured design critique sessions with 24 primary care providers.

ConverSense: An Automated Approach to Assess Patient-Provider Interactions using Social Signals.

Patient-provider communication influences patient health outcomes, and analyzing such communication could help providers identify opportunities for improvement, leading to better care. Interpersonal communication can be assessed through "social-signals" expressed in non-verbal, vocal behaviors like interruptions, turn-taking, and pitch. To automate this assessment, we introduce a machine-learning pipeline that ingests audio-streams of conversations and tracks the magnitude of four social-signals: dominance, interactivity, engagement, and warmth.

Improving Vaccine Equity: How Community Engagement and Informatics Facilitate Health System Outreach to Underrepresented Groups.

Background: Given the inequities in access to health care resources like COVID-19 vaccination, health systems should carefully consider how to reach underrepresented groups. Reflecting on vaccine rollout efforts holds insight on the role of community engagement and informatics support in promoting health equity.

Objectives: This study aimed to assess the effectiveness of four outreach strategies deployed by University of Washington (UW) Medicine in improving vaccine equity over traditional vaccine scheduling online or by phone, we report on appointment scheduling and completion of appointments (i.

Qualitative Analysis of Perspectives on Lung Transplant among People with Cystic Fibrosis.

Lung transplant (LTx) is a potentially lifesaving treatment option for individuals with advanced cystic fibrosis (CF), but more people with CF (PwCF) and advanced lung disease die each year than undergo transplant in the United States. Little is known about these individuals' LTx information needs and factors influencing their decision-making process related to transplant. To examine PwCF's experiences with and preferences for provision of LTx information and to identify transplant information needs that CF clinicians are well positioned to address.

Co-designing mind-body technologies for sleep with adolescents.

Sleep is critical for well-being, yet adolescents do not get enough sleep. Mind-body approaches can help. Despite the potential of technology to support mind-body approaches for sleep, there is a lack of research on adolescent preferences for digital mind-body technology.

Improving physical activity among prostate cancer survivors through a peer-based digital walking program.

Physical activity is important for prostate cancer survivors. Yet survivors face significant barriers to traditional structured exercise programs, limiting engagement and impact. Digital programs that incorporate fitness trackers and peer support via social media have potential to improve the reach and impact of traditional support.

Imagining Improved Interactions: Patients' Designs To Address Implicit Bias.

Implicit biases may negatively influence healthcare providers' behaviors toward patients from historically marginalized communities, impacting providers' communication style, clinical decision-making, and delivery of quality care. Existing interventions to mitigate negative experiences of implicit biases are primarily designed to increase recognition and management of stereotypes and prejudices through provider-facing tools and resources. However, there is a gap in understanding and designing interventions from patient perspectives.

Geospatial divide in real-world EHR data: Analytical workflow to assess regional biases and potential impact on health equity.

Real-world data (RWD) like electronic health records (EHR) has great potential for secondary use by health systems and researchers. However, collected primarily for efficient health care, EHR data may not equitably represent local regions and populations, impacting the generalizability of insights learned from it. We assessed the geospatial representativeness of regions in a large health system EHR data using a spatial analysis workflow, which provides a data-driven way to quantify geospatial representation and identify adequately represented regions.

Exploring needs, interests and preferences for digital mind-body tools for adolescents.

Sleep problems are common among adolescents and research on mind-body interventions for sleep is promising. Although technology-based mind-body interventions have been shown to help early adolescents with practicing mind-body approaches, engagement and adherence has been a challenge. Using a Human-Centered Design framework with semi-structured interviews with parent-adolescent dyads, we describe exposure to, interest in, and preferences for digital mind-body technology for sleep.

Usability preferences of people living with cystic fibrosis about a lung transplant education website.

People living with cystic fibrosis (CF) need educational resources about lung transplant prior to engaging in shared decision making with their medical providers. We conducted a usability study to elicit preferences of people living with CF about how didactic and experiential content could be used in an educational resource to learn about lung transplant. We created two prototypes with different design features that participants used in a scenario-based task and evaluated using the System Usability Scale.

Comparing Caregiving Needs in Asian And White Family Caregivers through a Journaling Exercise Delivered by a Conversational Agent.

Asian Americans are the fastest growing racial and ethnic group with nearly 1 in 5 self-identifying as a family caregiver. Understanding the needs of ethnic minority caregivers is needed to develop inclusive technology solutions that aim to support caregivers within these marginalized communities in managing their own health. This study aimed to describe and compare the common needs of Asian American (AA) and White caregivers through data collected using a short message service-based conversational agent.

Approaches for implementing digital interventions for alcohol use disorders in primary care: A qualitative, user-centered design study.

Background: Digital interventions, such as smartphone apps, can be effective in treating alcohol use disorders (AUD). However, efforts to integrate digital interventions into primary care have been challenging. To inform successful implementation, we sought to understand how patients and clinicians preferred to use apps in routine primary care.

Integrating patient voices into the extraction of social determinants of health from clinical notes: ethical considerations and recommendations.

Identifying patients' social needs is a first critical step to address social determinants of health (SDoH)-the conditions in which people live, learn, work, and play that affect health. Addressing SDoH can improve health outcomes, population health, and health equity. Emerging SDoH reporting requirements call for health systems to implement efficient ways to identify and act on patients' social needs.

Implementation Fidelity of Chatbot Screening for Social Needs: Acceptability, Feasibility, Appropriateness.

Objectives: Patient and provider-facing screening tools for social determinants of health have been explored in a variety of contexts; however, effective screening and resource referral remain challenging, and less is known about how patients perceive chatbots as potential social needs screening tools. We investigated patient perceptions of a chatbot for social needs screening using three implementation outcome measures: acceptability, feasibility, and appropriateness.

Methods: We implemented a chatbot for social needs screening at one large public hospital emergency department (ED) and used concurrent triangulation to assess perceptions of the chatbot use for screening.

Take on transplant: human-centered design of a patient education tool to facilitate informed discussions about lung transplant among people with cystic fibrosis.

Objective: Lung transplant (LTx) saves lives in cystic fibrosis (CF). However, many potential candidates express uncertainty about LTx and die before receiving this treatment. CF guidelines recommend LTx education and clinical discussions well before the need for LTx arises, but limited patient resources exist.

Comprehension, utility, and preferences of prostate cancer survivors for visual timelines of patient-reported outcomes co-designed for limited graph literacy: meters and emojis over comics.

Objective: Visual timelines of patient-reported outcomes (PRO) can help prostate cancer survivors manage longitudinal data, compare with population averages, and consider future trajectories. PRO visualizations are most effective when designed with deliberate consideration of users. Yet, graph literacy is often overlooked as a design constraint, particularly when users with limited graph literacy are not engaged in their development.

Maybe they had a bad day: how LGBTQ and BIPOC patients react to bias in healthcare and struggle to speak out.

Objective: People who experience marginalization, including Black, Indigenous, People of Color (BIPOC) and Lesbian, Gay, Bisexual, Transgender, Queer, Plus (ie, all other marginalized genders and sexual orientations) people (LGBTQ+) experience discrimination during healthcare interactions, which negatively impacts patient-provider communication and care. Yet, scarce research examines the lived experience of unfair treatment among patients from marginalized groups to guide patient-centered tools that improve healthcare equity.

Materials And Methods: We interviewed 25 BIPOC and/or LGBTQ+ people about their experiences of unfair treatment and discrimination when visiting healthcare providers.

Battling Bias in Primary Care Encounters: Informatics Designs to Support Clinicians.

Although clinical training in implicit bias is essential for healthcare equity, major gaps remain both for effective educational strategies and for tools to help identify implicit bias. To understand the perspectives of clinicians on the design of these needed strategies and tools, we conducted 21 semi-structured interviews with primary care clinicians about their perspectives and design recommendations for tools to improve patient-centered communication and to help mitigate implicit bias. Participants generated three types of solutions to improve communication and raise awareness of implicit bias: digital nudges, guided reflection, and data-driven feedback.

Design of digital walking programs that engage prostate cancer survivors: Needs and preferences from focus groups.

The majority of prostate cancer survivors do not meet physical activity (PA) recommendations. Although technology has shown to promote PA, engagement has been a challenge. This mixed method study characterizes survivors' needs and preferences for digital walking programs Through focus groups and surveys, we engaged prostate cancer support groups to describe PA motivators and barriers, interest in improving PA, and preferences for design features of a future digital walking program.

Implementation matters: How patient experiences differ when genetic counseling accompanies the return of genetic variants of uncertain significance.

Precision medicine presents challenges for effective return of results (ROR) to patients, particularly for variants of uncertain significance (VUS) where the need for genetic counseling and the impact of results are underexplored. We investigated patients' experiences with VUS ROR. Through interviews we compared experiences of patients who were referred to genetic counseling with those not referred.

Broken down by bias: Healthcare biases experienced by BIPOC and LGBTQ+ patients.

Bias toward historically marginalized patients affects patient-provider interactions and can lead to lower quality of care and poor health outcomes for patients who are Black, Indigenous, People of Color (BIPOC) and Lesbian, Gay, Bisexual, Transgender and Gender Diverse (LGBTQ+). We gathered experiences with biased healthcare interactions and suggested solutions from 25 BIPOC and LGBTQ+ people. Through qualitative thematic analysis of interviews, we identified ten themes.

A learning health systems approach to integrating electronic patient-reported outcomes across the health care organization.

Introduction: Foundational to a learning health system (LHS) is the presence of a data infrastructure that can support continuous learning and improve patient outcomes. To advance their capacity to drive patient-centered care, health systems are increasingly looking to expand the electronic capture of patient data, such as electronic patient-reported outcome (ePRO) measures. Yet ePROs bring unique considerations around workflow, measurement, and technology that health systems may not be poised to navigate.