Examining Linguistic Differences in Electronic Health Records for Diverse Patients With Diabetes: Natural Language Processing Analysis.

Background: Individuals from minoritized racial and ethnic backgrounds experience pernicious and pervasive health disparities that have emerged, in part, from clinician bias. Objective: We used a natural language processing approach to examine whether linguistic markers in electronic health record (EHR) notes differ based on the race and ethnicity of the patient. To validate this methodological approach, we also assessed the extent to which clinicians perceive linguistic markers to be indicative of bias. Methods: In this cross-sectional study, we extracted EHR notes for patients who were aged 18 years or older; had more than 5 years of diabetes diagnosis codes; and received care between 2006 and 2014 from family physicians, general internists, or endocrinologists practicing in an urban, academic network of clinics. The race and ethnicity of patients were defined as White non-Hispanic, Black non-Hispanic, or Hispanic or Latino. We hypothesized that Sentiment Analysis and Social Cognition Engine (SEANCE) components (ie, negative adjectives, positive adjectives, joy words, fear and disgust words, politics words, respect words, trust verbs, and well-being words) and mean word count would be indicators of bias if racial differences emerged. We performed linear mixed effects analyses to examine the relationship between the outcomes of interest (the SEANCE components and word count) and patient race and ethnicity, controlling for patient age. To validate this approach, we asked clinicians to indicate the extent to which they thought variation in the use of SEANCE language domains for different racial and ethnic groups was reflective of bias in EHR notes. Results: We examined EHR notes (n=12,905) of Black non-Hispanic, White non-Hispanic, and Hispanic or Latino patients (n=1562), who were seen by 281 physicians. A total of 27 clinicians participated in the validation study. In terms of bias, participants rated negative adjectives as 8.63 (SD 2.06), fear and disgust words as 8.11 (SD 2.15), and positive adjectives as 7.93 (SD 2.46) on a scale of 1 to 10, with 10 being extremely indicative of bias. Notes for Black non-Hispanic patients contained significantly more negative adjectives (coefficient 0.07, SE 0.02) and significantly more fear and disgust words (coefficient 0.007, SE 0.002) than those for White non-Hispanic patients. The notes for Hispanic or Latino patients included significantly fewer positive adjectives (coefficient -0.02, SE 0.007), trust verbs (coefficient -0.009, SE 0.004), and joy words (coefficient -0.03, SE 0.01) than those for White non-Hispanic patients. Conclusions: This approach may enable physicians and researchers to identify and mitigate bias in medical interactions, with the goal of reducing health disparities stemming from bias.

Storylines of family medicine II: foundational building blocks-context, community and health.

Storylines of Family Medicine is a 12-part series of thematically linked mini-essays with accompanying illustrations that explore the many dimensions of family medicine, as interpreted by individual family physicians and medical educators in the USA and elsewhere around the world. In 'II: foundational building blocks-context, community and health', authors address the following themes: 'Context-grounding family medicine in time, place and being', 'Recentring community', 'Community-oriented primary care', 'Embeddedness in practice', 'The meaning of health', 'Disease, illness and sickness-core concepts', 'The biopsychosocial model', 'The biopsychosocial approach' and 'Family medicine as social medicine.' May readers grasp new implications for medical education and practice in these essays.

ChatGPT's Performance in Cardiac Arrest and Bradycardia Simulations Using the American Heart Association's Advanced Cardiovascular Life Support Guidelines: Exploratory Study.

BACKGROUND: ChatGPT is the most advanced large language model to date, with prior iterations having passed medical licensing examinations, providing clinical decision support, and improved diagnostics. Although limited, past studies of ChatGPT's performance found that artificial intelligence could pass the American Heart Association's advanced cardiovascular life support (ACLS) examinations with modifications. ChatGPT's accuracy has not been studied in more complex clinical scenarios. As heart disease and cardiac arrest remain leading causes of morbidity and mortality in the United States, finding technologies that help increase adherence to ACLS algorithms, which improves survival outcomes, is critical. OBJECTIVE: This study aims to examine the accuracy of ChatGPT in following ACLS guidelines for bradycardia and cardiac arrest. METHODS: We evaluated the accuracy of ChatGPT's responses to 2 simulations based on the 2020 American Heart Association ACLS guidelines with 3 primary outcomes of interest: the mean individual step accuracy, the accuracy score per simulation attempt, and the accuracy score for each algorithm. For each simulation step, ChatGPT was scored for correctness (1 point) or incorrectness (0 points). Each simulation was conducted 20 times. RESULTS: ChatGPT's median accuracy for each step was 85% (IQR 40%-100%) for cardiac arrest and 30% (IQR 13%-81%) for bradycardia. ChatGPT's median accuracy over 20 simulation attempts for cardiac arrest was 69% (IQR 67%-74%) and for bradycardia was 42% (IQR 33%-50%). We found that ChatGPT's outputs varied despite consistent input, the same actions were persistently missed, repetitive overemphasis hindered guidance, and erroneous medication information was presented. CONCLUSIONS: This study highlights the need for consistent and reliable guidance to prevent potential medical errors and optimize the application of ChatGPT to enhance its reliability and effectiveness in clinical practice.

Maternal health outcomes associated with ambient air pollution: An umbrella review of systematic reviews and meta-analyses.

A growing body of literature demonstrated an association between exposure to ambient air pollution and maternal health outcomes with mixed findings. The objective of this umbrella review was to systematically summarize the global evidence on the effects of air pollutants on maternal health outcomes. We adopted the Joanna Briggs Institute (JBI) methodology and Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) reporting standards for this umbrella review. We conducted a comprehensive search across six major electronic databases and other sources to identify relevant systematic reviews and meta-analyses (SRMAs) published from the inception of these databases up to June 30, 2023. Out of 2399 records, 20 citations matched all pre-determined eligibility criteria that include SRMAs focusing on exposure to air pollution and its impact on maternal health, reported quantitative measures or summary effects, and published in peer-reviewed journals in the English language. The risk of bias of included SRMAs was evaluated based on the JBI critical appraisal checklist. All SRMAs reported significant positive associations between ambient air pollution and several maternal health outcomes. Specifically, particulate matter (PM), SO2, and NO demonstrated positive associations with gestational diabetes mellitus (GDM). Moreover, PM and NO2 showed a consistent positive relationship with hypertensive disorder of pregnancy (HDP) and preeclampsia (PE). Although limited, available evidence highlighted a positive correlation between PM and gestational hypertension (GH) and spontaneous abortion (SAB). Only one meta-analysis reported the effects of air pollution on maternal postpartum depression (PPD) where only PM10 showed a significant positive relationship. Limited studies were identified from low- and middle-income countries (LMICs), suggesting evidence gap from the global south. This review necessitates further research on underrepresented regions and communities to strengthen evidence on this critical issue. Lastly, interdisciplinary policymaking and multilevel interventions are needed to alleviate ambient air pollution and associated maternal health disparities.

Population-based assessment of the burden of COVID-19 infection in African countries: a first-year report card and public health implications.

Background: The COVID-19 pandemic constitutes a global health threat and poses a major burden on the African continent. We assessed the real-world burden of COVID-19 infection in African Union (AU) member states to determine the distributional patterns of epidemiological measures during the first 1 year of the pandemic. Methods: This retrospective cross-sectional study utilized COVID-19 data from publicly available data repositories of the African Center for Disease Control and Prevention and Our World in Data for the period February 2020 to January 2021. AU member states were classified into low, medium, and high burdens based on COVID-19 morbidity. We conducted descriptive and inferential analyses of COVID-19-reported cases, deaths, recoveries, active cases, COVID-19 tests, and epidemiological measures that included morbidity and mortality rates, case fatality rate (CFR), and case ratios. Results: A total of 3.21 million cases were reported during the 1-year period, with 2.6 million recoveries, 536,784 cases remaining active, and 77,486 deaths. Most countries (49.1%, n = 26) in AU experienced a low burden of COVID-19 infection compared to 28.3% (n = 15) with medium burden and 22.6% (n = 12) with high burden. AU nations with a high burden of the disease were mainly in the northern and southern regions. South Africa recorded the highest number of cases (1.31 million), followed by Morocco with 457,625 and Tunisia with 175,065 cases. Correspondently, death tolls for these countries were 36,467, 7888, and 5528 deaths, respectively. Of the total COVID-19 tests performed (83.8 million) during the first 1 year, 62.43% were from high-burden countries. The least testing occurred in the medium-burden (18.42%) countries. The overall CFR of AU was 2.21%. A morbidity rate of 327.52/105 population and mortality rate of 5.96/105 population were recorded during the first 1-year period with significant variations (p < 0.0001) across burden levels. Continental morbidity and mortality rates of 17,359/105 and 315.933/105 populations were recorded with significant correlation (r = 0.863, p < 0.0001) between them and variations across selected epidemiological measures by COVID-19 burden levels. Conclusion: Understanding the true burden of the disease in AU countries is important for establishing the impact of the pandemic in the African continent and for intervention planning, preparedness, and deployment of resources during COVID-19 surges and future pandemics.

Medical-Legal Partnership Effects on Mental Health, Health Care Use, and Quality of Life in Primary Care: A Randomized Clinical Trial.

PURPOSE: To determine whether an immediate referral to a medical-legal partnership (MLP), compared with a 6-month waitlist control, improved mental health, health care use, and quality of life. METHODS: This trial randomly assigned individuals to an immediate referral or a wait-list control. The MLP involved a collaboration between the primary care clinic and a legal services organization. The primary outcome was stress (6 months) as measured by the Perceived Stress Scale (PSS). Secondary measures included the Center for Epidemiologic Studies Depression Scale; Generalized Anxiety Disorder scale (GAD-7); Patient-Reported Outcomes Measurement Information System (PROMIS); and emergency department (ED), urgent care, and hospital visits. Assessments were at baseline and 3-, 6-, and 9-month follow-ups. Bayesian statistical inference and a 75% posterior probability threshold were used to identify noteworthy differences. RESULTS: Immediate referral was associated with lower PSS scores and higher GAD-7 scores. PROMIS scores were higher for the immediate referral group with respect to several subdomains. At 6 months, the immediate referral group demonstrated 21% fewer ED visits and 75.6% more hospital visits. CONCLUSION: Immediate referral to the MLP was associated with lower stress and a lower rate of ED visits but higher anxiety and a higher rate of hospital visits. TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT03805126.

Racial/Ethnic Minority Identifying Family Physicians Are More Likely to Work in Solo Practices.

While the overall proportion of family physicians who work in solo practices has been steadily declining, Black, Hispanic/Latino, and Asian family physicians are more likely to work in these settings. Given their association with high levels of continuity and improved health outcomes, and given patient preference for racial concordance with their physicians, policy makers and payors should consider how to support family physicians in solo practice in the interest of promoting access to and quality of care for ethnic/racial minorities.

An Assessment of How Clinicians and Staff Members Use a Diabetes Artificial Intelligence Prediction Tool: Mixed Methods Study.

BACKGROUND: Nearly one-third of patients with diabetes are poorly controlled (hemoglobin A1c≥9%). Identifying at-risk individuals and providing them with effective treatment is an important strategy for preventing poor control. OBJECTIVE: This study aims to assess how clinicians and staff members would use a clinical decision support tool based on artificial intelligence (AI) and identify factors that affect adoption. METHODS: This was a mixed methods study that combined semistructured interviews and surveys to assess the perceived usefulness and ease of use, intent to use, and factors affecting tool adoption. We recruited clinicians and staff members from practices that manage diabetes. During the interviews, participants reviewed a sample electronic health record alert and were informed that the tool uses AI to identify those at high risk for poor control. Participants discussed how they would use the tool, whether it would contribute to care, and the factors affecting its implementation. In a survey, participants reported their demographics; rank-ordered factors influencing the adoption of the tool; and reported their perception of the tool's usefulness as well as their intent to use, ease of use, and organizational support for use. Qualitative data were analyzed using a thematic content analysis approach. We used descriptive statistics to report demographics and analyze the findings of the survey. RESULTS: In total, 22 individuals participated in the study. Two-thirds (14/22, 63%) of respondents were physicians. Overall, 36% (8/22) of respondents worked in academic health centers, whereas 27% (6/22) of respondents worked in federally qualified health centers. The interviews identified several themes: this tool has the potential to be useful because it provides information that is not currently available and can make care more efficient and effective; clinicians and staff members were concerned about how the tool affects patient-oriented outcomes and clinical workflows; adoption of the tool is dependent on its validation, transparency, actionability, and design and could be increased with changes to the interface and usability; and implementation would require buy-in and need to be tailored to the demands and resources of clinics and communities. Survey findings supported these themes, as 77% (17/22) of participants somewhat, moderately, or strongly agreed that they would use the tool, whereas these figures were 82% (18/22) for usefulness, 82% (18/22) for ease of use, and 68% (15/22) for clinic support. The 2 highest ranked factors affecting adoption were whether the tool improves health and the accuracy of the tool. CONCLUSIONS: Most participants found the tool to be easy to use and useful, although they had concerns about alert fatigue, bias, and transparency. These data will be used to enhance the design of an AI tool.

Assessment of Unmet Health-Related Social Needs Among Patients With Mental Illness Enrolled in Medicare Advantage.

Importance: A large body of literature has found associations between unmet health-related social needs (HRSNs) and adverse mental health outcomes. A comparative analysis of the risks associated with HRSNs among patients with varying severity of mental illness and an assessment of how these risks compare with those of individuals without mental illness are needed. Objective: To examine the prevalence and risks of HRSNs among patients with serious and persistent mental illness (SPMI), patients with mental health diagnoses but no serious and persistent mental illness (non-SPMI), and patients with both SPMI and non-SPMI compared with individuals without mental illness. Design, Setting, and Participants: This retrospective cohort study used data from the Accountable Health Communities HRSN Screening Tool surveys, which target a nationally representative sample of Medicare Advantage members of a large payer (Humana Inc). The surveys were conducted between October 16, 2019, and February 29, 2020. Of the initial 329 008 eligible Medicare Advantage enrollees, 70 273 responded to the survey (21.4% response rate). Of those, 56 081 respondents (79.8%) had complete survey responses and were included in the final analytic sample. Main Outcomes and Measures: Outcomes of interest included 7 HRSNs (financial strain, food insecurity, housing instability, housing quality, severe loneliness, transportation problems, and utility affordability) based on responses to the survey. The major independent variable was the presence of mental illness up to 12 months preceding the date of survey completion. Codes indicating mental illness listed as the primary, principal, or secondary diagnoses of a patient's inpatient or outpatient medical claims data were identified, and participants were grouped into 4 cohorts: SPMI, non-SPMI, SPMI plus non-SPMI, and no mental illness. Results: Among 56 081 older adults, the mean (SD) age was 71.31 (8.59) years; 32 717 participants (58.3%) were female, and 43 498 (77.6%) were White. A total of 21 644 participants (38.6%) had at least 1 mental illness diagnosis in the past year, 30 262 (54.0%) had an HRSN, and 14 163 (25.3%) had both mental illness and an HRSN. Across all specific HRSNs, the odds of experiencing the respective HRSN was most substantial for those with SPMI plus non-SPMI vs those with only non-SPMI or SPMI. The HRSN with the largest risk differences among the study cohorts was severe loneliness; compared with the cohort without mental illness, the non-SPMI cohort had 2.07 times higher odds (95% CI, 1.84-2.32; P < .001), the SPMI cohort had 3.35 times higher odds (95% CI, 3.03-3.71; P < .001), and the SPMI plus non-SPMI cohort had 5.13 times higher odds (95% CI, 4.68-5.61; P < .001) of severe loneliness. Conclusions and Relevance: In this study, the increased risk of having HRSNs associated with SPMI, alone or in combination with non-SPMI, emphasizes the need for more targeted interventions to address social needs in this vulnerable population.

Competencies for the Use of Artificial Intelligence in Primary Care.

The artificial intelligence (AI) revolution has arrived for the health care sector and is finally penetrating the far-reaching but perpetually underfinanced primary care platform. While AI has the potential to facilitate the achievement of the Quintuple Aim (better patient outcomes, population health, and health equity at lower costs while preserving clinician well-being), inattention to primary care training in the use of AI-based tools risks the opposite effects, imposing harm and exacerbating inequalities. The impact of AI-based tools on these aims will depend heavily on the decisions and skills of primary care clinicians; therefore, appropriate medical education and training will be crucial to maximize potential benefits and minimize harms. To facilitate this training, we propose 6 domains of competency for the effective deployment of AI-based tools in primary care: (1) foundational knowledge (what is this tool?), (2) critical appraisal (should I use this tool?), (3) medical decision making (when should I use this tool?), (4) technical use (how do I use this tool?), (5) patient communication (how should I communicate with patients regarding the use of this tool?), and (6) awareness of unintended consequences (what are the "side effects" of this tool?). Integrating these competencies will not be straightforward because of the breadth of knowledge already incorporated into family medicine training and the constantly changing technological landscape. Nonetheless, even incremental increases in AI-relevant training may be beneficial, and the sooner these challenges are tackled, the sooner the primary care workforce and those served by it will begin to reap the benefits.

Evaluating a contact tracing course: How universities can develop the public health workforce.

OBJECTIVES: To describe the participants of a university-based COVID-19 contact tracing course and determine whether the course changed knowledge, attitudes, and intention to participate in contact tracing. PARTICIPANTS: Faculty, staff, and students were eligible. METHODS: Surveys evaluated the impact of the course on participant intentions to engage in contact tracing. Logistic regression identified characteristics associated with increased likelihood of participating in contact tracing. RESULTS: Nearly 800 individuals participated, of whom 26.2% identified as Hispanic/Latino and 14.0% as Black. Nearly half (48.8%) planned to conduct contact tracing. While attitudes did not change, knowledge improved (67.9% vs. 93.8% scores on assessments; p < 0.001). Younger participants and Black individuals were more more likely to be confident that they would participate in contact tracing. CONCLUSIONS: Course completion was associated with increased knowledge. Participants were racially and ethnically diverse, highlighting how universities can partner with health departments to develop workforces that reflect local communities.

Medical School Characteristics, Policies, and Practices That Support Primary Care Specialty Choice: A Scoping Review of 5 Decades of Research.

BACKGROUND AND OBJECTIVES: The United States, like many other nations, faces a chronic shortage of primary care physicians. The purpose of this scoping review was to synthesize literature describing evidence-based institutional practices and interventions that support medical students' choices of primary care specialties, published in the United States, Canada, Australia, and New Zealand. METHODS: We surveyed peer-reviewed, published research. An experienced medical librarian conducted searches of multiple databases. Articles were selected for inclusion based on explicit criteria. We charted articles by topic, methodology, year of publication, journal, country of origin, and presence or absence of funding. We then scored included articles for quality. Finally, we defined and described six common stages of development of institutional interventions. RESULTS: We reviewed 8,083 articles and identified 199 articles meeting inclusion criteria and 41 related articles. As a group, studies were of low quality, but improved over time. Most were quantitative studies conducted in the United States. Many studies utilized one of four common methodologic approaches: retrospective surveys, studies of programs or curricula, large-scale multi-institution comparisons, and single-institution exemplars. Most studies developed groundwork or examined effectiveness or impact, with few studies of planning or piloting. Few studies examined state or regional workforce outcomes. CONCLUSIONS: Research examining medical school interventions and institutional practices to support primary care specialty choice would benefit from stronger theoretical grounding, greater investment in planning and piloting, consistent use of language, more qualitative methods, and innovative approaches. Robust funding mechanisms are needed to advance these goals.

Impact of Curricula and Electives on Primary Care Specialty Choice: A Narrative Synthesis.

BACKGROUND AND OBJECTIVES: Educational components and electives that may influence medical student choice of primary care careers have been studied individually, but not reviewed or synthesized. Examining educational components and electives in a comprehensive manner may inform evidence-based approaches to raise the number of primary care physicians in the United States and help optimize use of finite resources. We sought to determine evidence-based educational components and electives associated with increased medical student choice of primary care careers. METHODS: We searched PubMed, Scopus, and CINAHL for undergraduate medical education articles in English describing an educational component or elective and outcome relevant to primary care specialty choice. We assessed titles, then abstracts, and finally full texts for inclusion in a narrative synthesis. RESULTS: The searches returned 11,211 articles and we found 42 that met the inclusion criteria. The most described components were outpatient clinical rotations, preclinical courses, and preceptorships. The most common electives were international health, summer preceptorships, and rural medicine. While most articles described curricula that appeared to have a positive correlation with primary care specialty choice, six articles found limited benefit. In sum, results were mixed. CONCLUSIONS: The current literature is limited, and many contemporary electives have not been studied with respect to primary care choice. Increased attention and funding to studying the impact of electives and other educational components on primary care specialty choice is warranted.

Examining longitudinal disparities in COVID-19 prevalence in the U.S.: a county level growth rate perspective.

Background: The objectives of the present study are to understand the longitudinal variability in COVID-19 reported cases at the county level and to associate the observed rates of infection with the adoption and lifting of stay-home orders.Materials and Methods: The study uses the trajectory of the pandemic in a county and controls for social and economic risk factors, physical environment, and health behaviors to elucidate the social determinants contributing to the observed rates of infection.Results and conclusion: Results indicated that counties with higher percentages of young individuals, racial and ethnic minorities and, higher population densities experienced greater difficulty suppressing transmission.Except for Education and the Gini Index, all factors were influential on the rate of COVID-19 spread before and after stay-home orders. However, after lifting the orders, six of the factors were not influential on the rate of spread; these included: African-Americans, Population Density, Single Parent Households, Average Daily PM2.5, HIV Prevalence Rate, and Home Ownership. It was concluded that different factors from the ones controlling the initial spread of COVID-19 are at play after stay-home orders are lifted.KEY MESSAGESObserved rates of COVID-19 infection at the County level in the U.S. are not directly associated with adoption and lifting of stay-home orders.Disadvantages in sociodemographic determinants negatively influence the rate of COVID-19 spread.Counties with more young individuals, racial and ethnic minorities, and higher population densities have greater difficulty suppressing transmission.

Associations between Patient- and Provider Level Factors, and Telemedicine Use in Family Medicine Clinics.

INTRODUCTION: Increased telemedicine implementation may promote primary care access. However, gaps in telemedicine uptake may perpetuate existing disparities in primary care access. This study assessed provider- and patient-level factors associated with telemedicine use in community-based family practice clinics. METHODS: This retrospective study used electronic medical records data from a large Federally Qualified Health Center. A 3-level mixed-effects logistic regression model explored predictors of telemedicine use, with provider and patient as random effects. RESULTS: The analytic sample included 37,428 unique patients with 106,567 primary care encounters with 42 family medicine providers. Fifty-seven percent of the sample identified as Hispanic, 28% non-Hispanic White, and 11% non-Hispanic Black. Compared to Hispanics, non-Hispanic White patients had 61% higher odds of a telemedicine visit, and non-Hispanic Black patients had 32% higher odds of a telemedicine visit. The odds of telemedicine use were lower for those who were uninsured. Those residing in metropolitan areas or medically underserved areas had greater odds of a telemedicine appointment. Commute time exhibited a dose-response relationship with telemedicine use. Provider characteristics were not significantly associated with telemedicine use. DISCUSSION: While provider characteristics were not associated with telemedicine use, greater focus on patient characteristics specific to the population served is necessary.

Primary Care: The Actual Intelligence Required for Artificial Intelligence to Advance Health Care and Improve Health.

With conversational agents triaging symptoms, cameras aiding diagnoses, and remote sensors monitoring vital signs, the use of artificial intelligence (AI) outside of hospitals has the potential to improve health, according to a recently released report from the National Academy of Medicine. Despite this promise, the success of AI is not guaranteed, and stakeholders need to be involved with its development to ensure that the resulting tools can be easily used by clinicians, protect patient privacy, and enhance the value of the care delivered. A crucial stakeholder group missing from the conversation is primary care. As the nation's largest delivery platform, primary care will have a powerful impact on whether AI is adopted and subsequently exacerbates health disparities. To leverage these benefits, primary care needs to serve as a medical home for AI, broaden its teams and training, and build on government initiatives and funding.

Transition to telemedicine and its impact on missed appointments in community-based clinics.

BACKGROUND AND OBJECTIVE: The Coronavirus Aid, Relief, and Economic Security Act led to the rapid implementation of telemedicine across health care office settings. Whether this transition to telemedicine has any impact on missed appointments is yet to be determined. This study examined the relationship between telemedicine usage and missed appointments during the COVID-19 pandemic. METHOD: This retrospective study used appointment-level data from 55 Federally Qualified Health Centre clinics in Texas between March and November 2020. To account for the nested data structure of repeated appointments within each patient, a mixed-effects multivariable logistic regression model was used to examine associations between telemedicine use and missed appointments, adjusting for patient sociodemographic characteristics, geographic classification, past medical history, and clinic characteristics. The independent variable was having a telemedicine appointment, defined as an audiovisual consultation started and finalized via a telemedicine platform. The outcome of interest was having a missed appointment (yes/no) after a scheduled and confirmed medical appointment. Results from this initial model were stratified by appointment type (in-person vs. telemedicine). RESULTS: The analytic sample included 278,171 appointments for 85,413 unique patients. The overall missed appointment rate was 18%, and 25% of all appointments were telemedicine appointments. Compared to in-person visits, telemedicine visits were less likely to result in a missed appointment (OR = 0.87, p < .001). Compared to Whites, Asians were less likely to have a missed appointment (OR = 0.82, p < .001) while African Americans, Hispanics, and American Indians were all significantly more likely to have missed appointments (OR = 1.61, p < .001; OR = 1.19, p = .01; OR = 1.22, p < .01, respectively). Those accessing mental health services (OR = 1.57 for in-person and 0.78 for telemedicine) and living in metropolitan areas (OR = 1.15 for in-person and 0.82 for telemedicine) were more likely to miss in-person appointments but less likely to miss telemedicine appointments. Patients with frequent medical visits or those living with chronic diseases were more likely to miss in-person appointments but less likely to miss telemedicine appointments. CONCLUSIONS: Telemedicine is strongly associated with fewer missed appointments. Although our findings suggest a residual lag in minority populations, specific patient populations, including those with frequent prior visits or chronic conditions, those seeking mental health services, and those living in metropolitan areas were less likely to miss telemedicine appointments than in-person visits. These findings highlight how telemedicine can enable effective and accessible care by reducing missed healthcare appointments.KEY MESSAGESTelemedicine was associated with 13% lower odds of missed appointments.Patients with frequent medical visits or those living with chronic diseases were less likely to miss telemedicine appointments but more likely to miss in-person appointments.Patients seeking mental health services were less likely to miss telemedicine appointments but more likely to miss in-person appointments.Similarly, those living in metropolitan areas were less likely to miss telemedicine appointments but more likely to miss in-person appointments.