Physician Turnover in the United States.

BACKGROUND: Medical groups, health systems, and professional associations are concerned about potential increases in physician turnover, which may affect patient access and quality of care. OBJECTIVE: To examine whether turnover has changed over time and whether it is higher for certain types of physicians or practice settings. DESIGN: The authors developed a novel method using 100% of traditional Medicare billing to create national estimates of turnover. Standardized turnover rates were compared by physician, practice, and patient characteristics. SETTING: Traditional Medicare, 2010 to 2020. PARTICIPANTS: Physicians billing traditional Medicare. MEASUREMENTS: Indicators of physician turnover-physicians who stopped practicing and those who moved from one practice to another-and their sum. RESULTS: The annual rate of turnover increased from 5.3% to 7.2% between 2010 and 2014, was stable through 2017, and increased modestly in 2018 to 7.6%. Most of the increase from 2010 to 2014 came from physicians who stopped practicing increasing from 1.6% to 3.1%; physicians moving increased modestly from 3.7% to 4.2%. Modest but statistically significant (P < 0.001) differences existed across rurality, physician sex, specialty, and patient characteristics. In the second and third quarters of 2020, quarterly turnover was slightly lower than in the corresponding quarters of 2019. LIMITATION: Measurement was based on traditional Medicare claims. CONCLUSION: Over the past decade, physician turnover rates have had periods of increase and stability. These early data, covering the first 3 quarters of 2020, give no indication yet of the COVID-19 pandemic increasing turnover, although continued tracking of turnover is warranted. This novel method will enable future monitoring and further investigations into turnover. PRIMARY FUNDING SOURCE: The Physicians Foundation Center for the Study of Physician Practice and Leadership.

Measuring Public Reaction to Violence Against Doctors in China: Interrupted Time Series Analysis of Media Reports.

BACKGROUND: Violence against doctors in China is a serious problem that has attracted attention from both domestic and international media. OBJECTIVE: This study investigates readers' responses to media reports on violence against doctors to identify attitudes toward perpetrators and physicians and examine if such trends are influenced by national policies. METHODS: We searched 17 Chinese violence against doctors reports in international media sources from 2011 to 2020. We then tracked back the original reports and web crawled the 19,220 comments in China. To ascertain the possible turning point of public opinion, we searched violence against doctors-related policies from Tsinghua University ipolicy database from 2011 to 2020, and found 19 policies enacted by the Chinese central government aimed at alleviating the intense patient-physician relationship. We then conducted a series of interrupted time series analyses to examine the influence of these policies on public sentiment toward violence against doctors over time. RESULTS: The interrupted time series analysis (ITSA) showed that the change in public sentiment toward violence against doctors reports was temporally associated with government interventions. The declarations of 10 of the public policies were followed by increases in the proportion of online public opinion in support of doctors (average slope changes of 0.010, P<.05). A decline in the proportion of online public opinion that blamed doctors (average level change of -0.784, P<.05) followed the declaration of 3 policies. CONCLUSIONS: The government's administrative interventions effectively shaped public opinion but only temporarily. Continued public policy interventions are needed to sustain the reduction of hostility toward medical doctors.

Frontline Perspectives on Physician Burnout and Strategies to Improve Well-Being: Interviews with Physicians and Health System Leaders.

BACKGROUND: Nationally over 50% of physicians report symptoms of burnout. OBJECTIVE: To understand the perspectives of health system leaders and frontline physicians on contributors to physician burnout and strategies to improve well-being. DESIGN: We conducted in-depth interviews with health system leaders and frontline physicians at a large, predominantly fee-for-service, multispecialty group practice with approximately 1300 physicians. PARTICIPANTS: The 17 participants included 15 physicians, (12 Internal Medicine and Family Medicine physicians and 3 from other specialties), 11 individuals in leadership roles, and 11 women. APPROACH: Interviews included a review of factors associated with burnout at the organization, asking participants which factors they believed contributed to burnout, questions about experiences of burnout, and what specific changes would improve well-being. KEY RESULTS: All 17 participants agreed that organizational factors were key contributors to burnout, while only 9 mentioned the salience of individual factors: "It does not matter how resilient or positive you are, the work environment, especially in primary care will eventually be a problem." An increasing workload associated with the electronic health record (EHR) and a culture focused on productivity were cited as contributing to burnout, especially among physicians in Internal Medicine and Family Medicine (primary care) departments. Physicians in primary care, women, and leaders described multiple barriers to well-being. Participants described responding to increased workloads by reducing clinical work hours. Participants suggested reducing and compensating EHR work, expanding care teams/support staff, reducing use of metrics, providing more support to leaders, changing the business model, and increasing positivity and collegiality, as essential to improving well-being. CONCLUSION: Interviews reveal a variety of interacting factors contributing to physician burnout. Reducing clinical work hours has become a coping strategy. Changes recommended to improve physician well-being include increasing support staff, reducing EHR workload, changing revenue generation and compensation approaches, and shifting organizational culture to place more value on physician wellness.

EHR audit logs: A new goldmine for health services research?

A byproduct of the transition to electronic health records (EHRs) is the associated observational data that capture EHR users' granular interactions with the medical record. Often referred to as audit log data or event log data, these datasets capture and timestamp user activity while they are logged in to the EHR. These data - alone and in combination with other datasets - offer a new source of insights, which cannot be gleaned from claims data or clinical data, to support health services research and those studying healthcare processes and outcomes. In this commentary, we seek to promote broader awareness of EHR audit log data and to stimulate their use in many contexts. We do so by describing EHR audit log data and offering a framework for their potential uses in quality domains (as defined by the National Academy of Medicine). The framework is illustrated with select examples in the safety and efficiency domains, along with their accompanying methodologies, which serve as a proof of concept. This article also discusses insights and challenges from working with EHR audit log data. Ensuring that researchers are aware of such data, and the new opportunities they offer, is one way to assure that our healthcare system benefits from the digital revolution.

Health-care use and cost for multimorbid persons with dementia in the National Health and Aging Trends Study.

BACKGROUND: Most persons with dementia have multiple chronic conditions; however, it is unclear whether co-existing chronic conditions contribute to health-care use and cost. METHODS: Persons with dementia and ≥2 chronic conditions using the National Health and Aging Trends Study and Medicare claims data, 2011 to 2014. RESULTS: Chronic kidney disease and ischemic heart disease were significantly associated with increased adjusted risk ratios of annual hospitalizations, hospitalization costs, and direct medical costs. Depression, hypertension, and stroke or transient ischemic attack were associated with direct medical and societal costs, while atrial fibrillation was associated with increased hospital and direct medical costs. No chronic condition was associated with informal care costs. CONCLUSIONS: Among older adults with dementia, proactive and ambulatory care that includes informal caregivers along with primary and specialty providers, may offer promise to decrease use and costs for chronic kidney disease, ischemic heart disease, atrial fibrillation, depression, and hypertension.

Gender differences among medical students, house staff, and faculty physicians at high risk for suicide: A HEAR report.

BACKGROUND: In comparison with the general population, physicians, and physicians-in-training are at greater risk for suicide. Although key gender differences in suicide risk factors and behaviors have been identified in the general population, the extent to which these differences apply to physicians and physicians-in-training is unclear. Here, we aimed to identify gender differences in risk factors, clinical presentation, and help-seeking behaviors of medical students, house staff, and physician faculty at high risk for suicide. METHODS: We explored gender differences among 450 physicians and trainees meeting criteria for high suicide risk on anonymous online questionnaires completed between 2009 and 2017. RESULTS: High-risk female trainees and physicians had higher mean Patient Health Questionnaire-9 (PHQ-9) scores compared with the males (11.1, standard deviation [SD] 5.1 vs. 9.8, SD 4.7) and were more likely to endorse feeling worried (73.8% vs. 61.2%), irritable (60.4% vs. 49.4%), and stressed (79.6% vs. 70%). High-risk male trainees and physicians were more likely than females to endorse suicidal thoughts (31.2% vs. 22.1%), intense anger (24.3% vs. 16.1%), drinking too much (31.2% vs. 22.3%), and recreational drug or prescription medication use without clinically appropriate follow-up (9.4% vs. 4.3%). There were no gender differences in help-seeking behaviors. CONCLUSIONS: This is the first study to report gender differences among risk factors, presentation, and help-seeking behaviors of physicians, and trainees at high risk for suicide. Our findings are mostly consistent with those of the general population and show that only a minority of at-risk men and women in healthcare sought treatment, highlighting the importance of intervention and suicide prevention in this population.

Using CollaboRATE, a brief patient-reported measure of shared decision making: Results from three clinical settings in the United States.

INTRODUCTION: CollaboRATE is a brief patient survey focused on shared decision making. This paper aims to (i) provide insight on facilitators and challenges to implementing a real-time patient survey and (ii) evaluate CollaboRATE scores and response rates across multiple clinical settings with varied patient populations. METHOD: All adult patients at three United States primary care practices were eligible to complete CollaboRATE post-visit. To inform key learnings, we aggregated all mentions of unanticipated decisions, problems and administration errors from field notes and email communications. Mixed-effects logistic regression evaluated the impact of site, clinician, patient age and patient gender on the CollaboRATE score. RESULTS: While CollaboRATE score increased only slightly with increasing patient age (OR 1.018, 95% CI 1.014-1.021), female patient gender was associated with significantly higher CollaboRATE scores (OR 1.224, 95% CI 1.073-1.397). Clinician also predicts CollaboRATE score (random effect variance 0.146). Site-specific factors such as clinical workflow and checkout procedures play a key role in successful in-clinic implementation and are significantly related to CollaboRATE scores, with Site 3 scoring significantly higher than Site 1 (OR 1.759, 95% CI 1.216 to 2.545) or Site 2 (z=-2.71, 95% CI -1.114 to -0.178). DISCUSSION: This study demonstrates that CollaboRATE can be used in diverse primary care settings. A clinic's workflow plays a crucial role in implementation. Patient experience measurement risks becoming a burden to both patients and administrators. Episodic use of short measurement tools could reduce this burden.

Workflow standardization of a novel team care model to improve chronic care: a quasi-experimental study.

BACKGROUND: Team-based chronic care models have not been widely adopted in community settings, partly due to their varying effectiveness in randomized control trials, implementation challenges, and concerns about physician acceptance. The Palo Alto Medical Foundation designed and implemented "Champion," a novel team-based model that includes new standard work (e.g. proactive patient outreach, pre-visit schedule grooming, depression screening, care planning, health coaching) to support patients' self-management of hypertension and diabetes. We investigated whether Champion improved clinical outcomes. METHODS: We conducted a quasi-experimental study comparing the Champion clinic-level intervention (n = 38 physicians) with a usual care clinic (n = 37 physicians) in Northern California. The primary outcomes, blood pressure and glycohemoglobin (A1c), were analyzed using a piecewise linear growth curve model for patients exposed to a Champion physician visit (n = 3156) or usual care visit (n = 8034) in the two years prior and one year post implementation. Secondary outcomes were provider experience, compared at baseline and 12 months in both the intervention and usual care clinics using multi-level ordered logistic modeling, and electronic health record based fidelity measures. RESULTS: Compared to usual care, in the first 6 months after a Champion physician visit, diabetes patients aged 18-75 experienced an additional -1.13 mm Hg (95% CI: -2.23 to -0.04) decline in diastolic blood pressure and -0.47 (95% CI: -0.61 to -0.33) decline in A1c. There were no additional improvements in blood pressure or A1c 6 to 12 months post physician visit. At 12 months, Champion physicians reported improved experience with managing chronic care patients in 6 of 7 survey items (p < 0.05), but compared to usual, this difference was only statistically significant for one item (p < 0.05). Fidelity to standard work was uneven; depression screening was the most commonly documented element (85% of patients), while care plans were the least (30.8% of patients). CONCLUSIONS: Champion standard work improved glycemic control over the first 6 months and physicians' experience with managing chronic care; changes in blood pressure were not clinically meaningful. Our results suggest the need to understand the relationship between the intervention, the contextual features of implementation, and fidelity to further improve chronic disease outcomes. This study was retrospectively registered with the ISRCTN Registry on March 15, 2017 (ISRCTN11341906).

Patient-initiated Electronic Messages and Quality of Care for Patients With Diabetes and Hypertension in a Large Fee-for-Service Medical Group: Results From a Natural Experiment.

BACKGROUND: Few studies have examined the association between patient-initiated electronic messaging (e-messaging) and clinical outcomes in fee-for-service settings. OBJECTIVE: To estimate the association between patient-initiated e-messages and quality of care among patients with diabetes and hypertension. DESIGN: Longitudinal observational study from 2009 to 2013. In March 2011, the medical group eliminated a $60/year patient user fee for e-messaging and established a provider payment of $3-5 per patient-initiated e-message. Quality of care for patients initiating e-messages was compared before and after March 2011, relative to nonmessaging patients. Propensity score weighting accounted for differences between e-messaging and nonmessaging patients in generalized estimating equations. SETTING: Large multispecialty practice in California compensating providers' fee-for-service. SUBJECTS: Patients with diabetes (N=4232) or hypertension (N=15,463) who had activated their online portal but not e-messaged before e-messaging became free. MEASURES: Quality of care included HEDIS-based process measures for hemoglobin (Hb) A1c, blood pressure, low-density lipoprotein (LDL), nephropathy, and retinopathy tests, and outcome measures for HbA1c, blood pressure, and LDL. E-messaging was measured as counts of patient-initiated e-message threads sent to providers. Patients were categorized into quartiles by e-messaging frequency. RESULTS: The probability of annually completing indicated tests increased by 1%-7% for e-messaging patients, depending on the outcome and e-messaging frequency. E-messaging was associated with small improvements in HbA1c and LDL for some patients with diabetes. CONCLUSION: Patient-initiated e-messaging may increase the likelihood of completing recommended tests, but may not be sufficient to improve clinical outcomes for most patients with diabetes or hypertension without additional interventions.

Patients report better satisfaction with part-time primary care physicians, despite less continuity of care and access.

BACKGROUND: The growing number of primary care physicians (PCPs) reducing their clinical work hours has raised concerns about meeting the future demand for services and fulfilling the continuity and access mandates for patient-centered care. However, the patient's experience of care with part-time physicians is relatively unknown, and may be mediated by continuity and access to care outcomes. OBJECTIVE: We aimed to examine the relationships between a physicians' clinical full-time equivalent (FTE), continuity of care, access to care, and patient satisfaction with the physician. DESIGN: We used a multi-level structural equation estimation, with continuity and access modeled as mediators, for a cross-section in 2010. PARTICIPANTS: The study included family medicine (n = 104) and internal medicine (n = 101) physicians in a multi-specialty group practice, along with their patient satisfaction survey responses (n = 12,688). MAIN MEASURES: Physician level FTE, continuity of care received by patients, continuity of care provided by physician, and a Press Ganey patient satisfaction with the physician score, on a 0-100 % scale, were measured. Access to care was measured as days to the third next-available appointment. KEY RESULTS: Physician FTE was directly associated with better continuity of care received (0.172% per FTE, p < 0.001), better continuity of care provided (0.108% per FTE, p < 0.001), and better access to care (-0.033 days per FTE, p < 0.01), but worse patient satisfaction scores (-0.080% per FTE, p = 0.03). The continuity of care provided was a significant mediator (0.016% per FTE, p < 0.01) of the relationship between FTE and patient satisfaction; but overall, reduced clinical work hours were associated with better patient satisfaction (-0.053 % per FTE, p = 0.03). CONCLUSIONS: These results suggest that PCPs who choose to work fewer clinical hours may have worse continuity and access, but they may provide a better patient experience. Physician workforce planning should consider these care attributes when considering the role of part-time PCPs in practice redesign efforts and initiatives to meet the demand for primary care services.

A Randomized Controlled Effectiveness Trial for PSA Screening Decision Support Interventions in Two Primary Care Settings.

BACKGROUND: Decision support interventions (DESIs) provide a mechanism to translate comparative effectiveness research results into clinical care so that patients are able to make informed decisions. Patient decision support interventions for prostate-specific antigen (PSA) have been shown to promote informed decision making and reduce PSA testing in efficacy trials, but their impact in real world settings is not clear. OBJECTIVE: We performed an effectiveness trial of PSA decision support interventions in primary care. DESIGN: A randomized controlled trial of three distribution strategies was compared to a control. PARTICIPANTS: Participants included 2,550 men eligible for PSA testing (76.6 % of the eligible population) and 2001 survey respondents (60.1 % survey response rate). INTERVENTIONS: The intervention groups were: 1) mailed the DESI in DVD format, 2) offered a shared medical appointment (SMA) to view the DESI with other men and discuss, and 3) both options. MAIN MEASURES: We measured PSA testing identified via electronic medical record at 12 months and DESI use by self-report 4 months after the intervention mailing. KEY RESULTS: We found no differences in PSA testing across the three distribution strategies over a year-long follow-up period: 21 %, 24 %, 22 % in the DESI, SMA, and combined group respectively, compared to 21 % in the control group (p = 0.51). Self-reported DESI use was low across all strategies at 4 months: 16 % in the mailed DESI group, 6 % in the SMA group, and 15 % in the combined group (p = < 0.0001). CONCLUSIONS: Mailing PSA decision support interventions or inviting men to shared medical appointments unrelated to a primary care office visit do not appear to promote informed decision making, or change PSA testing behavior.

Patients' body mass index and blood pressure over time: diagnoses, treatments, and the effects of comorbidities.

BACKGROUND: A national strategic framework to address multiple chronic conditions has called for further research on disease trajectories of patients with comorbidities. METHODS: An observational study using multilevel models to analyze electronic health record data from a multispecialty practice from 2003 to 2010 to examine disease trajectories of patients with at least 2 of 3 common chronic conditions: overweight/obese, hypertension, and depression. Using longitudinal data on up to 110,000 patients, the effects of comorbidities on the probability of having a diagnosis for overweight/obesity or hypertension and on the trajectories of body mass index (BMI) and blood pressure (BP) over time were examined. RESULTS: From 2003 to 2010, the percentage of patients with high BMI receiving an overweight/obesity diagnosis grew from 5.0% to 18.7%, and the percentage of patients with high BP having a hypertension diagnosis rose from 39.9% to 51.7%. The effect of time for patients with high BMI and depression was less than the effect of time for high BMI only patients (P<0.01) in receiving overweight/obesity diagnoses. Co-occurring depression and high BMI was positively associated with BMI trajectory (coefficient=0.06, P<0.01), whereas high BP and high BMI (coefficient=-0.07, P<0.01) or high BP and high BMI and depression (coefficient=-0.05, P<0.01) were negatively associated with BMI trajectories. CONCLUSIONS: Although physicians' recording of diagnoses for patients with high BMI and high BP has improved, significant gaps remain. Some co-occurrence patterns of these 3 conditions not only affected the recognition of overweight/obesity and hypertension over time, but also BMI trajectories over time. Quality improvement efforts should target patients with co-occurring depression and overweight/obesity.

A conceptual model of the role of complexity in the care of patients with multiple chronic conditions.

BACKGROUND: Effective healthcare for people with multiple chronic conditions (MCC) is a US priority, but the inherent complexity makes both research and delivery of care particularly challenging. As part of AHRQ Multiple Chronic Conditions Research Network (MCCRN) efforts, the Network developed a conceptual model to guide research in this area. OBJECTIVE: To synthesize methodological and topical issues relevant to MCC patient care into a framework that can improve the delivery of care and advance future research about caring for patients with MCC. METHODS: The Network synthesized essential constructs for MCC research identified from roundtable discussion, input from expert advisors, and previously published models. RESULTS: The AHRQ MCCRN conceptual model defines complexity as the gap between patient needs and healthcare services, taking into account both the multiple considerations that affect the needs of MCC patients, as well as the contextual factors that influence service delivery. The model reframes processes and outcomes to include not only clinical care quality and experience, but also patient health, well being, and quality of life. The single-condition paradigm for treating needs one-by-one falls apart and highlights the need for care systems to address dynamic patient needs. CONCLUSIONS: Defining complexity in terms of the misalignment between patient needs and services offers new insights in how to research and develop solutions to patient care needs.

Navigating the doctor-patient-AI relationship - a mixed-methods study of physician attitudes toward artificial intelligence in primary care.

BACKGROUND: Artificial intelligence (AI) is a rapidly advancing field that is beginning to enter the practice of medicine. Primary care is a cornerstone of medicine and deals with challenges such as physician shortage and burnout which impact patient care. AI and its application via digital health is increasingly presented as a possible solution. However, there is a scarcity of research focusing on primary care physician (PCP) attitudes toward AI. This study examines PCP views on AI in primary care. We explore its potential impact on topics pertinent to primary care such as the doctor-patient relationship and clinical workflow. By doing so, we aim to inform primary care stakeholders to encourage successful, equitable uptake of future AI tools. Our study is the first to our knowledge to explore PCP attitudes using specific primary care AI use cases rather than discussing AI in medicine in general terms. METHODS: From June to August 2023, we conducted a survey among 47 primary care physicians affiliated with a large academic health system in Southern California. The survey quantified attitudes toward AI in general as well as concerning two specific AI use cases. Additionally, we conducted interviews with 15 survey respondents. RESULTS: Our findings suggest that PCPs have largely positive views of AI. However, attitudes often hinged on the context of adoption. While some concerns reported by PCPs regarding AI in primary care focused on technology (accuracy, safety, bias), many focused on people-and-process factors (workflow, equity, reimbursement, doctor-patient relationship). CONCLUSION: Our study offers nuanced insights into PCP attitudes towards AI in primary care and highlights the need for primary care stakeholder alignment on key issues raised by PCPs. AI initiatives that fail to address both the technological and people-and-process concerns raised by PCPs may struggle to make an impact.

Generative artificial intelligence responses to patient messages in the electronic health record: early lessons learned.

Background: Electronic health record (EHR)-based patient messages can contribute to burnout. Messages with a negative tone are particularly challenging to address. In this perspective, we describe our initial evaluation of large language model (LLM)-generated responses to negative EHR patient messages and contend that using LLMs to generate initial drafts may be feasible, although refinement will be needed. Methods: A retrospective sample (n = 50) of negative patient messages was extracted from a health system EHR, de-identified, and inputted into an LLM (ChatGPT). Qualitative analyses were conducted to compare LLM responses to actual care team responses. Results: Some LLM-generated draft responses varied from human responses in relational connection, informational content, and recommendations for next steps. Occasionally, the LLM draft responses could have potentially escalated emotionally charged conversations. Conclusion: Further work is needed to optimize the use of LLMs for responding to negative patient messages in the EHR.

Measures of empathy and compassion: A scoping review.

Evidence to date indicates that compassion and empathy are health-enhancing qualities. Research points to interventions and practices involving compassion and empathy being beneficial, as well as being salient outcomes of contemplative practices such as mindfulness. Advancing the science of compassion and empathy requires that we select measures best suited to evaluating effectiveness of training and answering research questions. The objective of this scoping review was to 1) determine what instruments are currently available for measuring empathy and compassion, 2) assess how and to what extent they have been validated, and 3) provide an online tool to assist researchers and program evaluators in selecting appropriate measures for their settings and populations. A scoping review and broad evidence map were employed to systematically search and present an overview of the large and diverse body of literature pertaining to measuring compassion and empathy. A search string yielded 19,446 articles, and screening resulted in 559 measure development or validation articles reporting on 503 measures focusing on or containing subscales designed to measure empathy and/or compassion. For each measure, we identified the type of measure, construct being measured, in what context or population it was validated, response set, sample items, and how many different types of psychometrics had been assessed for that measure. We provide tables summarizing these data, as well as an open-source online interactive data visualization allowing viewers to search for measures of empathy and compassion, review their basic qualities, and access original citations containing more detail. Finally, we provide a rubric to help readers determine which measure(s) might best fit their context.

Artificial Intelligence-Generated Draft Replies to Patient Inbox Messages.

Importance: The emergence and promise of generative artificial intelligence (AI) represent a turning point for health care. Rigorous evaluation of generative AI deployment in clinical practice is needed to inform strategic decision-making. Objective: To evaluate the implementation of a large language model used to draft responses to patient messages in the electronic inbox. Design, Setting, and Participants: A 5-week, prospective, single-group quality improvement study was conducted from July 10 through August 13, 2023, at a single academic medical center (Stanford Health Care). All attending physicians, advanced practice practitioners, clinic nurses, and clinical pharmacists from the Divisions of Primary Care and Gastroenterology and Hepatology were enrolled in the pilot. Intervention: Draft replies to patient portal messages generated by a Health Insurance Portability and Accountability Act-compliant electronic health record-integrated large language model. Main Outcomes and Measures: The primary outcome was AI-generated draft reply utilization as a percentage of total patient message replies. Secondary outcomes included changes in time measures and clinician experience as assessed by survey. Results: A total of 197 clinicians were enrolled in the pilot; 35 clinicians who were prepilot beta users, out of office, or not tied to a specific ambulatory clinic were excluded, leaving 162 clinicians included in the analysis. The survey analysis cohort consisted of 73 participants (45.1%) who completed both the presurvey and postsurvey. In gastroenterology and hepatology, there were 58 physicians and APPs and 10 nurses. In primary care, there were 83 physicians and APPs, 4 nurses, and 8 clinical pharmacists. The mean AI-generated draft response utilization rate across clinicians was 20%. There was no change in reply action time, write time, or read time between the prepilot and pilot periods. There were statistically significant reductions in the 4-item physician task load score derivative (mean [SD], 61.31 [17.23] presurvey vs 47.26 [17.11] postsurvey; paired difference, -13.87; 95% CI, -17.38 to -9.50; P < .001) and work exhaustion scores (mean [SD], 1.95 [0.79] presurvey vs 1.62 [0.68] postsurvey; paired difference, -0.33; 95% CI, -0.50 to -0.17; P < .001). Conclusions and Relevance: In this quality improvement study of an early implementation of generative AI, there was notable adoption, usability, and improvement in assessments of burden and burnout. There was no improvement in time. Further code-to-bedside testing is needed to guide future development and organizational strategy.

Patients' Perspectives on Plans Generated During Primary Care Visits and Self-Reported Adherence at 3 Months: Data From a Randomized Trial.

BACKGROUND: Effective primary care necessitates follow-up actions by the patient beyond the visit. Prior research suggests room for improvement in patient adherence. OBJECTIVE: This study sought to understand patients' views on their primary care visits, the plans generated therein, and their self-reported adherence after 3 months. METHODS: As part of a large multisite cluster randomized pragmatic trial in 3 health care organizations, patients completed 2 surveys-the first within 7 days after the index primary care visit and another 3 months later. For this analysis of secondary outcomes, we combined the results across all study participants to understand patient adherence to care plans. We recorded patient characteristics and survey responses. Cross-tabulation and chi-square statistics were used to examine bivariate associations, adjusting for multiple comparisons when appropriate. We used multivariable logistic regression to assess how patients' intention to follow, agreement, and understanding of their plans impacted their plan adherence, allowing for differences in individual characteristics. Qualitative content analysis was conducted to characterize the patient's self-reported plans and reasons for adhering (or not) to the plan 3 months later. RESULTS: Of 2555 patients, most selected the top box option (9=definitely agree) that they felt they had a clear plan (n=2011, 78%), agreed with the plan (n=2049, 80%), and intended to follow the plan (n=2108, 83%) discussed with their provider at the primary care visit. The most common elements of the plans reported included reference to exercise (n=359, 14.1%), testing (laboratory, imaging, etc; n=328, 12.8%), diet (n=296, 11.6%), and initiation or adjustment of medications; (n=284, 11.1%). Patients who strongly agreed that they had a clear plan, agreed with the plan, and intended to follow the plan were all more likely to report plan completion 3 months later (P<.001) than those providing less positive ratings. Patients who reported plans related to following up with the primary care provider (P=.008) to initiate or adjust medications (P≤.001) and to have a specialist visit were more likely to report that they had completely followed the plan (P=.003). Adjusting for demographic variables, patients who indicated intent to follow their plan were more likely to follow-through 3 months later (P<.001). Patients' reasons for completely following the plan were mainly that the plan was clear (n=1114, 69.5%), consistent with what mattered (n=1060, 66.1%), and they were determined to carry through with the plan (n=887, 53.3%). The most common reasons for not following the plan were lack of time (n=217, 22.8%), having decided to try a different approach (n=105, 11%), and the COVID-19 pandemic impacted the plan (n=105, 11%). CONCLUSIONS: Patients' initial assessment of their plan as clear, their agreement with the plan, and their initial willingness to follow the plan were all strongly related to their self-reported completion of the plan 3 months later. Patients whose plans involved lifestyle changes were less likely to report that they had "completely" followed their plan. TRIAL REGISTRATION: ClinicalTrials.gov NCT03385512; https://clinicaltrials.gov/study/NCT03385512. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.2196/30431.

AI-Generated Draft Replies Integrated Into Health Records and Physicians' Electronic Communication.

Importance: Timely tests are warranted to assess the association between generative artificial intelligence (GenAI) use and physicians' work efforts. Objective: To investigate the association between GenAI-drafted replies for patient messages and physician time spent on answering messages and the length of replies. Design, Setting, and Participants: Randomized waiting list quality improvement (QI) study from June to August 2023 in an academic health system. Primary care physicians were randomized to an immediate activation group and a delayed activation group. Data were analyzed from August to November 2023. Exposure: Access to GenAI-drafted replies for patient messages. Main Outcomes and Measures: Time spent (1) reading messages, (2) replying to messages, (3) length of replies, and (4) physician likelihood to recommend GenAI drafts. The a priori hypothesis was that GenAI drafts would be associated with less physician time spent reading and replying to messages. A mixed-effects model was used. Results: Fifty-two physicians participated in this QI study, with 25 randomized to the immediate activation group and 27 randomized to the delayed activation group. A contemporary control group included 70 physicians. There were 18 female participants (72.0%) in the immediate group and 17 female participants (63.0%) in the delayed group; the median age range was 35-44 years in the immediate group and 45-54 years in the delayed group. The median (IQR) time spent reading messages in the immediate group was 26 (11-69) seconds at baseline, 31 (15-70) seconds 3 weeks after entry to the intervention, and 31 (14-70) seconds 6 weeks after entry. The delayed group's median (IQR) read time was 25 (10-67) seconds at baseline, 29 (11-77) seconds during the 3-week waiting period, and 32 (15-72) seconds 3 weeks after entry to the intervention. The contemporary control group's median (IQR) read times were 21 (9-54), 22 (9-63), and 23 (9-60) seconds in corresponding periods. The estimated association of GenAI was a 21.8% increase in read time (95% CI, 5.2% to 41.0%; P = .008), a -5.9% change in reply time (95% CI, -16.6% to 6.2%; P = .33), and a 17.9% increase in reply length (95% CI, 10.1% to 26.2%; P < .001). Participants recognized GenAI's value and suggested areas for improvement. Conclusions and Relevance: In this QI study, GenAI-drafted replies were associated with significantly increased read time, no change in reply time, significantly increased reply length, and some perceived benefits. Rigorous empirical tests are necessary to further examine GenAI's performance. Future studies should examine patient experience and compare multiple GenAIs, including those with medical training.

Recognition as a patient-centered medical home: fundamental or incidental?

PURPOSE: Little is known about reasons why a medical group would seek recognition as a patient-centered medical home (PCMH). We examined the motivations for seeking recognition in one group and assessed why the group allowed recognition to lapse 3 years later. METHODS: As part of a larger mixed methods case study, we conducted 38 key informant interviews with executives, clinicians, and front-line staff. Interviews were conducted according to a guide that evolved during the project and were audio-recorded and fully transcribed. Transcripts were analyzed and thematically coded. RESULTS: PCMH principles were consistent with the organization's culture and mission, which valued innovation and putting patients first. Motivations for implementing specific PCMH components varied; some components were seen as part of the organization's patient-centered culture, whereas others helped the practice compete in its local market. Informants consistently reported that National Committee for Quality Assurance recognition arose incidentally because of a 1-time incentive from a local group of large employers and because the organization decided to allocate some organizational resources to respond to the complex reporting requirements for about one-half of its clinics. CONCLUSIONS: Becoming patient centered and seeking recognition as such ran along separate but parallel tracks within this organization. As the Affordable Care Act continues to focus attention on primary care redesign, this apparent disconnect should be borne in mind.