Can the Administrative Loads of Physicians be Alleviated by AI-Facilitated Clinical Documentation?

BACKGROUND: Champions of AI-facilitated clinical documentation have suggested that the emergent technology may decrease the administrative loads of physicians, thereby reducing cognitive burden and forestalling burnout. Explorations of physicians' experiences with automated documentation are critical in evaluating these claims. OBJECTIVE: To evaluate physicians' experiences with DAX Copilot (DAXC), a generative AI-facilitated clinical documentation tool. DESIGN: Semi-structured interviews were conducted in August and September of 2023 with physician-users of DAXC. PARTICIPANTS: A purposive sample of 12 interviewees, selected from 116 primary care physicians, employed at a multi-site academic learning health system. APPROACH: After completing all 12 interviews, three study personnel independently analyzed and coded the transcripts. Reconciliation sessions were then held to merge the three analyses into one summary, eliminating redundant codes, and grouping findings into themes. KEY RESULTS: For a majority of interviewees, DAXC reduced the amount of time spent documenting encounters, and alleviated anxieties of having to retain important clinical details until there was time to make notes. DAXC also allowed physicians to be more engaged during appointments, resulting in more personable provider-patient encounters. However, some physicians weighed these benefits against an uneasy feeling that interviewees might be asked to see more patients if DAXC was mandated. Physicians also noted that the tool would occasionally imagine or misgender patients, offer unsolicited and inappropriate diagnoses, and mistake critical details in transcription. The few physicians less enthusiastic about the generative technology portrayed themselves as creatures of habit who had cultivated long-standing workflows and particular notation practices that DAXC could neither improve upon nor reproduce. CONCLUSIONS: According to physician interviewees, automated AI-driven clinical documentation has the potential to significantly reduce the administrative burden associated with particular types of provider-patient encounters. Addressing the growing pains of the incipient technology, identified here, may allow for a broader applicability for clinical practice.

Evaluating Racial/Ethnic Differences in Care Escalation Among COVID-19 Patients in a Home-Based Hospital.

The novel coronavirus disease 2019 (COVID-19) has infected over 414 million people worldwide with 5.8 million deaths, as of February 2022. Telemedicine-based interventions to expand healthcare systems' capacity and reduce infection risk have rapidly increased during the pandemic, despite concerns regarding equitable access. Atrium Health Hospital at Home (AH-HaH) is a home-based program that provides advanced, hospital-level medical care and monitoring for patients who would otherwise be hospitalized in a traditional setting. Our retrospective cohort study of positive COVID-19 patients who were admitted to AH-HaH aims to investigate whether the rate of care escalation from AH-HaH to traditional hospitalization differed based on patients' racial/ethnic backgrounds. Logistic regression was used to examine the association between care escalation within 14 days from index AH-HaH admission and race/ethnicity. We found approximately one in five patients receiving care for COVID-19 in AH-HaH required care escalation within 14 days. Odds of care escalation were not significantly different for Hispanic or non-Hispanic Blacks compared to non-Hispanic Whites. However, secondary analyses showed that both Hispanic and non-Hispanic Black patients were younger and with fewer comorbidities than non-Hispanic Whites. The study highlights the need for new care models to vigilantly monitor for disparities, so that timely and tailored adaptations can be implemented for vulnerable populations.

Adrenal Crisis Mimicking COVID-19 Encephalopathy in a Teenager with Craniopharyngioma.

There is an increasing number of reported cases with neurological manifestations of COVID-19 in children. Symptoms include headache, general malaise, ageusia, seizure and alterations in consciousness. The differential diagnosis includes several potentially lethal conditions including encephalopathy, encephalitis, intracranial hemorrhage, thrombosis and adrenal crisis. We report the case of a 17-year-old boy with a positive antigen test of COVID-19 who presented with fever for one day, altered mental status and seizure, subsequently diagnosed with adrenal insufficiency. He had a history of panhypopituitarism secondary to a suprasellar craniopharyngioma treated with surgical resection; he was treated with regular hormone replacement therapy. After prompt administration of intravenous hydrocortisone, his mental status returned to normal within four hours. He recovered without neurologic complications. Adrenal insufficiency can present with neurological manifestations mimicking COVID-19 encephalopathy. Prompt recognition and treatment of adrenal insufficiency, especially in patients with brain tumors, Addison's disease or those recently treated with corticosteroids, can rapidly improve the clinical condition and prevent long-term consequences.

The Association Between Metabolic Syndrome and Non-Alcoholic Fatty Liver Disease Diagnosis Varies by Race.

Objectives: This study investigated how the association between metabolic syndrome (MetS) and nonalcoholic fatty liver disease (NAFLD) diagnosis varies between non-Hispanic African American and white patients. Methods: A retrospective cohort study was performed using electronic medical records from an integrated health care system (2010-2018). Adults with records for all MetS measurements (body mass index, lipids, blood pressure, and blood glucose) in 2011, who did not have a NAFLD diagnosis before their last MetS measurement, were included. Results: The study cohort consisted of 139,336 patients (age 56.1 ± 15.2 years, 57.9% female, 79.4% non-Hispanic white). The rate of NAFLD diagnosis was higher in MetS patients compared with non-MetS patients [adjusted hazards ratio (AHR) = 1.99, 95% CI = 1.91-2.09] with a significant interaction by race (AHR = 2.05, 95% CI = 1.95-2.15 in non-Hispanic whites vs. AHR = 1.76, 95% CI = 1.58-1.96 non-Hispanic African Americans, P = 0.017). Secondary analyses revealed that the relative NAFLD diagnosis rate was higher in non-Hispanic whites with MetS compared with non-Hispanic African Americans with MetS among females and patients 18-39 years of age and 40-59 years, but not among males and those ≥60 years of age. Conclusions: Non-Hispanic white patients with MetS, particularly females and those <60 years of age, may be at increased risk of NAFLD compared with non-Hispanic African American MetS patients and may benefit from extra attention regarding NAFLD screening.

Variations in Receipt of Contraceptives by Insurance Status and Race/Ethnicity.

BACKGROUND Although use of contraceptives has increased among young women in the United States, more than half of pregnancies remain unplanned. The goal of this study was to examine the association between insurance status and receipt of contraceptives among young women receiving care within a large integrated health care system in the Southeastern United States to better inform strategies for increasing access to contraception.METHODS This retrospective study used electronic medical record data from an integrated health care system based in Charlotte, North Carolina. Data were analyzed for 51,900 women aged 18-29 who lived in Mecklenburg County and had at least 1 primary care visit between 2014 and 2016. Contraceptive orders were identified by service and procedure codes and grouped into long-acting reversible contraceptives (LARC) and non-LARC categories. Adjusted multinomial logistic regression models were used to assess the association between receipt of contraceptives and insurance status.RESULTS Compared to non-Hispanic White women with commercial insurance, non-Hispanic Black (OR = 1.25; 95% CI, 1.13-1.38) and Hispanic (OR = 2.25; 95% CI, 1.93-2.61) women with Medicaid had higher odds of receiving LARC. Similar variations by insurance and race/ethnicity were observed for the non-LARC group.LIMITATIONS Data were limited to a single health care system and did not capture contraceptive orders by unaffiliated providers. Analyses used the most frequent payor and did not account for changes in insurance status.CONCLUSION Findings indicate an important role of race/ethnicity and insurance coverage in contraceptive care. Higher receipt of LARC among Black and Hispanic women also suggests that implicit biases may influence contraception counseling and promotion practices. Future study is warranted to further delineate these relationships.

Original Research: Well-Being and Resilience Among Health Care Workers During the COVID-19 Pandemic: A Cross-Sectional Study.

BACKGROUND: Poor well-being among health care workers, often observed as professional burnout, is a well-documented phenomenon. The coronavirus disease 2019 (COVID-19) pandemic has further stressed the health care workforce, but its specific effects on this workforce remain unknown. This study examined well-being and resilience among health care workers during the COVID-19 pandemic. METHODS: The study used a cross-sectional survey design. Data collection took place through anonymous surveys of nurses (LPNs and RNs), advanced practice providers (NPs, physician assistants, and certified nurse midwives), certified registered nurse anesthetists, respiratory therapists, health care technicians, and therapy service professionals (physical, occupational, and speech therapists). Of the 6,120 health care workers recruited to participate in the study, data from 2,459 participants were analyzed using logistic regression and linear regression. RESULTS: The study found that several factors significantly increased the likelihood of at-risk well-being. These included having a lower level of resilience, using support resources, feeling the organization lacked understanding of the emotional support needs of health care workers during the pandemic, believing the workload had increased, believing there was insufficient personal protective equipment, believing there was inadequate staffing to safely care for patients, and having a lower degree of psychological safety. After controlling for health care workers' role and employment location, several factors were found to be significantly associated with higher levels of resilience. These included having positive perceptions about the organization's understanding of the emotional support needs of health care workers during the pandemic, believing sufficient educational resources were available regarding the care of COVID-19 patients, having positive perceptions of leadership support from direct managers, having positive perceptions of the redeployment policy, and having a higher degree of psychological safety. CONCLUSIONS: This study identified several work environment factors that have significantly affected health care workers' well-being and resilience during the COVID-19 pandemic. This knowledge has practical relevance for health care leaders who aim to better understand and address the well-being and resilience of the health care workforce during this pandemic and beyond.

Patient and Caregiver Outcomes and Experiences With Team-Based Memory Care: A Mixed Methods Study.

Patients with dementia and their caregivers need ongoing educational and psychosocial support to manage their complex diagnosis. This mixed methods study evaluated the impact of a memory clinic with an embedded dementia navigator on the experiences and health outcomes of patients with dementia and their caregivers. At the 12-month follow-up, patients receiving memory clinic services (n = 238) had higher emergency department visits than a matched cohort with dementia (n = 938), although hospitalizations did not differ. Patient quality of life and caregiver burden scores also did not differ between baseline and 12-months. Interviews revealed that caregivers (n = 12) valued the educational and social support components of the memory clinic and perceived that the clinic had a positive impact on their experiences. Findings suggest that this embedded navigator model is useful for addressing caregiver needs and may have potential to stem increases in caregiver burden and patient quality of life that occur with disease progression.

Insurance Differences in Preventive Care Use and Adverse Birth Outcomes Among Pregnant Women in a Medicaid Nonexpansion State: A Retrospective Cohort Study.

Background: Lack of quality preventive care has been associated with poorer outcomes for pregnant women with low incomes. Health policy changes implemented with the Affordable Care Act (ACA) were designed to improve access to care. However, insurance coverage remains lower among women in Medicaid nonexpansion states. We compared health care use and adverse birth outcomes by insurance status among women giving birth in a large health system in a Medicaid nonexpansion state. Materials and Methods: We conducted a population-based retrospective cohort study using data for 9,613 women with deliveries during 2014-2015 at six hospitals associated with a large vertically integrated health care system in North Carolina. Adjusted logistic regression and zero-inflated negative binomial models examined associations between insurance status at delivery (commercial, Medicaid, or uninsured) and health care utilization (well-woman visits, late prenatal care, adequacy of prenatal care, postpartum follow-up, and emergency department [ED] visits) and outcomes (preterm birth, low birth weight, preeclampsia, and gestational diabetes). Results: Having Medicaid at delivery was associated with lower rates of well-woman visits (rate ratio [RR] 0.25, 95% CI 0.23-0.28), higher rates of ED visits (RR 2.93, 95% CI 2.64-3.25), and higher odds of late prenatal care (odds ratio [OR] 1.18, 95% CI 1.03-1.34) compared to having commercial insurance, with similar results for uninsured women. Differences in adverse pregnancy outcomes were not statistically significant after adjusting for patient characteristics. Conclusions: Findings suggest that large gaps exist in use of preventive care between Medicaid/uninsured and commercially insured women. Policymakers should consider ways to improve potential and realized access to care.

Comparative Effectiveness of Metformin Dosage Uptitration Versus Adding Another Antihyperglycemic Medication on Glycemic Control in Type 2 Diabetes Patients Failing Initial Metformin Monotherapy: A Retrospective Cohort Study.

Metformin is recommended as first-line treatment for type 2 diabetes (T2D). A disadvantage of metformin is the possibility of gastrointestinal adverse effects in some patients. Many T2D patients are not able to achieve/maintain glycemic control from initial metformin treatment and receive treatment intensification by means of metformin dosage uptitration or addition of a T2D drug. This retrospective study evaluated the comparative effectiveness of these 2 treatment intensification strategies. The study cohort included T2D patients at a US integrated health care system who: were initiated on metformin monotherapy (MM) during January 2009 - September 2013; had an uncontrolled HbA1c (≥7%) after at least 90 days of MM; and received metformin dosage uptitration or an additional T2D medication within 6 months of the uncontrolled HbA1c reading. Statistical techniques included Kaplan-Meier curves and Cox proportional hazards regression. The study cohort included 1167 patients, 52.4% male and 65.1% white, with a mean age of 55.3 (±11.9) years. Of these, 49.1% received metformin dosage uptitration and 50.9% received an additional T2D medication. Metformin dosage uptitration was as effective as adding another T2D medication with the probability of not achieving glycemic control (P = 0.599) and rate of glycemic control (adjusted hazard ratio = 1.28, 95% confidence interval = 0.98-1.68) within 6 months of intensification not significantly different between the 2 groups. Metformin dosage uptitration could be a preferable initial intensification strategy in patients failing initial MM unless there is a concern for gastrointestinal adverse effects, in which case adding a T2D medication might be preferable.

Correction: Who Treats Patients with Diabetes and Compensated Cirrhosis.

[This corrects the article DOI: 10.1371/journal.pone.0165574.].

Shared decision making and time to exacerbation in children with asthma.

Objective: Although shared decision making (SDM) is a promising approach for improving outcomes for patients with chronic diseases, no evidence currently supports the use of SDM to delay asthma exacerbations. We evaluated the impact of an SDM intervention implemented by providers in a real-world setting on time to exacerbation in children with asthma. Methods: This study used a prospective cohort observed between 2011 and 2013 at five primary care practices that serve vulnerable populations (e.g., Medicaid and uninsured patients) in Charlotte, NC. Patients aged 2 to 17 receiving SDM were matched to those receiving usual care using propensity scores. Time to asthma exacerbation (asthma hospitalization, emergency department visit or oral steroid prescription in the outpatient setting) was compared between groups using Kaplan-Meier curves and conditional Cox proportional hazards models. Results: The cohort included 746 children, 60.5% male and 54.2% African American, with a mean age of 8.6 years. Of these, 625 received usual care and 121 received SDM. The final analysis included 100 matched pairs of children. Kaplan-Meier curves showed longer exacerbation-free time for patients in the SDM intervention compared to those in usual care (p = 0.005). The difference in risk of experiencing an exacerbation was marginally significant between the two groups (HR = 0.56, 95% C.I. = 0.29-1.08, p = 0.08). Conclusions: SDM was found to delay exacerbations among children with asthma. Clinicians should consider incorporating patient preferences in treatment decisions through SDM as a means for longer exacerbation-free time among children with poor asthma control.

Impact of shared decision making on asthma quality of life and asthma control among children.

OBJECTIVE: Few studies have examined the effectiveness of shared decision making (SDM) in clinical practice. This study evaluated the impact of SDM on quality of life and symptom control in children with asthma. METHODS: We conducted a prospective 3-year study in six community-based practices serving a low-income patient population. Practices received training on SDM using an evidence-based toolkit. Patients aged 2-17 with a diagnosis of asthma were identified from scheduling and billing data. At approximate 6-month intervals, patients completed a survey consisting of the Mini Pediatric Asthma Quality of Life Questionnaire (range 1-7) and the control domain of the Pediatric Asthma Therapy Assessment Questionnaire (range 0-7). We used propensity scores to match 46 children receiving SDM to 46 children receiving usual care with decision support. Included children had completed a baseline survey and at least one follow-up survey. Random coefficient models incorporated repeated measures to assess the effect of SDM on asthma quality of life and asthma control. RESULTS: The sample was primarily of non-White patients (94.6%) with Medicaid insurance (92.4%). Receipt of SDM using an evidence-based toolkit was associated with higher asthma quality of life [mean difference 0.9; 95% confidence interval (CI) 0.4-1.4] and fewer asthma control problems (mean difference -0.9; 95% CI -1.6--0.2) compared to usual care with decision support. CONCLUSIONS: Implementation of SDM within clinical practices using a standardized toolkit is associated with improved asthma quality of life and asthma control for low-income children with asthma when compared to usual care with decision support.

Exploring Patient Awareness and Perceptions of the Appropriate Use of Antibiotics: A Mixed-Methods Study.

In the outpatient setting, estimates suggest that 30% of the antibiotics prescribed are unnecessary. This study explores patient knowledge and awareness of appropriate use of antibiotics and expectations regarding how antibiotics are used for their treatment in outpatient settings. A survey was administered to a convenience sample of patients, parents, and caregivers (n = 190) at seven primary care clinics and two urgent care locations. Fisher's exact tests compared results by patient characteristics. Although 89% of patients correctly believed that antibiotics work well for treating infections from bacteria, 53% incorrectly believed that antibiotics work well for treating viral infections. Patients who incorrectly believed that antibiotics work well for treating viral infections were more than twice as likely to expect a provider to give them an antibiotic when they have a cough or common cold. Patients who completed the survey also participated in semi-structured interviews (n = 4), which were analyzed using thematic analysis. Patients reported experiencing confusion about which illnesses may be treated by antibiotics and unclear communication from clinicians about the appropriate use of antibiotics. Development of easy to understand patient educational materials can help address patients' incorrect perceptions of appropriate antibiotic use and facilitate patient-provider communication.