Improved Accuracy/Completeness of EHR Race/Ethnicity Data: A Requisite Step to Address Disparities in Care.

Accurate and complete racial/ethnic data in the electronic health record are a requisite step to addressing disparities in neurologic care, and at local, regional, and national levels. The current data pertaining to the patients' race and ethnicity contained in the electronic health record are inadequate. This article outlines recommendations at the individual practice and electronic health record vendor level to improve documentation of race and ethnicity.

Predicting Mortality Prior to Interhospital Hospital for "Unseen" General Surgery Patients: Development, Validation and Feasibility Trial of a Mortality Risk Calculator.

OBJECTIVE: Develop and validate a mortality risk calculator that could be utilized at the time of transfer, leveraging routinely collected variables that could be obtained by trained non-clinical transfer personnel. SUMMARY BACKGROUND DATA: There are no objective tools to predict mortality at the time of inter-hospital transfer for Emergency General Surgery (EGS) patients that are "unseen" by the accepting system. METHODS: Patients transferred to general or colorectal surgery services from January 2016 through August 2022 were retrospectively identified and randomly divided into training and validation cohorts (3:1 ratio). The primary outcome was admission-related mortality, defined as death during the index admission or within 30 days post-discharge. Multiple predictive models were developed and validated. RESULTS: Among 4,664 transferred patients, 280 (6.0%) experienced mortality. Predictive models were generated utilizing 19 routinely collected variables; the penalized regression model was selected over other models due to excellent performance using only 12 variables. The model performance on the validating set resulted in an area under the receiver operating characteristic curve, sensitivity, specificity, and balanced accuracy of 0.851, 0.90, 0.67, and 0.79, respectively. After bias correction, Brier score was 0.04, indicating a strong association between the assigned risk and the observed frequency of mortality. CONCLUSION: A risk calculator using twelve variables has excellent predictive ability for mortality at the time of interhospital transfer among "unseen" EGS patients. Quantifying a patient's mortality risk at the time of transfer could improve patient triage, bed and resource allocation, and standardize care.

Implications of Large Language Models for Quality and Efficiency of Neurologic Care: Emerging Issues in Neurology.

Large language models (LLMs) are advanced artificial intelligence (AI) systems that excel in recognizing and generating human-like language, possibly serving as valuable tools for neurology-related information tasks. Although LLMs have shown remarkable potential in various areas, their performance in the dynamic environment of daily clinical practice remains uncertain. This article outlines multiple limitations and challenges of using LLMs in clinical settings that need to be addressed, including limited clinical reasoning, variable reliability and accuracy, reproducibility bias, self-serving bias, sponsorship bias, and potential for exacerbating health care disparities. These challenges are further compounded by practical business considerations and infrastructure requirements, including associated costs. To overcome these hurdles and harness the potential of LLMs effectively, this article includes considerations for health care organizations, researchers, and neurologists contemplating the use of LLMs in clinical practice. It is essential for health care organizations to cultivate a culture that welcomes AI solutions and aligns them seamlessly with health care operations. Clear objectives and business plans should guide the selection of AI solutions, ensuring they meet organizational needs and budget considerations. Engaging both clinical and nonclinical stakeholders can help secure necessary resources, foster trust, and ensure the long-term sustainability of AI implementations. Testing, validation, training, and ongoing monitoring are pivotal for successful integration. For neurologists, safeguarding patient data privacy is paramount. Seeking guidance from institutional information technology resources for informed, compliant decisions, and remaining vigilant against biases in LLM outputs are essential practices in responsible and unbiased utilization of AI tools. In research, obtaining institutional review board approval is crucial when dealing with patient data, even if deidentified, to ensure ethical use. Compliance with established guidelines like SPIRIT-AI, MI-CLAIM, and CONSORT-AI is necessary to maintain consistency and mitigate biases in AI research. In summary, the integration of LLMs into clinical neurology offers immense promise while presenting formidable challenges. Awareness of these considerations is vital for harnessing the potential of AI in neurologic care effectively and enhancing patient care quality and safety. The article serves as a guide for health care organizations, researchers, and neurologists navigating this transformative landscape.

An overview of clinical machine learning applications in neurology.

Machine learning techniques for clinical applications are evolving, and the potential impact this will have on clinical neurology is important to recognize. By providing a broad overview on this growing paradigm of clinical tools, this article aims to help healthcare professionals in neurology prepare to navigate both the opportunities and challenges brought on through continued advancements in machine learning. This narrative review first elaborates on how machine learning models are organized and implemented. Machine learning tools are then classified by clinical application, with examples of uses within neurology described in more detail. Finally, this article addresses limitations and considerations regarding clinical machine learning applications in neurology.

Improving Neurology Clinical Care With Natural Language Processing Tools.

The integration of natural language processing (NLP) tools into neurology workflows has the potential to significantly enhance clinical care. However, it is important to address the limitations and risks associated with integrating this new technology. Recent advances in transformer-based NLP algorithms (e.g., GPT, BERT) could augment neurology clinical care by summarizing patient health information, suggesting care options, and assisting research involving large datasets. However, these NLP platforms have potential risks including fabricated facts and data security and substantial barriers for implementation. Although these risks and barriers need to be considered, the benefits for providers, patients, and communities are substantial. With these systems achieving greater functionality and the pace of medical need increasing, integrating these tools into clinical care may prove not only beneficial but necessary. Further investigation is needed to design implementation strategies, mitigate risks, and overcome barriers.

Gender Discrepancies in Neurologist Compensation.

BACKGROUND AND OBJECTIVES: Previous studies have shown gender disparities in physician pay in various specialties. This retrospective, cross-sectional study evaluated data from the American Academy of Neurology (AAN) Compensation and Productivity Survey for differences in neurologist compensation by gender. METHODS: Of the 3,268 completed surveys submitted, 2,719 were from neurologists and 1,466 had sufficient data for analysis (551 women, 951 men respondents). We calculated an hourly wage from full-time equivalent (FTE) status and weeks worked per year. We evaluated differences in men and women neurologist compensation with multivariable generalized linear models adjusting for race, ethnicity, geographic region, practice setting, years in practice, call status, leadership role, straight salary, and subspecialty. RESULTS: Baseline characteristics for men and women neurologists were similar with the exception of subspecialty distribution. More men were practicing in higher-wage subspecialties compared to women (p < 0.05). Mean FTE annual salary for all neurologists was $280,315, and mean standardized hourly compensation was $131. Estimated annual salary for women was 10.7% less (p ≤ 0.001, 95% confidence interval -4% to -16%) after controlling for race, region, years of practice, practice setting, call status, leadership role, and subspecialty-wage category. FTE annual salary for women neurologists in high-compensation specialties ($281,838) was lower than the mean annual salary for men neurologists in both high-compensation ($365,751) and low-compensation subspecialties ($282,813). When broken down by years of practice, the highest earning women neurologists' mean hourly wage (11-20 years of practice, $128/h) was less than that of all men neurologists except those with 0 to 5 years of practice ($125/h). DISCUSSION: This study, using convenience sample data, adds to the existing body of evidence demonstrating that, despite adjustment for multiple confounding variables, ongoing disparities exist in physician compensation. Despite efforts by professional societies such as the AAN, ongoing systemic issues and barriers exist. Further research into underlying causes and mitigation strategies is recommended; use of probability sampling methods in future research will be important to decrease potential bias and to increase generalizability.

Late occurrence of progressive multifocal leukoencephalopathy after anti-CD19 chimeric antigen receptor T-cell therapy.

Progressive multifocal leukoencephalopathy (PML) is a life-threatening infection of the central nervous system in immunocompromised patients, with an established predilection in non-Hodgkin's lymphoma and stem cell transplant recipients. In the era of chimeric antigen receptor T-cell therapy (CAR T-cell), the occurrence of new-onset neurological symptoms and encephalopathy in this patient population can be attributed to a variety of factors, including therapy-related neurotoxicity or disease progression. PML has not been implicated as a common cause of encephalopathy in CAR T-cell therapy recipients, and the identification of such rare infections is important to guide prognosis and treatment decisions. We hereby report the first case of late occurrence of PML, over one year after CAR T-cell therapy, for a patient with relapsed large B-cell lymphoma.

Operationalizing COVID-19 testing: Who, what, when, where, why, and how.

The authors review the rationale behind and approaches to testing for COVID-19, the quality of currently available tests, the role of data analytics in strategizing testing, and using the electronic medical record and other programs designed to steward COVID-19 testing and follow-up of patients.

Neurology steering board effects change for a major electronic health record vendor.

Neurologists are among the least satisfied physicians with their current electronic health record (EHR), with many known pain points and great opportunities for improved tools and workflows. Improved EHR functionality can have major implications for patient care, physician efficiency, and prevention of burnout. We describe the advocacy of the American Academy of Neurology for improved EHR usability and the resultant formation and subsequent accomplishments of a Neurology Subspecialty Steering Board at 1 major EHR vendor (Epic).

American Academy of Neurology members' preparedness to treat sexual and gender minorities.

OBJECTIVE: To measure the attitudes and knowledge of American Academy of Neurology (AAN) member neurologists in caring for sexual and gender minority (SGM) patients (e.g., those who identify in the lesbian, gay, bisexual, transgender, queer, or questioning [LGBTQ+] spectrum) to inform future educational offerings. METHODS: A questionnaire was created in an iterative process by the LGBTQ+ Survey Task Force, consisting of 21 questions examining self-reported knowledge, attitudes, and clinical preparedness in caring for SGM patients. Participants responded to each statement with a 5-point Likert scale ("strongly disagree" to "strongly agree"). The survey was distributed via electronic and conventional mail to a random, representative sample of 1,000 AAN members. RESULTS: The response rate was 13.5% (n = 135). Most respondents (60%-66%) were aware of local and national barriers that inhibit SGM individuals from using health care services; the majority (73%-91%) felt comfortable assessing SGM patients. Over half believed sexual orientation (SO) and gender identity (GI) to be social determinants of health (61% and 57%, respectively). Yet a third would not tailor neurologic care based on a patient's SGM identity, and 43% believed that SO/GI has no bearing on the management of neurologic illness. CONCLUSIONS: Most neurologists surveyed were aware of overarching barriers to care experienced by SGM individuals; however, a minority of respondents recognized the intersection of SGM identity with neurologic health. Our results highlight awareness gaps that could be addressed via targeted educational opportunities, ensuring that neurologists provide high-quality neurologic care to patients of all sexual orientations and gender identities.

Operational Aspects of a Clinical Decision Support Program.

Clinical decision support tools that involve improving test utilization should be jointly overseen by a laboratory stewardship committee and the hospital informatics team. The roles of these groups vary by institution and may overlap. This is a team effort and collaboration is a must. The effectiveness of these efforts in an institution depends on the receptiveness of leadership and providers, as well as the effectiveness of the associated committees. Examples of the challenges and successes of laboratory stewardship interventions that have been operationalized at the Cleveland Clinic that use clinical decision support tools, as well as associated literature, are reviewed.

Computerized prescriber order entry and opiate prescription in ambulatory care visits.

OBJECTIVES: To assess the impact of computerized prescriber order entry (CPOE) on opioid-prescribing practices. METHODS: This study analyzed 233,390 office-based medical visits in the 2011-2015 National Ambulatory Medical Care Survey. We used survey-adjusted logistic regression analysis comparing prescription of opiate medications by physicians with and without CPOE. Results were adjusted by covariates describing patient demographics, insurance status, and geography; clinical factors including noncancer pain, cancer, and other chronic medical problems; and physician specialty category and solo practitioner status. RESULTS: Opiates were prescribed in 10.4% of patient visits to physicians with access to CPOE in the sample, compared with 7.5% of visits to physicians without access to CPOE. The adjusted odds of opiate prescription were 1.35 times greater in visits to physicians who had access to CPOE (P = 0.001; 95% CI 1.14-1.58). Among patients visits citing pain (n = 52,978), the adjusted odds of opioid prescription were significantly greater when physicians had access to CPOE (odds ratio 1.28, 95% CI 1.02-1.61; P = 0.035). CONCLUSION: These findings support efforts to review and redesign embedded CPOE tools to improve guideline adherence and reduce problematic opiate prescription.

Telemedicine vs Office Visits in a Movement Disorders Clinic: Comparative Satisfaction of Physicians and Patients.

OBJECTIVE: To compare patient and physician satisfaction between home-based telemedicine visits and office visits for follow-up care within a movement disorders program. METHODS: Patients were offered telemedicine visits as follow-up care. After telemedicine visits, a questionnaire of items along a 10-point Likert Scale (10 = most satisfied) assessed patient and overall physician satisfaction, comparing the experience to past in-office visits. RESULTS: Patients and physicians were highly satisfied with the telemedicine experience, both groups having median endorsement scores of 9.25 and 10.0, respectively (response range 6-10), and furthermore, favoring future telemedicine visits when feasible. Although some assessments could not be performed (postural stability, rigidity), physicians likewise favored having future telemedicine visits (median score 10, range 5.0-10). CONCLUSIONS: This direct comparison of patient satisfaction with telemedicine visits to previously experienced office visits strongly supports telemedicine care, with patients highlighting convenience, time, and expense. Despite some limitations with telemedicine, physicians expressed highly rated quality-of-service provided.

Sharing notes with patients: A review of current practice and considerations for neurologists.

Improved patient engagement is a critical consideration in the new payment climate. Releasing progress notes for patients to view may improve patient involvement and engagement in their care. Patients perceive benefit from viewing physician progress notes. As initial studies involved only primary care physicians, specialist physicians may have specific considerations when releasing notes to patients. This article provides a framework for neurologists to implement a note release policy in their practice.

Use of the Electronic Health Record for Coding in Outpatient Neurology.

Diagnostic coding now factors into reimbursement, quality assessments, reputational metrics, and epidemiologic analysis; therefore, it is more critical than ever that neurologists are accurate and precise in their coding. In addition to being the means though which most neurologists are capturing this information, the electronic health record can offer multiple tools to assist in these efforts. With conscientious design, build, and implementation of the electronic health record, diagnostic coding can be effortless, even for the most complex and varied of conditions seen in an outpatient neurology visit.