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.

Screening for Quality of Life in a Neurology Tic Clinic Using Quality Improvement Methodology.

BACKGROUND: Tic disorders in children often co-occur with other disorders that can significantly impact functioning. Screening for quality of life (QoL) can help identify optimal treatment paths. This quality improvement (QI) study describes implementation of a QoL measure in a busy neurology clinic to help guide psychological intervention for patients with tics. METHODS: Using QI methodology outlined by the Institute for Healthcare Improvement, this study implemented the PedsQL Generic Core (4.0) in an outpatient medical clinic specializing in the diagnosis and treatment of tic disorders. Assembling a research team to design process maps and key driver diagrams helped identify gaps in the screening process. Conducting several plan-do-study-act cycles refined identification of patients appropriate to receive the measure. Over the three-year study, electronic health record notification tools and data collection were increasingly utilized to capture patients' information during their visit. RESULTS: Over 350 unique patients were screened during the assessment period. Electronic means replaced paper measures as time progressed. The percentage of patients completing the measure increased from 0% to 51.9% after the initial implementation of process improvement, advancing to 91.6% after the introduction of electronic measures. This average completion rate was sustained for 15 months. CONCLUSIONS: Using QI methodology helped identify the pragmatics of implementing a QoL assessment to enhance screening practices in a busy medical clinic. Assessment review at the time of appointment helped inform treatment and referral decisions.

European Academy of Neurology (EAN) guideline on the management of amyotrophic lateral sclerosis in collaboration with European Reference Network for Neuromuscular Diseases (ERN EURO-NMD).

BACKGROUND: This update of the guideline on the management of amyotrophic lateral sclerosis (ALS) was commissioned by the European Academy of Neurology (EAN) and prepared in collaboration with the European Reference Network for Neuromuscular Diseases (ERN EURO-NMD) and the support of the European Network for the Cure ALS (ENCALS) and the European Organization for Professionals and Patients with ALS (EUpALS). METHODS: Grading of Recommendations Assessment, Development, and Evaluation (GRADE) methodology was used to assess the effectiveness of interventions for ALS. Two systematic reviewers from Cochrane Response supported the guideline panel. The working group identified a total of 26 research questions, performed systematic reviews, assessed the quality of the available evidence, and made specific recommendations. Expert consensus statements were provided where insufficient evidence was available. RESULTS: A guideline mapping effort revealed only one other ALS guideline that used GRADE methodology (a National Institute for Health and Care Excellence [NICE] guideline). The available evidence was scarce for many research questions. Of the 26 research questions evaluated, the NICE recommendations could be adapted for 8 questions. Other recommendations required updates of existing systematic reviews or de novo reviews. Recommendations were made on currently available disease-modifying treatments, multidisciplinary care, nutritional and respiratory support, communication aids, psychological support, treatments for common ALS symptoms (e.g., muscle cramps, spasticity, pseudobulbar affect, thick mucus, sialorrhea, pain), and end-of-life management. CONCLUSIONS: This update of the guideline using GRADE methodology provides a framework for the management of ALS. The treatment landscape is changing rapidly, and further updates will be prepared when additional evidence becomes available.

Guidelines for Qualifications of Neurodiagnostic Personnel: A Joint Position Statement of the American Clinical Neurophysiology Society, the American Association of Neuromuscular & Electrodiagnostic Medicine, the American Society of Neurophysiological Monitoring, and ASET-The Neurodiagnostic Society.

SUMMARY: The Guidelines for Qualifications of Neurodiagnostic Personnel (QNP) document has been created through the collaboration of the American Clinical Neurophysiology Society (ACNS), the American Society of Neurophysiological Monitoring (ASNM), the American Association of Neuromuscular & Electrodiagnostic Medicine (AANEM), and ASET-The Neurodiagnostic Society (ASET). The quality of patient care is optimized when neurophysiological procedures are performed and interpreted by appropriately trained and qualified practitioners at every level. These societies recognize that neurodiagnostics is a large field with practitioners who have entered the field through a variety of training paths. This document suggests job titles, associated job responsibilities, and the recommended levels of education, certification, experience, and ongoing education appropriate for each job. This is important because of the growth and development of standardized training programs, board certifications, and continuing education in recent years. This document matches training, education, and credentials to the various tasks required for performing and interpreting neurodiagnostic procedures. This document does not intend to restrict the practice of those already working in neurodiagnostics. It represents recommendations of these societies with the understanding that federal, state, and local regulations, as well as individual hospital bylaws, supersede these recommendations. Because neurodiagnostics is a growing and dynamic field, the authors fully intend this document to change over time.

Patient perspectives in pediatric neurology: a critical shift in the paradigm of outcome measurement.

This review explores children's self-reported outcome measurements in pediatric neurology. We examine the following questions: (1) What is meant by patient-reported health, functioning, and quality of life outcomes? (2) How can patients express whether the interventions they receive do more good than harm? (3) Why and how should pediatric neurology patients help determine the outcomes of interest? (4) What tools and recommendations are available to evaluate the outcomes of interest? Applying patients' perspectives across the processes of evaluation of medical interventions has become an important expectation. These developments, consistent with current healthcare goals, coincide with the evolution of pediatric neurology into a sophisticated diagnostic-interventional field that aims to prolong survival, decrease impairments and symptoms, and improve patients' well-being - the recognized essential endpoints of interest in all medicine.

Improving Patient Outreach by Defining Telehealth Suitability in a Tertiary Huntington's Disease Clinic.

BACKGROUND: The COVID-19 pandemic has increased the need for remote healthcare options among patients with Huntington's disease (HD). However, since not every HD patient is suitable for telehealth, it is important to differentiate who can be seen virtually from who should remain as in-person. Unfortunately, there are no clinical guidelines on how to evaluate HD patients for telehealth eligibility. OBJECTIVE: To standardize the teleneurology selection process in HD by implementing a screening tool that accounts for patient-specific factors. METHODS: We organized various indications and contraindications to teleneurology into a flowchart. If any indications or contraindications were met, patients were assigned to telehealth or maintained as in-person, respectively. If no indications or contraindications were met, patients were given the option of telehealth or in-person for their upcoming appointments. In two implementation cycles, we tested this screening tool among all HD patients scheduled for clinic visits, aided by chart review and phone interview. RESULTS: In a cohort of 81 patients, telehealth acceptance among eligible patients increased from 45.0%to 83.3%. Frequency of telehealth visits increased from a pre-intervention baseline of 12.8%to 28.2%. CONCLUSION: Teleneurology utilization among HD patients more than doubled across our study. Our intervention promotes consistency and patient-centeredness in HD clinical care and streamlines the overall telehealth selection process. Future studies can seek to reduce telehealth no-shows and also evaluate the utility of the motor and psychiatric criteria included in our screening tool.

Classifying migraine subtypes and their characteristics by latent class analysis using data of a nation-wide population-based study.

Migraine neither presents with a definitive single symptom nor has a distinct biomarker; thus, its diagnosis is based on combinations of typical symptoms. We aimed to identify natural subgroups of migraine based on symptoms listed in the diagnostic criteria of the third edition of the International Classification of Headache Disorders. Latent class analysis (LCA) was applied to the data of the Korean Sleep-Headache Study, a nationwide population-based survey. We selected a three-class model based on Akaike and Bayesian information criteria and characterized the three identified classes as "mild and low frequency," "photophobia and phonophobia," and "severe and high frequency." In total, 52.0% (65/125) of the participants were classified as "mild and low frequency," showing the highest frequency of mild headache intensity but the lowest overall headache frequency. Meanwhile, "photophobia and phonophobia" involved 33.6% (42/125) of the participants, who showed the highest frequency of photophobia and phonophobia. Finally, "severe and high frequency" included 14.4% (18/125) of the participants, and they presented the highest frequency of severe headache intensity and highest headache frequency. In conclusion, LCA is useful for analyzing the heterogeneity of migraine symptoms and identifying migraine subtypes. This approach may improve our understanding of the clinical characterization of migraine.

Clinical potential of pupillary light reflex parameters as objective indicators reflecting chronic rhinosinusitis-specific quality of life: a 12-month prospective longitudinal study.

Pupillary light reflex (PLR) and heart rate variability (HRV) parameters can be objective indicators of chronic rhinosinusitis (CRS) status from the viewpoint of autonomic nervous system activity. This study aimed to establish objective indicators for CRS using the 22-item Sino-Nasal Outcome Test (SNOT-22) and PLR/HRV parameters. Sixty-seven patients were prospectively and longitudinally followed up after surgical treatment. We investigated changes in SNOT-22 scores, representing CRS-specific quality of life (QOL). We prepared two models: linear regression model adjusting clinical factors as predictor variables (model 1) and linear mixed-effects model adjusting clinical factors and among-individual variability (model 2). We compared Akaike's information criterion (AIC) values and regression coefficients. The model with lower AIC values was defined as the better-fit model. Model 2 showed lower AIC values in all parameters (better-fit model). Three parameters showed opposite results between the two models. The better-fit models showed significances in the five PLR parameters but not in any HRV parameters. Among these PLR parameters, constriction latency can be the most robust indicator because of the narrowest 95% confidence intervals. Adjusting the among-individual variability while investigating clinical potential of PLR/HRV parameters to reflect CRS-specific QOL can improve the model fit, thereby reaching robust conclusions from obtained data.

Gene-Targeted Therapies in Pediatric Neurology: Challenges and Opportunities in Diagnosis and Delivery.

BACKGROUND: Gene-targeted therapies are becoming a reality for infants and children with diseases of the nervous system. Rapid scientific advances have led to disease-modifying or even curative treatments. However, delays and gaps in diagnosis, inequitable delivery, and the need for long-term surveillance pose unresolved challenges. OBJECTIVE AND METHODS: The goal of the Child Neurology Society Research Committee was to evaluate and provide guidance on the obstacles, opportunities, and uncertainties in gene-targeted therapies for pediatric neurological disease. The Child Neurology Society Research Committee engaged in collaborative, iterative literature review and committee deliberations to prepare this consensus statement. RESULTS: We identified important challenges for gene-targeted therapies that require resource investments, infrastructure development, and strategic planning. Barriers include inequities in diagnosis and delivery of therapies, high costs, and a need for long-term surveillance of efficacy and safety, including systematic tracking of unanticipated effects. Key uncertainties regarding technical aspects and usage of gene-targeted therapies should be addressed, and characterization of new natural histories of diseases will be needed. Counterbalanced with these obstacles and uncertainties is the tremendous potential being demonstrated in treatments and clinical trials of gene-targeted therapies. CONCLUSIONS: Given that gene-targeted therapies for neurological diseases are in their earliest phase, the pediatric neurology community can play a vital role in their guidance and implementation. This role includes facilitating development of infrastructure and guidelines; ensuring efficient, equitable, and ethical implementation of treatments; and advocating for affordable and broad access for all children.

Comparison of Whole-Head Functional Near-Infrared Spectroscopy With Functional Magnetic Resonance Imaging and Potential Application in Pediatric Neurology.

BACKGROUND: Changes in cerebral blood flow in response to neuronal activation can be measured by time-dependent fluctuations in hemoglobin species within the brain; this is the basis of functional magnetic resonance imaging (fMRI) and functional near-infrared spectroscopy (fNIRS). There is a clinical need for portable neural imaging systems, such as fNIRS, to accommodate patients who are unable to tolerate an MR environment. OBJECTIVE: Our objective was to compare task-related full-head fNIRS and fMRI signals across cortical regions. METHODS: Eighteen healthy adults completed a same-day fNIRS-fMRI study, in which they performed right- and left-hand finger tapping tasks and a semantic-decision tones-decision task. First- and second-level general linear models were applied to both datasets. RESULTS: The finger tapping task showed that significant fNIRS channel activity over the contralateral primary motor cortex corresponded to surface fMRI activity. Similarly, significant fNIRS channel activity over the bilateral temporal lobe corresponded to the same primary auditory regions as surface fMRI during the semantic-decision tones-decision task. Additional channels were significant for this task that did not correspond to surface fMRI activity. CONCLUSION: Although both imaging modalities showed left-lateralized activation for language processing, the current fNIRS analysis did not show concordant or expected localization at the level necessary for clinical use in individual pediatric epileptic patients. Future work is needed to show whether fNIRS and fMRI are comparable at the source level so that fNIRS can be used in a clinical setting on individual patients. If comparable, such an imaging approach could be applied to children with neurological disorders.

Consensus Statement for the Management and Treatment of Sturge-Weber Syndrome: Neurology, Neuroimaging, and Ophthalmology Recommendations.

BACKGROUND: Sturge-Weber syndrome (SWS) is a sporadic, neurocutaneous syndrome involving the skin, brain, and eyes. Because of the variability of the clinical manifestations and the lack of prospective studies, consensus recommendations for management and treatment of SWS have not been published. OBJECTIVE: This article consolidates the current literature with expert opinion to make recommendations to guide the neuroimaging evaluation and the management of the neurological and ophthalmologic features of SWS. METHODS: Thirteen national peer-recognized experts in neurology, radiology, and ophthalmology with experience treating patients with SWS were assembled. Key topics and questions were formulated for each group and included (1) risk stratification, (2) indications for referral, and (3) optimum treatment strategies. An extensive PubMed search was performed of English language articles published in 2008 to 2018, as well as recent studies identified by the expert panel. The panel made clinical practice recommendations. CONCLUSIONS: Children with a high-risk facial port-wine birthmark (PWB) should be referred to a pediatric neurologist and a pediatric ophthalmologist for baseline evaluation and periodic follow-up. In newborns and infants with a high-risk PWB and no history of seizures or neurological symptoms, routine screening for brain involvement is not recommended, but brain imaging can be performed in select cases. Routine follow-up neuroimaging is not recommended in children with SWS and stable neurocognitive symptoms. The treatment of ophthalmologic complications, such as glaucoma, differs based on the age and clinical presentation of the patient. These recommendations will help facilitate coordinated care for patients with SWS and may improve patient outcomes.

Quality of Neurologic Care in the United States: Initial Report From the Axon Registry.

OBJECTIVE: To provide the initial description of the quality of outpatient US neurologic care as collected and reported in the Axon Registry. METHODS: We describe characteristics of registry participants and the performance of neurology providers on 20 of the 2019 Axon Registry quality measures. From the distribution of providers' scores on a quality measure, we calculate the median performance for each quality measure. We test for associations between quality measure performance, provider characteristics, and intrinsic measure parameters. RESULTS: There were 948 neurology providers who contributed a total of 6,480 provider-metric observations. Overall, the average quality measure performance score at the provider level was 66 (median 77). At the measure level (n = 20), the average quality measure performance score was 53 (median 55) with a range of 2 to 100 (interquartile range 20-91). Measures with a lower-complexity category (e.g., discrete orders, singular concepts) or developed through the specialty's qualified clinical data registry pathway had higher performance distributions. There was no difference in performance between Merit-Based Incentive Payment System (MIPS) and non-MIPS providers. There was no association between quality measure performance and practice size, measure clinical topic/neurologic condition, or measure year of entry. CONCLUSIONS: This cross-sectional assessment of quality measure performance in 2019 Axon Registry data demonstrates modest performance scores and considerable variability across measures and providers. More complex measures were associated with lower performance. These findings serve as a baseline assessment of quality of ambulatory neurologic care in the United States and provide insights into future measure design.

American Academy of Neurology Telehealth Position Statement.

Telehealth services complement in-person neurologic care. The American Academy of Neurology supports patient access to telehealth services regardless of location, coverage for telehealth services by all subscriber benefits and insurance, equitable provider reimbursement, simplified state licensing requirements easing access to virtual care, and expanding telehealth research and quality initiatives. The roles and responsibilities of providers should be clearly delineated in telehealth service models.

Sexual and Gender Minority Health in Neurology: A Scoping Review.

Importance: Little is known about the neurologic health needs of sexual and gender minority (SGM) individuals, and existing research indicates health care disparities for this group. Objective: To describe the current state of science in SGM neurology and highlight areas of knowledge and gaps to guide future research. Evidence Review: All articles published before April 12, 2020, in PubMed, Embase, Web of Science, PsycInfo, CINAHL, and BIOSIS Previews were searched using a search string encompassing SGM descriptors and neurologic disorders. A total of 8359 items were found and entered into EndNote, and 2921 duplicates were removed. A blind title and abstract review was performed followed by full-text review in duplicate, with conflicts settled through consensus, to identify 348 articles eligible for data abstraction. Articles presenting primary data about an identified adult SGM population addressing a clinical neurology topic were included. Descriptive statistics were used for abstracted variables. Findings: Of 348 studies, 205 (58.9%) were case reports or series, 252 (72.4%) included sexual minority cisgender men, and 247 (70.9%) focused on HIV. An association was found between autism spectrum disorder and gender dysphoria in 9 of 16 studies (56.3%), and a higher risk of ischemic stroke in transgender women was shown in other studies. Literature in neuroinfectious disease, the most common topic, largely focused on HIV (173 of 200 studies [86.5%]). Findings in other neurologic topics were limited by lack of data. Conclusions and Relevance: In this rigorous compendium of SGM neurology literature, several deficiencies were found: most studies focused on a limited breadth of neurologic pathology, included only a portion of the overall SGM community, and did not assess other aspects of sociodemographic diversity that may contribute to disparities in health care access and outcomes among SGM individuals. Expanding neurologic research to include broader representation of SGM individuals and incorporating sociodemographic factors, like race/ethnicity and socioeconomic status, are essential steps toward providing equitable neurologic care for this community.