ChatGPT M.D.: Is there any room for generative AI in neurology?

ChatGPT, a general artificial intelligence, has been recognized as a powerful tool in scientific writing and programming but its use as a medical tool is largely overlooked. The general accessibility, rapid response time and comprehensive training database might enable ChatGPT to serve as a diagnostic augmentation tool in certain clinical settings. The diagnostic process in neurology is often challenging and complex. In certain time-sensitive scenarios, rapid evaluation and diagnostic decisions are needed, while in other cases clinicians are faced with rare disorders and atypical disease manifestations. Due to these factors, the diagnostic accuracy in neurology is often suboptimal. Here we evaluated whether ChatGPT can be utilized as a valuable and innovative diagnostic augmentation tool in various neurological settings. We used synthetic data generated by neurological experts to represent descriptive anamneses of patients with known neurology-related diseases, then the probability for an appropriate diagnosis made by ChatGPT was measured. To give clarity to the accuracy of the AI-determined diagnosis, all cases have been cross-validated by other experts and general medical doctors as well. We found that ChatGPT-determined diagnostic accuracy (ranging from 68.5% ± 3.28% to 83.83% ± 2.73%) can reach the accuracy of other experts (81.66% ± 2.02%), furthermore, it surpasses the probability of an appropriate diagnosis if the examiner is a general medical doctor (57.15% ± 2.64%). Our results showcase the efficacy of general artificial intelligence like ChatGPT as a diagnostic augmentation tool in medicine. In the future, AI-based supporting tools might be useful amendments in medical practice and help to improve the diagnostic process in neurology.

Persistent Postural Perceptual Dizziness In The Neurology Clinic.

Aim: To determine the proportion of referrals to a General Neurology New Patient Clinic which meet the diagnostic criteria of Persistent Postural Perceptual Dizziness (PPPD) and to gauge patient-perceived response to treatment. Methods: Referral letters, n=1315, to a General Neurology New Patient Clinic from 2021-2023 were screened for terms 'dizziness', 'vertigo', 'unsteadiness' and 'vestibular'. A chart review was performed to establish study outcomes. Results: 202 (15.4%) patients were referred with 'dizziness', 'vertigo' or 'unsteadiness', 22 (11%) of which fulfilled the diagnostic criteria. Venlafaxine was offered in 10 (45.5%) patients and conferred ≥50% benefit in 8 (80%). Vestibular physiotherapy improved symptoms by ≥25% in all 7 (100%) patients with access to the intervention. Cognitive behavioural therapy and effective communication of the diagnosis alleviated symptoms by 50% in 3 (14%) patients respectively. Discussion: PPPD is increasingly recognised in patients with chronic vestibular symptoms and can cause significant functional morbidity. Venlafaxine may independently improve symptoms1.

Cranial Autonomic Symptoms in Migraine Patient Presenting in the Department of Neurology of a Tertiary Care Center: A Descriptive Cross-sectional Study.

INTRODUCTION: Cranial autonomic symptoms (CAS) are typically associated with trigeminal autonomic cephalagias (TACs) and are also a part of TACs' diagnostic criteria. However, they have also been commonly reported in migraine patients. This study aimed to find the prevalence of CAS in Migraine patients who presented to the Department of Neurology in a tertiary care center. METHODS: This descriptive cross-sectional study was conducted among migraine patients who visited the Department of Neurology of a tertiary care center from September 2023 to December 2023 after obtaining ethical approval from the Institutional Review Committee. Neurologists used ICHD-3 beta criteria to diagnose migraine and the presence of cranial autonomic symptoms in patients with migraine through face-to-face interviews using a structured questionnaire. A convenience sampling method was used. The point estimate was calculated at a 95% Confidence Interval. RESULTS: Among 119 migraine patients, at least one cranial autonomic symptom was seen in 76 (63.86%) (55.23-72.51, at 95% Confidence Interval). Lacrimation 34 (44.73%) and conjunctival injection 27 (35.52%) were the two most commonly reported symptoms. Bilateral CAS was present in 60 (78.94%) patients. CONCLUSIONS: The prevalence of at least one CAS in migraine patients was found to be similar to other studies done in similar settings.

Using Multilevel Models and Generalized Estimating Equation Models to Account for Clustering in Neurology Clinical Research.

In clinical and health services research, clustered data (also known as data with a multilevel or hierarchical structure) are frequently encountered. For example, patients may be clustered or nested within hospitals. Understanding when data have a multilevel structure is important because clustering of individuals can induce a homogeneity in outcomes within clusters, so that, even after adjusting for measured covariates, outcomes for 2 individuals in the same cluster are more likely to be similar than outcomes for 2 individuals from different clusters. Using conventional statistical regression models to analyze clustered data can result in incorrect conclusions being drawn. In particular, estimated CIs may be artificially narrow, and significance levels may be artificially low. As a result, one may conclude that there is a statistically significant association when there is none. To avoid this problem, investigators should ensure that their analyses use techniques that account for clustering of data. Generalized linear models estimated using generalized estimating equation (GEE) methods and multilevel regression models (also known as hierarchical regression models, mixed-effects models, or random-effects models) are two such techniques. We provide an introduction to clustered or multilevel data and describe how GEE models or multilevel models can be used for the analysis of multilevel data.

[Online quizzes for practice and assessment of pharmacotherapeutic knowledge during clinical courses in medical school - a pilot study in the psychiatry and neurology courses]. / Webbaserade quiz om läkemedel för övning och examination.

In this study, we developed auto-graded quizzes for practice and for summative assessment, covering drugs of relevance in the undergraduate clinical psychiatry and neurology courses in medical school. The underlying intention was to combine repetition of theoretical aspects and promoting progression to the clinical context. The quizzes were implemented in two steps. After the courses in question were completed, before and after the first as well as the second step of quiz implementation, the students' achieved level of knowledge was investigated by a voluntary formative test/questionnaire including 20 patient-based single best answer questions. In the first step, voluntary practice quizzes and a summative assessment test were introduced. In the second step, a clinical context was provided to the quizzes, using the structure of the practical manual to good prescribing issued by the World Health Organization in 1994. Furthermore, the summative test was expanded for improved constructive alignment, exposing the students to the drug-related course content to a greater extent. In all, 274 students out of 404 participated in the study (response rate: 68%; 56% women; 66% ≤24 years). Compared with before the quiz implementation (median number of correct answers: 10 [interquartile range: 9-13]), no difference was seen after the first step (11 [8-13]; P=0.88) but a clear improvement appeared after the second step (14 [12-16]; P<0.0001). After the second step, the students reported having used all (17%), most (22%), some (32%), or no (29%) practice quizzes. The extent of use was positively correlated with the number of correct answers in the formative test (r=0.33; P=0.002). After the second step, the student-reported number of attempts at the assessment quiz was in median 6 times (interquartile range: 3-9). There was a negative correlation between the number of quiz attempts and the extent of use of practice quizzes (r=-0.22; P=0.034) as well as the number of correct answers in the formative test (r=-0.44; P<0.0001). In conclusion, practice and assessment quizzes about drugs, elaborated with clinical context and constructive alignment, may increase pharmacotherapeutic knowledge in medical students.

The history of the European Neurological Society (1986-2014)-10 years later.

BACKGROUND AND PURPOSE: The European Academy of Neurology (EAN) was a merger from two parent societies: the European Neurological Association (ENS, founded in 1986) and the European Federation of Neurological Societies (EFNS, founded in 1987). METHODS: This article was written by nine former presidents, three of whom were also founders of the ENS, and is based on recollections and documents. It follows up on a review of the ENS history stored in the EAN archive. RESULTS: The first European society (ENS) was founded by eight individual European academic clinician-neuroscientists aiming at joining with other qualified European neuroscientists on an individual membership basis. After 1990 members were also invited from behind the former Iron Curtain. A principal goal was holding neurology meetings (700 participants in 1988 and over 3000 in 2010), promoting collaborative research projects with exchange of junior neuroscientists, and providing teaching and education independent from nationality. Health politics were not part of the agenda. The executive boards (4-year term) were staffed with academic scientists from all subspecialties of neurology. Numerous bursaries and fellowships were established for junior neurologists. The impact of ENS members on research activities of young investigators was appreciated by academia at large. After years of negotiations ENS and EFNS joint efforts resulted in forming the EAN covering all fields of neurology and neuroscience under one roof. CONCLUSION: The basic principles of the ENS were successfully integrated into the new EAN in particular documented by the number of individual members rising to over 4000 in 2024.

Trends in direct healthcare utilization observed for persons with MS among teleneurology users and diverse populations.

BACKGROUND: The impact of teleneurology on healthcare utilization (HCU) in MS is unknown. OBJECTIVE: Evaluate the association between teleneurology and HCU. METHODS: A retrospective longitudinal analysis of HCU among adult MS and clinically isolated syndrome (CIS) patients residing in the Cleveland/Akron area from July 2020 to July 2022. Negative binomial regression models evaluated the association between number of laboratory and MRI orders per visit and number of emergency visits per patient across patient groups with variable proportions of teleneurology visits. RESULTS: A total of 3208 patients completed 15,795 visits. Patients using teleneurology had more visits (rate ratio (RR) 1.707-1.719, p < 0.001). Teleneurology visits had fewer laboratory (RR 0.571) and MRI orders (RR 0.693, p < 0.001). There was no difference in emergency care utilization for teleneurology patients (p ⩾ 0.05). More emergency visits were observed in Black (RR 1.414) and Medicaid (RR 1.893) patients, regardless of visit type (p < 0.001). CONCLUSION: Teleneurology visits were associated with fewer orders, suggesting teleneurology may be incorporated into healthcare models without increasing utilization related to the visit. Teleneurology was also associated with increased visit volumes but no difference in emergency HCU. More studies are needed to clarify the ultimate impact of teleneurology on overall HCU. More emergency visits, regardless of visit type, were observed among at-risk populations, warranting further investigation.

Assessing Patient Safety Culture: Insights from a Neurological Institute.

Introduction-Aim: Assessment of patient safety culture is important for enhancing hospital service quality and clinical outcomes. This study aimed to evaluate the safety of patient culture among health professionals in a neurological institute, in order to identify areas of improvement. The second objective of our study was to determine the influence of the sociodemographic data of the participants on the awareness of patient safety. METHODS: A cross-sectional descriptive study was conducted among healthcare workers exercising at a neurological institution using a validated Hospital Survey of Patient Safety Culture questionnaire containing ten safety care dimensions. RESULTS: A total of 123 responses to the questionnaire were analyzed, accounting for 34.5% of the total (Cronbach's alpha=0.677). Among the participants, 61.8% considered the level of awareness regarding patient safety to be acceptable. The dimensions considered as strengths were "Organizational learning and continuous improvement" with the highest positive response (60.3%) "Relationship patient-staff member" (58.9%) and "Teamwork within units" (58.9%). However, the dimensions considered as weaknesses were "Management support for patient safety" with 28.5% of positive responses and "Communication openness and non-punitive response to error" (40%). CONCLUSION: Patient safety culture among healthcare professionals is at an average with "Organizational learning and continuous improvement" being a positive aspect. However, improvements should be made in all dimensions to enhance and promote patient safety within the institution.

We Don't Talk About X(Twitter): A Cross-Sectional Analysis of Social Media Utilization Among Neurologists.

BACKGROUND AND OBJECTIVES: Medical professionals use social media for career development, education, clinical outreach, or advocacy. Prior studies estimate that 25% to 65% of health care providers use social media professionally; however, the number of users and platforms are rapidly changing. Therefore, as part of a broader study, we set out to assess platform preferences and social media usage among neurologists. METHODS: This was a multisite cross-sectional analysis consisting of a REDCap survey of clinicians, residents, and medical students. Faculty, trainees, or clinical year medical students interested in child neurology or adult neurology residency or fellowship programs within the United States were eligible to participate. Recruitment methods were broad to encompass as diverse and extensive participation as possible. Results were analyzed using descriptive statistics. Data are presented according to the STROBE guidelines. RESULTS: Of the 226 neurology respondents, 55% (n = 124) were child neurology and 45% (n = 102) were adult neurology across all career stages, including students. Of the 70% who reported using social media in a professional capacity, the most commonly reported reasons were for networking and collaboration (n = 95, 60%), self-directed medical learning (n = 90, 57%), and brand building and reputation (n = 62, 39%). Twitter and Facebook were the most common and versatile platforms used by neurologists. Medical students had the highest documentation of social media scholarships on their curriculum vitae (37%, P = .016) and the most interest (33%, P = .016) in learning how to document social media scholarships if they were not already. Early faculty shared this interest more than residents, fellows, or mid-late career faculty. In all groups except for mid-late career faculty, a majority of respondents (>75%) showed interest in learning how to leverage social media for career development. DISCUSSION: Social media is used professionally by a majority of neurologists, most commonly for networking, self-directed learning, and building individual brands. Opportunities exist to better understand platform preferences and ways to optimize their use for various professional activities as well as to provide education on effective professional use of social media including documentation for promotion.

European Academy of Neurology: First 10 years.

The European Academy of Neurology (EAN) was founded in May 2014 as the scientific society of all neurologists and all national neurological societies in Europe. The creation of EAN was based on the conscious decision of two predecessor societies (the European Federation of Neurological Societies and the European Neurological Society) to have a unique society for this continent with its 53 countries according to the World Health Organization and with the EU as the most important continental political decision level. In this report, the important milestones and the motivations of the decision-makers during the first 10 years are described. The development of the annual congress, the broad educational agenda, and the scientific groundwork including the European guidelines for the practise of neurology are described. Collaboration with and work for the national neurological societies is an important task for EAN. The political representation of neurology in Brussels and collaboration with the scientific societies of neighbouring medical disciplines and patient organizations are other major tasks on the agenda of the organization. EAN's goal is to reduce the burden of neurological diseases and to be the "home of neurology" in Europe for physicians, patients, and society. EAN communicates and interacts with its members, patients, partners, politicians, and the public through different channels. EAN is the owner of the scientifically independent European Journal of Neurology. EAN is based in Vienna, where its head office is located, but is also strongly represented in Brussels.

Cell and gene therapy in neuro-oncology.

The majority of primary brain tumors are gliomas, among which glioblastoma multiforme (GBM) is the most common malignant brain tumor in adults. GBM has a median survival of 18-24 months, and despite extensive research it remains incurable, thus novel therapies are urgently needed. The current standard of care is a combination of surgery, radiation, and chemotherapy, but still remains ineffective due to the invasive nature and high recurrence of gliomas. Gene therapy is a versatile treatment strategy investigated for multiple tumor types including GBM. In gene therapy, a variety of vectors are employed to deliver genes designed for different antitumoral effects. Also, over the past decades, stem cell biology has provided a new approach to cancer therapies. Stem cells can be used as regenerative medicine, therapeutic carriers, drug targeting, and generation of immune cells. Stem cell-based therapy allows targeted therapy that spares healthy brain tissue as well as establishes a long-term antitumor response by stimulating the immune system and delivering prodrug, metabolizing genes, or even oncolytic viruses. This chapter describes the latest developments and the current trends in gene and cell-based therapy against GBM from both preclinical and clinical perspectives, including different gene therapy delivery systems, molecular targets, and stem cell therapies.

Partnering in Global Health: What Is a Successful Dyad? The Duke Experience.

This article explores the transformative partnership between Duke Global Neurosurgery and Neurology (DGNN) and Uganda, emphasizing the power of dyads in international collaboration. It details the partnership's focus on service, research, and training, highlighting key accomplishments like the establishment of a neurosurgery residency program, expansion of services, and an epilepsy clinic. Challenges such as resource constraints and cross-cultural collaboration are addressed. Recommendations are provided for developing similar partnerships, underlining the importance of mutual respect, shared goals, and long-term commitment. The DGNN-Uganda dyad is a blueprint for leveraging collaboration to improve global neurosurgical care and reduce health care inequities.