18 January 2024 in European Journal of Neurology
Background and purpose: The integration of artificial intelligence (AI) in healthcare has the potential to revolutionize patient care and clinical decision‐making. This study aimed to explore the reliability of large language models in neurology by comparing the performance of an AI chatbot with neurologists in diagnostic accuracy and decision‐making.Methods: A cross‐sectional observational study was conducted. A pool of clinical cases from the American Academy of Neurology's Question of the Day application was used as the basis for the study. The AI chatbot used was ChatGPT, based on GPT‐3.5. The results were then compared to neurology peers who also answered the questions—a mean of 1500 neurologists/neurology residents.Results: The study included 188 questions across 22 different categories. The AI chatbot demonstrated a mean success rate of 71.3% in providing correct answers, with varying levels of proficiency across different neurology categories. Compared to neurology peers, the AI chatbot performed at a similar level, with a mean success rate of 69.2% amongst peers. Additionally, the AI chatbot achieved a correct diagnosis in 85.0% of cases and it provided an adequate justification for its correct responses in 96.1%.Conclusions: The study highlights the potential of AI, particularly large language models, in assisting with clinical reasoning and decision‐making in neurology and emphasizes the importance of AI as a complementary tool to human expertise. Future advancements and refinements are needed to enhance the AI chatbot's performance and broaden its application across various medical specialties.
17 May 2024 in Journal of Neuroimmunology
28 February 2026 in Headache and Pain Research
Purpose: This study aimed to determine whether patients with migraine experience improvements in self-reported sleep quality and daytime sleepiness after starting monoclonal antibody (mAb) therapy targeting the calcitonin gene-related peptide (CGRP) or its receptor, and to explore the association between treatment efficacy and improvements in sleep quality.Methods: This prospective, multicenter, observational, longitudinal study was conducted across 12 headache centers. Adults with episodic or chronic migraine who began anti-CGRP mAb therapy were assessed at baseline, 3 months, and 6 months. Sleep quality and daytime sleepiness were evaluated using the Portuguese version of the Pittsburgh Sleep Quality Index (PSQI-PT) and the Portuguese version of the Epworth Sleepiness Scale (ESS-PT), respectively. Results: Of 118 enrolled patients, 109 completed the study (86.4% female; mean age, 43.6 years). A significant improvement in sleep quality was observed, with median PSQI-PT scores decreasing from 9 at baseline to 6 at 6 months (p<0.001). Daytime sleepiness also improved, with median ESS-PT scores decreasing from 7 to 6 (p=0.04). Migraine frequency decreased significantly, from a median of 13 to 4 monthly migraine days (p<0.001). Greater migraine improvement was independently associated with greater PSQI-PT improvement (p<0.001), whereas changes in ESS-PT were not correlated with treatment efficacy.Conclusion: Anti-CGRP mAb therapy was associated with significant improvements in sleep quality, likely mediated through migraine relief. Changes in ESS-PT were not correlated with treatment efficacy, suggesting a possible interaction between migraine mechanisms and CGRP-mediated sleep–wake regulation. Future research should focus on clarifying the mechanisms underlying these associations.
20 April 2025 in Clinical Neurophysiology
31 August 2024 in BMJ Case Reports
Stroke warning syndromes manifest as brief, recurring episodes of focal neurological deficits that precede definitive brain ischaemia. Although the mechanisms remain unclear, intermittent hypoperfusion in specific vascular territories may explain these phenomena. A man in his 60s with vascular risk factors experienced recurrent episodes of sudden loss of consciousness. Initial imaging and tests were normal, excluding other potential causes. MRI revealed bilateral thalamic infarction and the presence of an artery of the Percheron variant. We propose ‘thalamic warning syndrome’ as a new term for this clinical presentation, characterised by recurrent transient loss of consciousness and a high risk of subsequent thalamic infarction. Early recognition of this syndrome can aid in the initial management and prognosis of similar cases, potentially preventing more severe neurological impairments.