The use of artificial intelligence technology is progressively expanding and advancing in the health and biomedical literature. Since its launch, ChatGPT has rapidly gained popularity and become one of the fastest-growing artificial intelligence applications in history. This study evaluated the accuracy and comprehensiveness of ChatGPT-generated responses to medical queries in clinical neurology. We directed 216 questions from different subspecialties to ChatGPT. The questions were classified into three categories: multiple-choice, descriptive, and binary (yes/no answers). Each question in all categories was subjectively rated as easy, medium, or hard according to its difficulty level. Questions that also tested for intuitive clinical thinking and reasoning ability were evaluated in a separate category. ChatGPT correctly answered 141 questions (65.3%). No significant difference was detected in the accuracy and comprehensiveness scale scores or correct answer rates in comparisons made according to the question style or difficulty level. However, a comparative analysis assessing question characteristics revealed significantly lower accuracy and comprehensiveness scale scores and correct answer rates for questions based on interpretations that required critical thinking (p = 0.007, 0.007, and 0.001, respectively). ChatGPT had a moderate overall performance in clinical neurology and demonstrated inadequate performance in answering questions that required interpretation and critical thinking. It also displayed limited performance in specific subspecialties. It is essential to acknowledge the limitations of artificial intelligence and diligently verify medical information produced by such models using reliable sources.

The study investigated associations between chronotypes (Morning [M], Neither [N], Evening [E]), sociodemographic characteristics, body mass index (BMI), smoking habits, years with migraines, sleep quality (PSQI), anxiety (HADS-A), depression (HADS-D), migraine disability (MIDAS), headache frequency, and pain intensity (VAS) in 80 individuals with migraine. Significant age differences emerged (p < 0.001), with M-types being the oldest. BMI also varied, with M-types presenting the highest median BMI (p = 0.005). While migraine duration and headache frequency showed no significant variance, sleep quality did, with E-types reporting the poorest sleep (p = 0.030). Anxiety and depression were significantly worse in E-types (HADS-A: p = 0.002; HADS-D: p = 0.010). Differences in MIDAS levels were notable (p = 0.038); however, differences in MIDAS scores were not significant (p = 0.115). Pain intensity varied, with E-types experiencing the most severe pain (p = 0.009). Post-hoc analysis showed higher MIDAS scores in E-types compared to N-types (χ² = 6.56, p = 0.038, ε² = 0.0831). The findings highlight the need for thorough patient evaluations and tailored care, considering the complex interplay of factors affecting migraine severity, particularly among different chronotypes.

Emine Kılıçparlar Cengiz, Yasemin Ekmekyapar Fırat, Meltem Güngör, İhsan Berk, Abdurrahman Neyal, Eyüp İlker Saygılı, Ayşe Münife Neyal. Clin Psychopharmacol Neurosci -0001;0:. https://doi.org/10.9758/cpn.24.1235