Artificial intelligence performance in clinical neurology queries: the ChatGPT model.

INTRODUCTION: 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. METHODS: 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. RESULTS: 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). CONCLUSION: 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.

Quality and Reliability Analysis of Essential Tremor Disease Information on Social Media: The Study of YouTube.

Background: YouTube has evolved into an important educational tool and information source for patients and their families. YouTube videos have the potential to influence the patients' health-related diagnosis and treatment decision-making. We aimed to evaluate the quality and usefulness of videos on essential tremor available on YouTube using quantitative instruments. Methods: Video searches were performed by typing the keywords 'essential tremor', 'postural tremor', 'action tremor', 'essential tremor hand', and 'essential tremor head' into the YouTube search bar. The top 30 videos were reviewed for each search term. The videos were analyzed by two independent raters using the DISCERN and Global Quality Scale (GQS) scoring systems. Qualitative and quantitative data were recorded for each video. Results: A total of 83 videos were analyzed. The mean DISCERN score was 41.96 out of 75 possible points, and the mean GQS score was 2.97 out of 5 possible points. Twelve percent of the videos were categorized as very poor, 38.6% as poor, 20.5% as fair, 19.3% as good, and 9.6% as excellent. The videos containing qualitative content features, such as clear information, symptoms, etiology, diagnosis, treatment, treatment response, epidemiology, diagrams, and radiological images had significantly higher DISCERN and GQS scores. Discussion: We consider that reliable and useful content is not provided on YouTube for individuals searching for information on essential tremor. We listed the best-quality videos on this topic as a reference for healthcare practitioners and patients. Patients should always verify information provided in such videos through more reliable sources.

Content and quality analysis of videos about multiple sclerosis on social media: The case of YouTube.

BACKGROUND: YouTube (YT) has grown into the largest online video platform across the world. Known to have more than two billion users of all ages, YT also serves as an important educational tool and information source for patients and their families. YT videos have the potential to influence patients' understanding of their diagnoses and treatment decision-making. METHODS: Videos were identified using the keywords "multiple sclerosis," "multiple sclerosis treatment," "relapsing remitting MS," and "central demyelinating disorder" in the YT search bar. For each search term, the top 30 videos were reviewed. The videos were analyzed by two independent raters using the DISCERN and Global Quality Scale (GQS) scoring systems. Qualitative and quantitative data were recorded for each video. RESULTS: A total of 99 videos were analyzed. The mean DISCERN score was 43.44 out of 75 possible points, and the mean Global Quality Scale (GQS) score was 2.77 out of 5 possible points. Of all the videos, 14.1, 29.3, 15.2, and 29.3% were categorized as very poor, poor, moderate, good, and excellent, respectively. Videos that included qualitative features such as clear information; information related to symptomatology, etiology, diagnosis, treatment, treatment response, and epidemiology; and diagrams and radiological images had significantly higher scale scores. Audience engagement parameters were significantly higher for videos containing animation, treatment response, and radiological images. CONCLUSION: We maintain that sufficient, reliable, and useful content is not provided for those seeking information on YT about MS. Everyone seeking information about MS should always verify information provided in YT videos using more reliable sources of information. Video producers should optimize their videos to contain high-quality and reliable data and to attract larger audiences.