Background/Objectives: Large language models (LLMs) are revolutionizing the world and the field of medicine while constantly improving themselves. With recent advancements in image interpretation, evaluating the reasoning capabilities of these models and benchmarking their performance on brain MRI tasks has become crucial, as they may be utilized—albeit off-label—for patient care by both neurosurgeons and non-neurosurgeons. Methods: ChatGPT-4o, Grok, and Gemini were presented with 35,711 slices of brain MRI, including various pathologies and normal MRIs. Models were asked to identify the MRI sequence and determine the presence of pathology. Their individual performances were measured and compared with one another. Results: GPT refused to answer 28.02% of the slices despite three attempts, whereas Grok and Gemini provided responses on the first attempt for every slice. Gemini achieved 74.54% pathology prediction and 46.38% sequence prediction accuracy. GPT-4o achieved 74.33% pathology prediction and 85.98% sequence prediction accuracy for questions that it had answered (53.50% and 61.67% in total, respectively). Grok achieved 65.64% pathology prediction and 66.23% sequence prediction accuracy. Conclusions: The image interpretation capabilities of the investigated LLMs are limited for now and require further refinement before competing with specifically trained and fine-tuned dedicated applications. Amongst them, Gemini outperforms the others in pathology prediction while Grok outperforms others in sequence prediction. These limitations should be kept in mind if use during patient care is planned.

BACKGROUND: The aim of this paper is to report one of the significant applications of artificial intelligence (AI) and how it affects everyday clinical practice in neurosurgery. The authors present a case in which a patient was diagnosed via an AI algorithm during ongoing magnetic resonance imaging (MRI). According to this algorithm, the corresponding physicians were immediately warned, and the patient received prompt appropriate treatment. OBSERVATIONS: A 46-year-old female presenting with nonspecific headache was admitted to undergo MRI. Scanning revealed an intraparenchymal mass that was detected by an AI algorithm running on real-time patient data while the patient was still in the MRI scanner. The day after MRI, a stereotactic biopsy was performed. The pathology report confirmed an isocitrate dehydrogenase wild-type diffuse glioma. The patient was referred to the oncology department for evaluation and immediate treatment. LESSONS: This is the first report of a glioma diagnosed by an AI algorithm and a subsequent prompt operation in the literature—the first of many and an example of how AI will enhance clinical practice.

Telomeric repeat-containing RNAs (TERRAs) are expressed from subtelomeric regions, as long non-coding RNAs responsible for maintaining telomere length and stabilizing the genome. After TERRA is transcribed (f-TERRA) from subtelomere regions, it hybridizes (h-TERRA) into telomeres and intergenic regions to maintain genome and telomere stability. Here, we separately determine changes in two TERRA fractions, f-TERRA and h-TERRA levels in relation to telomere length (TL) in first time meningioma patients with preoperative and postoperative comparisons with the control group. Since there is a lack of established biomarkers for monitoring meningiomas despite their high prevalence among primary brain tumors, this study was designed. Fifty patients and 44 healthy controls were included in this study. Real-time quantitative PCR (q-PCR) reactions were performed to determine telomere length (TL), f-TERRA and h-TERRA levels. Statistically significant differences were observed between the levels of f-TERRA, h-TERRA, telomere length (TL), compared with the healthy control group and patients. When postoperative blood h-TERRA levels were compared between the patient group and the control group, no statistically significant differences were observed. However, in the correlation analysis between postoperative tumor volume and postoperative blood h-TERRA levels, a positive, moderate and statistically significant relationship was found. This study highlights the importance of presenting the results by means of preoperative and postoperative comparisons of meningiomas. Based on the available information, we suggest that the levels of f-TERRA and h-TERRA could also be potential biomarkers for diagnostic, therapeutic, and following of meningiomas.