This bibliometric study examines the trends and global productivity of artificial intelligence (AI) research in clinical neurology and neuroimaging from 1980 to 2024. Data were retrieved from the Web of Science database, encompassing 5,020 publications focusing on AI in clinical neurology and neuroimaging. Among these, 2,687 were original research articles, predominantly published in English, with an average of 19.44 citations per article and an H-index of 90. Our analysis reveals a significant increase in publication activity, particularly after 2019, with the annual count peaking at 607 articles in 2024. The United States and China emerged as the leading contributors, and a strong positive correlation was found between publication productivity and both gross domestic product (GDP) and GDP purchasing power parity. However, no significant relationship was observed with the Human Development Index. Key research areas include radiology, psychiatry, and surgery, with machine learning and deep learning dominating the field. Regression models predict continued growth in AI-related research, underscoring its expanding role in advancing diagnostic and therapeutic strategies for neurological disorders. This study highlights the importance of interdisciplinary collaboration and high-impact journals in shaping the future of AI applications in clinical neurology and neuroimaging.

A case admitted with dysarthria and syncope and hyperintense lesion in the splenium of the corpus callosum, diagnosed as Legionnaires' disease by detecting Legionella antigen in the urine, and recovered only with antibiotic treatment is presented because it is rare in the literature. When a 64-year-old female patient was admitted to the emergency department with complaints of sudden loss of consciousness and fainting at home, she had speech impairment, and her pulse oxygen saturation in room air was 88%. In the neurological examination, there was no pathological finding except dysarthria in the patient with no motor deficit. The patient had no respiratory complaints and had a recent travel history. In laboratory examinations, hyponatremia was detected with increased C-reactive protein and liver enzymes. Consolidation was observed in the lower right zone on chest computed tomography. Ampicillin + sulbactam (4x1 gr, intravenous) and clarithromycin (2 × 500 mg orally) were initiated. On cranial magnetic resonance, a hyperintense lesion was observed in the splenium of the corpus callosum in the oval T2 sequence. Legionella pneumophila serogroup 1 antigen in urine was reported as positive. On the ^fourth day of her hospitalization, the patient, whose CRP and liver enzyme values regressed, her hyponatremia improved, her pulse oxygen saturation increased to 92% in room air, and her speech became comprehensible, was discharged after oral antibiotic treatment was arranged. On the 12^th day, the speech ability of the patient completely returned to normal.ConclusionLegionella infection should be suspected in the presence of pneumonia and corpus callosum splenium lesion.

Background The relationship between collateral circulation and prognosis after endovascular treatment in anterior circulation strokes has been reported in many studies. Objective In this study, we aimed to compare the predictive power of clinical outcome by comparing five different collateral scores that are frequently used. Methods Among the patients who underwent endovascular treatment in our clinic between November 2019 and December 2021, patients with premorbid mRS < 3, intracranial ICA and/or MCA M1 occlusion, and a pre-procedural multiphase CTA examination were included in the study. Demographic, technical, and duration information about the procedure, major events after the procedure, and clinical outcomes at 3 months were recorded. The mCTA, Tan, Maas, Miteff, and rLMC collateral scores of the patients were evaluated. Results Clinical outcome at 3 months were good in 37 of the 68 patients included in the study (mRS ≤ 2). Only the mCTA and rLMC collateral scores were statistically significantly higher in those with a good clinical outcome. Significant correlation with 3-month mRS was detected only in mCTA and rLMC scores. Although rLMC and mCTA collateral scores showed a statistically significant association with prognosis, they were not sufficient to be an independent predictor of prognosis. Conclusion mCTA and rLMC were found to have the highest predictive power of clinical outcome and the highest correlation with the 3-month clinical outcome. Our study suggests that it would be beneficial to develop a new scoring system over multiphase CTA, which combines regional and temporal evaluation, which are the strengths of both collateral scoring.

Background/Objectives: This study aimed to evaluate the ability of ChatGPT-5, a multimodal large language model, to perform automated ASPECTS assessment on non-contrast CT (NCCT) in patients with acute ischemic stroke. Methods: This retrospective, single-center study included 199 patients with anterior circulation AIS who underwent baseline NCCT before reperfusion therapy between November 2020 and February 2025. Each NCCT was evaluated by two human readers and by ChatGPT-5 using four representative images (two ganglionic and two supraganglionic). Interobserver agreement was measured with the intraclass correlation coefficient (ICC), and prognostic performance was analyzed using multivariable logistic regression and receiver operating characteristic (ROC) analysis for 3-month functional independence (mRS ≤ 2). Results: ChatGPT-5 demonstrated good-to-excellent agreement with expert consensus (ICC = 0.845; 95% CI, 0.792–0.884; κ = 0.79). ChatGPT-ASPECTS were independently associated with 3-month functional independence (OR = 1.28 per point; p = 0.004), comparable to consensus-ASPECTS (OR = 1.31; p = 0.003). Prognostic discrimination was similar between ChatGPT-5 and consensus scoring (AUC = 0.78 vs. 0.80; p = 0.41). Conclusions: ChatGPT-5 achieved high reliability and strong prognostic validity in automated ASPECTS assessment without task-specific training. These findings highlight the emerging potential of large language models for quantitative image interpretation, though clinical implementation will require multicenter validation and regulatory approval.

Objective: In this study, we aimed to examine mainly the uric acid to HDL ratio (UHR) and some other factors in patients with OSAS and to see if this ratio could be used as a marker for the disease.Materials and Methods: We reviewed the records of 113 patients who had polysomnography. We collected demographic information, OSAS risk factors, polysomnography results such as minimum oxygen saturation, REM percentage, and apnea hypopnea index, and laboratory values including UHR and the monocyte to HDL ratio. We analyzed how these factors were related to disease severity.Results: We found that UHR was significantly associated with disease severity, showing that it may be a useful predictive marker. The monocyte to HDL ratio and the mean heart rate during sleep were also related to disease severity. These results show that several simple and accessible markers may help in understanding OSAS.Conclusion: UHR may support earlier and more effective identification of patients with OSAS.

Vestibüler migren (VM), genellikle periferik vertigo olarak yanlış teşhis edilen, epizodik vertigo ve migren semptomları ile karakterize, engelliliğe neden olan bir hastalıktır. Bu olgu sunumunda, dirençli VM'si olan 25 yaşındaki bir kadın hastanın, büyük oksipital sinir (GON) blokajı ile başarılı bir şekilde tedavi edilmesi anlatılmaktadır. GON blokajı, hem baş ağrısı hem de vestibüler semptomlarda hızlı ve belirgin bir rahatlama sağlamış olup, maliyet etkin ve az kullanılan bir müdahale olarak potansiyelini vurgulamaktadır. Bu olgu, dirençli VM yönetiminde doğru tanının ve multimodal tedavi yaklaşımlarının önemini vurgulamaktadır.