Background: Evidence of immune-mediated neurological syndromes associated with the severe acute respiratory syndrome coronavirus (SARS-CoV-2) infection is limited. We therefore investigated clinical, serological and CSF features of coronavirus disease 2019 (COVID-19) patients with neurological manifestations. Methods: Consecutive COVID-19 patients with neurological manifestations other than isolated anosmia and/or non-severe headache, and with no previous neurological or psychiatric disorders were prospectively included. Neurological examination was performed in all patients and lumbar puncture with CSF examination was performed when not contraindicated. Serum anti-gangliosides antibodies were tested when clinically indicated. Results: Of the 349 COVID-19 admitted to our center between March 23rd and April 24th 2020, 15 patients (4.3%) had neurological manifestations and fulfilled the study inclusion/exclusion criteria. CSF examination was available in 13 patients and showed lymphocytic pleocytosis in 2 patients: 1 with anti-contactin-associated protein 2 (anti-Caspr2) antibody encephalitis and 1 with meningo-polyradiculitis. Increased serum titer of anti-GD1b antibodies was found in three patients and was associated with variable clinical presentations, including cranial neuropathy with meningo-polyradiculitis, brainstem encephalitis and delirium. CSF PCR for SARS-CoV-2 was negative in all patients. Conclusions: In SARS-Cov-2 infected patients with neurological manifestations, CSF pleocytosis is associated with para- or post-infectious encephalitis and polyradiculitis. Anti-GD1b and anti-Caspr2 autoantibodies can be identified in certain cases, raising the question of SARS-CoV-2-induced secondary autoimmunity.

Background/Objectives: Artificial intelligence (AI), particularly large language models (LLMs), has demonstrated versatility in various applications but faces challenges in specialized domains like neurology. This study evaluates a specialized LLM’s capability and trustworthiness in complex neurological diagnosis, comparing its performance to neurologists in simulated clinical settings. Methods: We deployed GPT-4 Turbo (OpenAI, San Francisco, CA, US) through Neura (Sciense, New York, NY, US), an AI infrastructure with a dual-database architecture integrating “long-term memory” and “short-term memory” components on a curated neurological corpus. Five representative clinical scenarios were presented to 13 neurologists and the AI system. Participants formulated differential diagnoses based on initial presentations, followed by definitive diagnoses after receiving conclusive clinical information. Two senior academic neurologists blindly evaluated all responses, while an independent investigator assessed the verifiability of AI-generated information. Results: AI achieved a significantly higher normalized score (86.17%) compared to neurologists (55.11%, p < 0.001). For differential diagnosis questions, AI scored 85% versus 46.15% for neurologists, and for final diagnosis, 88.24% versus 70.93%. AI obtained 15 maximum scores in its 20 evaluations and responded in under 30 s compared to neurologists’ average of 9 min. All AI-provided references were classified as relevant with no hallucinatory content detected. Conclusions: A specialized LLM demonstrated superior diagnostic performance compared to practicing neurologists across complex clinical challenges. This indicates that appropriately harnessed LLMs with curated knowledge bases can achieve domain-specific relevance in complex clinical disciplines, suggesting potential for AI as a time-efficient asset in clinical practice.