Aller au contenu
  1. Publications/

Specialized Large Language Model Outperforms Neurologists at Complex Diagnosis in Blinded Case-Based Evaluation

Brain Sciences · 2025

DOI: 10.3390/brainsci15040347

Auteurs

Barrit S, Torcida N, Mazeraud A, Boulogne S, Benoit J, Carette T, Carron T, Delsaut B, Diab E, Kermorvant H, Maarouf A, Maldonado Slootjes S, Redon S, Robin A, Hadidane S, Harlay V, Tota V, Madec T, Niset A, Al Barajraji M, Madsen JR, El Hadwe S, Massager N, Lagarde S, Carron R

Les auteurs en lien sont membres de l'INS.

Équipes

DynaMap, NeuroStim

Résumé

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 di

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 di

Lire l’article