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.
13 January 2023 in Seizure: European Journal of Epilepsy
We conducted a pilot study utilizing automatic delineation of electrocardiogram (ECG) and machine learning that considered all components of the ECG complex for seizure detection. The primary outcome was to assess the feasibility of this method. The secondary outcome was to identify the most effective machine learning algorithm. We screened ECG recordings from patients included in the EPICARD cohort who underwent video-electroencephalogram monitoring. A total of 47 seizures from 32 patients were selected. Epochs of 90 min surrounding the seizures were retained. Each ECG was converted into a sequence of heartbeats modeled as a P-Q-R-S-T succession. Derivative quantities measuring time variations between the inner and outer components of heartbeats were computed, designated as δX and ΔX. Our algorithm monitored 3 to 60 successive heartbeats within a sliding window. An alarm was triggered when more than N heartbeats were classified as in-seizure (N between 3 and 20). Heartbeats were categorized as in-seizure by trained neurophysiologists. We used automated machine learning (auto-ML) platforms (Dataiku & Flaml) to assess six different algorithms: Random Forest, LightGBM, XGBoost, Decision Tree, K-Nearest Neighbors, and Extra Trees. The Extra Trees algorithm provided the best seizure detection performance regardless of the validation method used. Although longer-window models enhance detection sensitivity, they do so at the cost of delayed identification. A model analyzing 60 heartbeats with a trigger of 20 achieved 86 % sensitivity and 99.9 % specificity. Automatic delineation is reliable, however the false alarm rate remains high (1.5 per hour). Future work should focus on personalizing detection algorithms to improve this false alarm rate.
Anti-myelin-associated glycoprotein (anti-MAG) IgM antibodies provoke demyelinating neuropathies, which can be particularly disabling. Conventionally, patients with anti-MAG neuropathies were treated with rituximab alone. This study aimed to evaluate the clinical and electrophysiological efficacy of bendamustine-rituximab (BR) combination therapy for anti-MAG neuropathy patients. We retrospectively consulted the medical records of 11 patients whose diagnosis of anti-MAG neuropathy was retained and who were given BR combination therapy at university and community hospitals in northern France between 2017 and 2022. We collected clinical scores and electrophysiological data before BR therapy and at six to eleven months after treatment end (mean=8.40months). After BR therapy, six of eleven patients (54%) showed an improvement in their overall neuropathy limitations scale (ONLS) score as did five of eleven (45%) in their peripheral neuropathy disability (PND) score, but these results did not reach statistical significance. For the six patients who had a more complete clinical revaluation based on the neuropathy impairment score (NIS), five improved (P=0.021). An improvement in the sensory NIS was observed in three of six patients (50%), while the motor NIS remained stable. Patients improving their PND score seemed to start from a higher baseline value. Five of eight (62%) patients with electrodiagnostic control data met Lunn and Nobile-Orazio's electrophysiological improvement criteria. The higher the baseline PND score, the less likely was improvement of electrodiagnostic parameters. No link between duration of disease progression before treatment and clinical response was found. This multicenter cohort of anti-MAG patients given BR combination therapy is, to our knowledge, the largest published to date. Although BR therapy seems to improve the clinical and electrophysiological outcome of anti-MAG patients, precise evaluation scales are nevertheless needed to highlight improvement. Sensitive scales such as the NIS should be used routinely for monitoring anti-MAG patients. Prospective studies with a larger number of patients would be useful to confirm the efficacy of BR therapy in these patients.