Leveraging Large Language Models to Derive Multiple Sclerosis Progression Assessments from Clinical Notes: A...

Area of Science:

• Neurology
• Artificial Intelligence
• Clinical Informatics

Background:

• Accurate assessment of multiple sclerosis (MS) progression is crucial for patient care and research.
• Key progression indicators are often embedded within unstructured clinical notes.
• Current methods for extracting this data can be labor-intensive.

Purpose of the Study:

• To evaluate the feasibility of developing and validating a large language model (LLM)-based classifier.
• To ascertain multiple sclerosis (MS) progression using clinical notes.
• To extract Expanded Disability Status Scale (EDSS) and Functional Systems (FS) scores automatically.

Main Methods:

• Development of a large language model (LLM) classifier.
• Utilizing clinical notes as the data source.
• Validation of the LLM's performance in classifying MS progression indicators.

Main Results:

• The study assessed the feasibility of the LLM-based approach.
• Preliminary findings indicate potential for automated MS progression ascertainment.
• Further validation is required to confirm accuracy and reliability.

Conclusions:

• Developing an LLM-based classifier is a feasible approach for MS progression ascertainment from clinical notes.
• This method holds promise for improving efficiency in clinical care and research.
• Future work should focus on robust validation and integration into clinical workflows.