Previously submitted to: Journal of Medical Internet Research (no longer under consideration since Aug 15, 2025)
Date Submitted: Apr 23, 2025
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Development of a Core Outcome Set for Neurological Disorders (COS-Neuro): an AI-Assisted Thematic Framework Analysis.
ABSTRACT
Background:
Neurological disorders affect approximately 3 billion people globally, yet clinical trial success is often hindered by poorly chosen outcome measures, impacting trial design, compliance, and interpretation. Core Outcome Sets (COS) have emerged over the past 25 years as standardized tools to enhance outcome selection, ensuring comparability across studies and reflecting the priorities of both researchers and patients. Despite the success of COS initiatives in other fields, their development in neurology remains limited, leaving many trialists without disease-specific guidance. Given common themes across neurological COS, a unified framework—a ‘COS of COS’—could support outcome selection where no disease-specific COS exists.
Objective:
This study (COS-Neuro) uses Artificial Intelligence (AI) to analyse existing COS, identifying shared outcome domains to develop a thematic framework, streamlining COS creation and improving neurological trial design.
Methods:
COS-Neuro was developed using AI-assisted thematic framework analysis, followed by expert review. A modified 6-step thematic analysis was used without pre-determined codes: 1. Dataset Gathering – Data from the COMET database was collected and COS domains for neurological diseases were coded. 2. Prompt Design & Testing – LLMs (ChatGPT 3.5, Google Gemini 1.5 Flash, Meta Llama-2-70b) were trialled, and prompts refined based on responses. 3. Thematic Analysis – LLMs categorised domains into core areas. 4. Human Refinement – Experts reviewed LLM-generated core areas and selected the most appropriate for interpretation. 5. Clinical Validation – Experts validated domains, core areas, and concepts. This streamlined approach integrated AI with expert oversight to develop a standardised COS framework for neurological disorders.
Results:
With the assistance of LLMs, particularly ChatGPT, a robust conceptual framework for COS in neurological disorders was developed based on the existing 112 COS. Adapting OMERACT model, 4 concepts, 13 core areas and 75 domains were finalised following consensus of clinicians.
Conclusions:
COS-Neuro establishes AI-assisted recommendations for COS in neurological disorders. This project provides a foundation for future COS research and a reference for trials lacking established COS. It also sets a precedent for AI-assisted qualitative analysis in medicine, with the successful adaptation of OMERACT highlighting its scalability for ‘COS of COS’ development across specialties.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.