Previously submitted to: JMIR AI (no longer under consideration since Apr 21, 2025)
Date Submitted: Feb 14, 2025
Open Peer Review Period: Mar 3, 2025 - Apr 28, 2025
(closed for review but you can still tweet)
NOTE: This is an unreviewed Preprint
Warning: This is a unreviewed preprint (What is a preprint?). Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).
Peer review me: Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period (in this case, a "Peer Review Me" button to sign up as reviewer is displayed above). All preprints currently open for review are listed here. Outside of the formal open peer-review period we encourage you to tweet about the preprint.
Citation: Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
Final version: If our system detects a final peer-reviewed "version of record" (VoR) published in any journal, a link to that VoR will appear below. Readers are then encourage to cite the VoR instead of this preprint.
Settings: If you are the author, you can login and change the preprint display settings, but the preprint URL/DOI is supposed to be stable and citable, so it should not be removed once posted.
Submit: To post your own preprint, simply submit to any JMIR journal, and choose the appropriate settings to expose your submitted version as preprint.
Warning: This is an author submission that is not peer-reviewed or edited.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.
Yesil o1 Pro: Evidence-Based AI Model for Health and Benchmarking in Clinical Decision Support
ABSTRACT
Background:
Integrating evidence-based approaches in healthcare and artificial intelligence (AI) is crucial for enhancing clinical decision-making and patient safety. Yesil o1 Pro is a specialized large language model (LLM) designed to transform medical knowledge synthesis by leveraging a comprehensive, curated database of scientific literature, clinical guidelines, and medical textbooks.
Objective:
The system's innovative "AI Hospital" framework employs domain-specific expert agents coordinated by a central Master Agent, enabling tailored and precise medical responses across multiple disciplines.
Methods:
The model's advanced methodology incorporates sophisticated techniques including GraphRAG-based retrieval, extensive fine-tuning with 1.5 million question-answer pairs, and Chain of Thought (CoT) reasoning. Its robust training dataset comprises 100.5M words from high-impact journals, 96.8M words from core medical texts, and 74.4M words from international standards, ensuring a comprehensive and authoritative knowledge base.
Results:
Benchmark evaluations demonstrate Yesil o1 Pro's exceptional performance, achieving an overall accuracy of 89.1% and surpassing leading models like GPT-4o (83.9%) and Claude 3.5 Sonnet (83.0%). Domain-specific accuracies are particularly impressive, with 96.1% in Mental Health, 94.6% in Epidemiology, and 94.6% in Dentistry, highlighting the model's proficiency in handling complex, reasoning-intensive medical queries.
Conclusions:
The model shows promising applications in clinical decision support, interdisciplinary collaboration, professional education, and medical research. While challenges remain in real-world integration and maintaining alignment with evolving medical knowledge, Yesil o1 Pro represents a significant advancement in AI-driven healthcare support. Future research will focus on validating the model's utility in clinical environments and developing strategies for seamless healthcare system integration.
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.