@article {Wang2025.12.04.25341678,
	author = {Wang, Benlu and Schaefer, Elizabeth and Aguirre, Nicole and Huang, Juncheng and Li, Xiawei and Kolamuri, Santhi Raj and Ying, Lee and Li, Xinyue and Chao, Grace and Ang, Sheryl S. and Vallabhajosyula, Prashanth and Krumholz, Harlan and Gibbs, Karen E. and Pai, Sara I. and Schneider, Eric B. and Cohan, Arman and Ong, Chin Siang},
	title = {Hippocrates-o1: A Guideline-Aware, Orchestrated, Self-Refining Protocol for Specialty-Specific Clinical Reasoning},
	elocation-id = {2025.12.04.25341678},
	year = {2025},
	doi = {10.64898/2025.12.04.25341678},
	publisher = {Cold Spring Harbor Laboratory Press},
	abstract = {Background Clinical decision support requires language models that provide guideline-aligned, context-aware reasoning with clear justification. Many existing benchmarks emphasize multiple-choice or short-form question answering and mainly capture factual recall rather than longitudinal clinical reasoning from extended clinical notes. Hippocrates-o1 is a family of domain-tailored clinical reasoning pipelines that combine structured prompts, guideline-informed retrieval, and iterative self-refinement across oncology, general surgery, and vascular surgery.Methods Real-world head and neck cancer cases were drawn from the MIMIC-IV-Note database, with a subset (n=20) randomly selected for detailed annotation. Six physicians adjudicated treatment phase and intent using structured criteria and rated model outputs. For each case, we generated outputs using both a general-purpose baseline model (VanillaLLM) and our oncology-specific reasoning model, Hippocrates-Karkinos-o1. Experts evaluated the outputs across five dimensions on a scale of 1 to 5: Clinical Knowledge Application, Contextual Understanding, Reasoning Transparency, Chain-of-Thought Quality, and Hallucination Audit. Overall Reasoning was the mean of domain scores. To explore whether the approach could extend beyond oncology, we also processed inguinal hernia and aortic aneurysm cases through Hippocrates-Chirurgos-o1 and Hippocrates-Angios-o1 domain adaptations.Results Across paired ratings, Hippocrates-Karkinos-o1 improved Overall Reasoning from 3.40{\textpm}0.90 to 4.00{\textpm}0.73 (p\&lt;0.001). Domain scores increased for Clinical Knowledge Application (2.87{\textpm}1.20 to 3.70{\textpm}1.03), Contextual Understanding (3.48{\textpm}0.95 to 3.98{\textpm}0.95), Hallucination Audit (3.90{\textpm}1.32 to 4.74{\textpm}0.76), Reasoning Transparency (3.45{\textpm}1.02 to 3.86{\textpm}0.87), and Chain-of-Thought Quality (3.32{\textpm}1.04 to 3.69{\textpm}1.00), all p<=0.001. Surgical and vascular adaptations showed parallel qualitative improvements.Conclusions The Hippocrates-o1 protocol improved reasoning fidelity, guideline alignment, and factual grounding relative to a general-purpose model and generalized across oncology, surgery, and vascular care. Orchestrated retrieval and self-refinement provide a reproducible template for evaluating and enhancing clinical reasoning in medical AI.Competing Interest StatementThe authors have declared no competing interest.Funding StatementThis study was funded by the Yale University Artificial Intelligence Initiatives and the Office of the Provost through the Envisioning Artificial Intelligence at Yale Seed Grants program, awarded for the project "SurgiMind: Enhancing Surgical Practice through Advanced Large Language Model Reasoning".Author DeclarationsI confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.YesThe details of the IRB/oversight body that provided approval or exemption for the research described are given below:Ethics committee/IRB of Yale University waived ethical approval for this work.I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.YesI understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).YesI have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.YesAll data analyzed in this study are available through controlled-access repositories and from the authors upon reasonable request, subject to applicable data use agreements.},
	URL = {https://www.medrxiv.org/content/early/2025/12/05/2025.12.04.25341678},
	eprint = {https://www.medrxiv.org/content/early/2025/12/05/2025.12.04.25341678.full.pdf},
	journal = {medRxiv}
}