How OpenEvidence operates as a clinical decision-support platform for physicians

OpenEvidence is an AI-powered medical search engine built for licensed healthcare professionals. Access requires a verified National Provider Identifier (NPI) number; patients, students without clinical licences, and non-U.S. researchers cannot use it. The platform was developed by Harvard and MIT researchers through the Mayo Clinic Platform Accelerate program and has grown to serve over 10,000 hospitals and medical centres across the United States.

The core interaction is a search bar. A physician types a natural-language clinical question, such as alternatives to metformin for a patient with GI intolerance, and receives a synthesised answer grounded in peer-reviewed literature within seconds. Every response includes inline citations linking to the source papers or guidelines. The system draws from licensed content partnerships with the New England Journal of Medicine (NEJM), the JAMA Network, the National Comprehensive Cancer Network (NCCN), Cochrane Systematic Reviews, PubMed, the FDA, and the CDC.

OpenEvidence also offers a Visits feature that integrates evidence surfacing into the patient encounter itself, including transcription and note-drafting assistance. This is a clinical workflow tool; it is not designed for literature synthesis, hypothesis generation, or research-phase reasoning.

How BioSkepsis retrieves and reasons over biomedical literature for researchers

BioSkepsis retrieval is weighted by Gene Ontology terms, MeSH descriptors, gene symbols, and pathway relationships. A query about AMPK activation and its downstream effects on hepatic lipogenesis returns papers linked by the biological concepts involved, not just papers whose abstracts contain matching keywords. This biology-native retrieval layer is what separates BioSkepsis from both general-purpose LLMs and clinical search tools that treat biomedical papers as undifferentiated text.

Answers are grounded in full text including methods, controls, and supplementary data. Every claim links back to the exact passage in the retrieved paper. When evidence is insufficient, BioSkepsis declines to answer rather than generating a plausible-sounding response. The research landscape graph classifies papers by structural role (Foundational, Hub, Bridge, and Novel) and draws on Semantic Scholar's 214M+ corpus for landscape expansion.

BioSkepsis is open to anyone. There is no credentialing gate, no NPI requirement, no geographic restriction. PhD students, postdocs, principal investigators, industry researchers, and independent scientists all use the same platform.

Feature comparison: BioSkepsis vs OpenEvidence for biomedical professionals

Corpus and retrieval: clinical guidelines vs full-spectrum life-science literature

The fundamental architectural difference is what each tool indexes and how it finds relevant papers.

OpenEvidence draws from licensed partnerships with specific high-impact publishers. Content from NEJM, JAMA, NCCN, and Cochrane is available in full text, including figures, tables, and multimedia. Additional sources include PubMed, the FDA, and the CDC. This is a curated clinical corpus: deep within the boundaries of clinical medicine, but not designed to cover agricultural science, ecology, veterinary research, or the broader life sciences.

BioSkepsis indexes 40M+ curated biomedical and life-science papers spanning biology, medicine, pharmaceuticals, biotechnology, agricultural and food sciences, veterinary science, and environmental sciences. Retrieval is weighted by Gene Ontology terms, MeSH descriptors, and gene symbols, meaning a query about a specific kinase or signalling pathway returns papers linked by biological function, not just keyword overlap. The research landscape graph extends into Semantic Scholar's 214M+ corpus for discovery of papers outside the curated biomedical index.

CME credits, certifications, and professional development

OpenEvidence launched free Continuing Medical Education credits in April 2025. Verified physicians earn AMA PRA Category 1 Credits by reviewing their past OpenEvidence queries, completing short learning assessments, and receiving official transcripts. This is a significant retention mechanism: U.S. physicians are legally required to accumulate CME credits to maintain their medical licences, and OpenEvidence converts routine clinical queries into credit-earning activity without additional workflow.

OpenEvidence also functions as an exam-preparation tool. Its AI system was the first to score 100% on the United States Medical Licensing Examination (USMLE), and the platform generates practice questions with detailed, referenced explanations that medical students and residents use for board preparation.

BioSkepsis does not offer CME credits, USMLE preparation, or any clinical certification programme. Researchers do not face a mandatory credentialing cycle equivalent to physician CME. The professional development pressures for researchers are different: publication output, grant competitiveness, methodological rigour, and staying current with an accelerating literature. BioSkepsis addresses these through its research feed, hypothesis generation, citation network analysis, and export workflows rather than through formal certification.

Who should use which tool in biomedical and life-science research

Using both OpenEvidence and BioSkepsis as a clinician-researcher

Many academic physicians and clinician-scientists operate in both modes: treating patients during clinical hours and running research programmes the rest of the time. The two tools cover different phases of this dual role.

In clinic: OpenEvidence for fast, guideline-grounded treatment decisions. A query about SGLT2 inhibitor selection in a diabetic patient with heart failure returns an answer optimised for a 30-second bedside read, with CME credit accruing passively.

In the lab or at the desk: BioSkepsis for deep literature synthesis. A query about the molecular mechanisms linking SGLT2 inhibition to cardiac remodelling returns a citation-grounded synthesis across dozens of full-text papers, with a landscape graph showing how the field is structured, which papers are foundational, and where the knowledge gaps are.

Grant writing: BioSkepsis generates testable hypotheses and maps the mechanistic rationale across published evidence. OpenEvidence does not offer hypothesis generation or grant-support features.

Reference management: BioSkepsis syncs directly to Zotero on all tiers. References discovered during research sessions flow into the same library used for manuscripts and grant applications.

Frequently asked questions