Chat et al. helps clinicians move from a patient question to traceable guideline passages, structured reasoning, and cited answers in one workflow.
Private beta for licensed medical professionals
We review requests from clinicians and clinical teams before granting access.
Responses are linked to specific guideline passages, so you can verify where information comes from.
Clinical guidelines are parsed into a knowledge graph that captures entities, thresholds, drug classes, and decision pathways.
The system retrieves relevant sections based on your query context, reducing time spent searching through documents.
Guidelines evolve frequently. In busy clinical settings, locating the right passage across PDFs and apps takes time that isn't always available.
Protocols, updates, and reference tables are spread across multiple documents and platforms.
Clinical decisions often can't wait for lengthy searches and cross-referencing.
New guidelines and consensus statements are published regularly and can be easy to miss.
Risk calculators, tables, and figures often live in separate applications.
Not every decision can wait for a colleague's input, especially during off-hours or high-volume shifts.
Translating guideline recommendations into structured notes requires additional steps.
We evaluated Chat et al. alongside other AI systems on the 2025 SSM exam to understand retrieval and reasoning accuracy.
Percentage of questions answered correctly
Methodology
All systems were tested on the complete 2025 SSM exam question set under identical conditions. Score = correct answers / total questions.
| Model | Pass Rate |
|---|---|
| Chat et al. | 89% |
| OpenEvidence | 88% |
| ChatGPT | 82% |
| Gemini | 74% |
A retrieval-augmented pipeline that combines semantic search with structured clinical knowledge.
Clinical guidelines (e.g., ESC, AHA) are parsed from source documents, preserving structure, tables, and figures.
Entities—conditions, drugs, thresholds, contraindications—are extracted and linked into a graph that captures clinical relationships.
Text passages are embedded and stored in a vector database for semantic similarity search.
Given a query, the system retrieves relevant passages from both the vector index and the knowledge graph.
A language model synthesizes retrieved content into a coherent answer, citing source passages.
How we approach clinical decision support.
The system is designed as a reasoning aid for clinicians, not an autonomous decision-maker. Final judgment remains with you.
Guidelines are periodically re-ingested to reflect updates and new evidence as they become available.
We acknowledge that retrieval may miss relevant context and that LLM-generated text can contain errors. Always verify critical information.
Queries are not used for model training. Conversations are encrypted and handled according to privacy best practices.
Request access to the private beta. Approved clinicians are routed directly to sign in.
We review requests from clinicians and clinical teams before granting access.