MedOrqis: An Open-Source Medical AI Skills Ecosystem for Clinical Agents

Описание и применение

MedOrqis – открытая экосистема медицинских навыков, обеспечивающая детерминированные расчёты и защиту от галлюцинаций в LLM‑поддержке клинических решений.

Задача

Deploying large language models in healthcare risks hallucinations, calculation errors, lack of deterministic guardrails, and non-reproducible outputs.

Результат

MedOrqis delivers deterministic, zero-token clinical calculations and safety guardrails, reducing hallucinations and ensuring reproducible, evidence-grounded outputs for clinical AI assistants.

Рабочий процесс

• 1. Install MedOrqis via CLI: npx skills add seotarek/MedOrqis
• 2. Import desired calculator, e.g., calculate_egfr_ckd_epi
• 3. Call the function with patient parameters
• 4. Receive deterministic result and safety-validated output
• 5. Optionally integrate with EHR via FHIR/HL7 schemas

Доказательства

Deploying Large Language Models in healthcare and clinical decision support comes with immense challenges: hallucinations, calculation errors, lack of deterministic guardrails, and non-reproducible outputs.

Источник

MedOrqis is an open-source, evidence-grounded, cross-platform ecosystem of 24 specialized clinical AI skills, 12 deterministic zero-token clinical calculators & safety engines, and multi-platform adapters (Skills CLI, Claude Code, Gemini CLI, Model Context Protocol, and OpenAI).

Источник

Built with an evidence-first, patient-safety-first architecture, MedOrqis eliminates medical hallucination risks in high-stakes clinical calculations by executing arithmetic, unit conversions, PHI scrubbing, negation parsing, and drug interaction screenings through a local, deterministic Python core with zero LLM API token overhead.

Источник