Back to the blog

Medicine: revise for the EDN with France's public drug database

Health4 min read · 26 September 2026

The GetPack team

You’re preparing for the EDN (Épreuves Dématérialisées Nationales, France’s national computer-based medical licensing exams) or the ECOS (clinical skills stations), and a good chunk of what you’ll be asked about concerns medications: composition, indications, SMR, available generics. Rather than searching for this information on third-party sheets that are sometimes outdated, there’s a public, free, continuously updated source: the Base de données publique des médicaments (BDPM, France’s public drug database). Here’s what it actually contains, and how to use it to revise without falling into the trap of an AI that makes up a figure.

What the BDPM contains

The BDPM is run by the ANSM (Agence nationale de sécurité du médicament, France’s national medicines safety agency), in coordination with the HAS (Haute Autorité de Santé, the national health authority) and the UNCAM (Union nationale des caisses d’assurance maladie, the national health insurance body). It gives access to reference administrative and scientific data on medications marketed in France, or marketed at some point over the past three years. Specifically, it exposes:

  • Pharmaceutical specialties: each medication identified by its CIS code, with its active-substance composition, its presentations (boxes, dosages, prices, reimbursement rates).
  • HAS’s SMR and ASMR ratings. The SMR (Service Médical Rendu, “medical benefit rendered”) answers a precise question: does the medication have enough clinical value to be covered by national health insurance? The ASMR (Amélioration du Service Médical Rendu, “improvement in medical benefit”), rated from I to V, measures the therapeutic progress it brings compared with treatments already available — I for a major breakthrough, IV for a minor improvement, V for no improvement at all.
  • Generic groups. For each reference medication (the brand-name original, marked “R” in the directory), the database lists the associated generics (marked “G”), making it easy to see quickly what can be substituted for what.
  • Availability and supply tensions, with downloadable files on shortages and restocking. One point of caution: the BDPM doesn’t give a real-time snapshot of what’s actually available in pharmacies; it reflects a declared regulatory status, not the actual availability at a given moment.
  • MITM status (Médicament d’Intérêt Thérapeutique Majeur, “medication of major therapeutic interest”), which flags medications whose shortage would create a serious, immediate risk for patients.
  • Direct links to the SPC (Summary of Product Characteristics, known in France as the RCP) and the package leaflet, which remain the most complete reference documents on a given medication.

All of this data is published under an open-reuse framework, and a REST API allows structured access to it — which is exactly what the medicaments connector does, to give you this information directly within a conversation.

Turning this into a useful revision sheet

An effective EDN revision sheet on a medication or a therapeutic class benefits from following a simple structure, drawing on what the BDPM actually exposes:

  1. INN (International Nonproprietary Name) and therapeutic class, with the most common brand name(s).
  2. SMR and ASMR for the main indication — an item often tested, which clearly distinguishes the question “is this medication useful” (SMR) from “does it bring progress compared with existing options” (ASMR).
  3. Available generics in the group, useful for substitution and adherence questions.
  4. MITM status and recent shortages, a topic increasingly present in exams, especially in pharmacology and public health.
  5. Prescribing conditions as they appear in the marketing authorization (initial hospital prescription only, restricted to certain specialists, etc.).

The advantage of going through the BDPM rather than a sheet found online is that every piece of data is dated and sourced to the ANSM or the HAS: if an SMR rating changes, the database is updated, whereas a revision sheet shared among students can be several years old.

The limits you absolutely need to know

This point is central and should never be forgotten while revising: the BDPM, and any tool built on it, are meant for revision, not for deciding on a treatment for a real patient. No information drawn from this database replaces individualized medical advice, which accounts for a specific person’s history, comorbidities, and clinical context. A revision tool built on the BDPM must refuse any question about dosage or clinical management for a patient case, and refer the user to a doctor or pharmacist — this is also a way of respecting the boundary between a revision tool and a clinical decision-support tool, which falls under a different regulatory framework.

Another point of caution specific to using AI on this kind of content: if you ask for an automatically generated summary or sheet, always check that the SMR, ASMR, or shortage status cited actually matches what the BDPM shows at the time you’re revising, and cross-check it with your specialty college’s reference curriculum (the CNCI’s reference frameworks and those of the specialty colleges remain the authoritative source for exam content). An official database gives you verifiable facts; it doesn’t replace the curriculum and the knowledge hierarchy expected for the EDN.

Key takeaways

  • The BDPM (ANSM, with HAS ratings) gives composition, presentations, SMR/ASMR, generics, MITM status, and shortages for medications marketed in France.
  • SMR = sufficient clinical value for coverage; ASMR = therapeutic progress compared with existing options, rated from I (major) to V (none).
  • The availability shown is a regulatory status, not a real-time snapshot of pharmacy stock.
  • This database is for revising and understanding: never for deciding on a treatment for a real patient, and never as a replacement for your college’s curriculum.
  • Always cross-check an AI-generated sheet against the BDPM’s sourced, dated data before learning it.

To turn this data directly into sourced revision sheets, without ever inventing an SMR rating or a composition, the medicaments MCP queries the BDPM live and always cites its source and date.

Sources

  1. Base de données publique des médicaments — Glossaire (ANSM) · accessed 26 September 2026
  2. data.gouv.fr — Jeu de données Évaluation des médicaments (avis HAS, SMR/ASMR) · accessed 26 September 2026
  3. data.gouv.fr — API REST de la Base de données publique des médicaments · accessed 26 September 2026

Read the next article

Career26 September 2026

Internship pay and apprentice wages in 2026: the rules

Explainer26 September 2026

AI and academic integrity: what universities actually say

Tutorial26 September 2026

Installing a skill in Claude in 2 minutes

Thesis26 September 2026

Thesis: building your research question and outline with AI

Method26 September 2026

Building your exam study schedule with AI, the right way

Method26 September 2026

Revising with AI, honestly: active recall, Feynman, quizzes

Career26 September 2026

Choosing your apprenticeship with real employment data

Code27 September 2026

Learning to code in the age of AI: what you still need to know how to do yourself

Code27 September 2026

The one-page spec to write before you prompt an AI to code

Thesis27 September 2026

How to cite ChatGPT or Claude in a thesis: APA, MLA, ISO 690

Code27 September 2026

Claude Code for beginners: install, first launch, CLAUDE.md

AI news27 September 2026

Claude Opus 5.5: what really changes (and how to use it to study)

Analysis27 September 2026

The AI race: why some people are scared and others aren't

Code27 September 2026

Building your first MCP server, step by step

Code27 September 2026

Deploying your first site for free: Vercel, Netlify, Cloudflare Pages, or GitHub Pages

Explainer27 September 2026

AI detectors: are Turnitin, GPTZero and Compilatio reliable?

Code27 September 2026

Writing your own Claude skill: structure, SKILL.md, and a description that triggers

Career27 September 2026

France's national student-entrepreneur status (SNEE) and the PEPITE network, explained

Analysis27 September 2026

France in the AI race: Mistral, energy and talent

AI news27 September 2026

French Tech and AI: the French startups to know in 2026

Code27 September 2026

Git without fear: commit, branch, remote explained, then the commands that save you

Explainer27 September 2026

Chinese AI: DeepSeek, Qwen, Kimi… why Europe is wary

Health27 September 2026

AI in medical school: study for PASS, LAS and the EDN safely

Tools27 September 2026

Free AI for students: every offer and discount (2026)

Career27 September 2026

AI on an internship or apprenticeship: what’s allowed, what isn’t

Code27 September 2026

From IDE to ADE: coding with AI agents in 2026

Code27 September 2026

Reading an error without panicking: the anatomy of a stack trace (Python and JavaScript)

Tools27 September 2026

Best AI for students in 2026: the honest comparison

Tools27 September 2026

New AI models in 2026: which one should you study with?

Tools27 September 2026

French AI tools you’ve never heard of: Noota, Moshi, Vibe…

Analysis27 September 2026

Why AI is so expensive (and American AI even more so)

Code27 September 2026

How to prompt an AI coding tool well: the method that changes everything

Code27 September 2026

Securing a vibe-coded app: 7 mistakes to fix before you publish

Code27 September 2026

Slopsquatting: when AI recommends packages that don't exist

Weekly brief27 September 2026

AI news roundup: the week of September 21–27, 2026

Code27 September 2026

Vibe coding: what it actually means (and how not to mess it up)

AI news27 September 2026

Why Yann LeCun wants AMI: AI beyond LLMs

Tutorial26 September 2026

Connect an MCP connector to Claude without writing a line of code

Degrees26 September 2026

Choosing your program with real MonMaster and InserSup data

Method26 September 2026

APA 7, ISO 690, Vancouver: how to cite your sources properly

Explainer26 September 2026

ChatGPT's 'hidden codes' on TikTok: fact vs. fiction

Join GetPack

Already have an account? Sign in