Mistral 7B Instruct (FR)
Generation · Patient chat
Medical document summaries, contextual answers in patient chat.
- ↳
- OVH AI Labs · France · HDS v2
- ↳
- Open-source · Apache 2.0
AI at MDMC is an assistant, not a decision-maker. Here is exactly how, where and why.
No closed proprietary model in production. No call to OpenAI or Anthropic at patient runtime.
Generation · Patient chat
Medical document summaries, contextual answers in patient chat.
French medical NER
Extraction of medications, exams, diagnoses from prescriptions and scanned reports. Fine-tuned on Quaero / E3C.
Intent classification · Suggestions
Chatbot intent routing, lightweight CPU-friendly suggestions. Low latency.
Doctor decision support V2.5+
Clinical decision support with CE IIa marking (in progress). Always with human validation.
Metrics monitored continuously, drift detected, models re-evaluated quarterly.
Medical NER accuracy
85%
F1-score on Quaero 2024
Chat p95 latency
< 2 s
Mistral 7B streaming response
Alert false positives
< 15%
Internal target · monthly review
AI uptime
99.5%
SLO 24/7 OVH HDS v2
Indicative figures — pilot phase. Public reporting from Q4 2026 (AI Act high-risk register).
No AI suggestion replaces a healthcare professional's opinion. Summaries and alerts are indicative.
Models trained mostly on French adult data. Possible degraded performance on under-represented populations (pediatrics, regional languages, rare diseases).
You can disable any AI feature from Settings → AI & Privacy. 1 tap, immediate effect, no questions asked.
No automated decision alone producing legal effects. Systematic human validation for any impactful clinical suggestion.
You enable or disable each AI feature separately (summary, alerts, chat, NER). No bundled imposition.
Every AI suggestion shows its source (HAS guideline, patient document, indexed article) and confidence level (low / medium / high).
Settings → AI → Disable all. Immediate effect, past suggestions kept read-only, right to be forgotten respected.
Technical files available on request for partners, authorities and auditors.
HDS v2
AI and data hosted in certified OVH/Scaleway datacenters.
AI Act high-risk
Medical device classified high-risk · risk management + human oversight + post-market monitoring.
GDPR art.25
Privacy by design — minimization of data sent to inference, no conversation history persisted on the model side.
CE marking (in progress)
LNE-GMED · French Notified Body · CE marking Track C decision support, target Q4 2027.
Four non-negotiable principles, acknowledged limits and a contractual manifesto. AI is a tool. You remain the decision-maker.