Doctolib builds an AI consultation assistant on Azure OpenAI Service and Mistral Large that summarises consultations in 15 seconds
Doctolib· FranceAzure OpenAI · Mistral LargeDoctolib, a French eHealth company, built a consultation assistant using Azure OpenAI Service (GPT-4o) and Mistral Large on Azure, fine-tuned on proprietary French-language data. It transcribes consultations in real time and produces a structured summary within 15 seconds, which the practitioner reviews and validates. Audio and transcription are destroyed soon after validation. It was beta-tested with over 400 volunteer health professionals.
Overview
Doctolib, a French eHealth company, built a consultation assistant using Azure OpenAI Service (GPT-4o) and Mistral Large on Azure, fine-tuned on proprietary French-language data. It transcribes consultations in real time and produces a structured summary within 15 seconds, which the practitioner reviews and validates. Audio and transcription are destroyed soon after validation. It was beta-tested with over 400 volunteer health professionals.
This entry has 13 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
Taking notes on the computer for the patient file and putting together the medical record is time-consuming for practitioners, who Doctolib wants to be able to spend more time looking at their patients rather than their computer screen.
The solution
Doctolib built a Consultation Assistant that transcribes the consultation in real time and turns it into a structured summary within 15 seconds. Practitioners review, edit and validate the information before it is integrated into the patient's file or shared with the patient. The assistant is based on a series of models including GPT-4o on Azure OpenAI Service, chained with Mistral Large on Azure and built on Azure AI Studio; the models were fine-tuned on proprietary data reannotated in-house in native French. Both the audio and the transcription are destroyed soon after the summary is checked by the practitioner.
Reported business value
According to the Microsoft customer story, consultations are summarised in 15 seconds, aiming to let practitioners spend twice as much time interacting with their patients, and physicians report a reduced mental workload. The assistant was beta-tested with over 400 voluntary health professionals over thousands of consultations per week, with extremely positive feedback.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other healthcare entries in the register.
Less paperwork, more time for people: Azure OpenAI at Landsberg Hospital
Klinikum Landsberg am Lech, a German acute-care hospital, deployed an AI language solution built on Azure OpenAI with partner Pexon Consulting that transcribes doctor-patient consultations in real time via tablet, recognizes medical terms, structures the content, and transfers it directly into the hospital information system.
Novo Nordisk builds AI drug discovery platform on Azure with Microsoft Research
Novo Nordisk partnered with Microsoft Research to build an AI platform on Azure AI and data stacks spanning regulatory affairs, early research, drug discovery and trial design, using Azure OpenAI Service, Azure Cosmos DB and Azure Kubernetes Service, with Power BI and Power Apps for collaboration. The platform includes a copilot for researchers, shared reasoning-chain templates, and governance/auditing of how data and models are used. The teams published early results on predictive AI models for cardiovascular disease risk detection, including an algorithm that Novo Nordisk says predicts patients' cardiovascular risk better than the best clinical standards, drawing on more than 100 years of insulin research data.
Novo Nordisk· DenmarkAzure OpenAI Service · Azure Cosmos DB · Azure Kubernetes Service +2BAYADA Builds a Unified, AI-Ready Platform for Compassionate Care
BAYADA Home Health Care is consolidating three separate legacy data platforms (multiple practice management systems, an on-prem ODS, and Snowflake) and 65+ enterprise data sources into a single Databricks Lakehouse under its Data Modernization program, using medallion tiers, Lakeflow Jobs, Asset Bundles, and Unity Catalog governance. As part of the migration, BAYADA uses an LLM-powered code converter and Databricks Assistant to automate SQL and stored-procedure translation, and applies a machine learning-based data mastering accelerator to create golden Client, Payor, Candidate, and Referrer records. BAYADA reports roughly 30% better workload performance and cost efficiency versus its prior Snowflake environment, and is laying a governed foundation for AI agents supporting payroll validation, compliance monitoring, and operational insights, separately from its roadmap for AI-assisted chart review and risk prediction.
BAYADA Home Health CareDatabricks SQL · Lakeflow Jobs · Unity Catalog +1
Heidi Health fine-tunes NVIDIA Parakeet/Nemotron ASR, cutting clinical transcription latency 75% and costs 64%
Heidi Health, which processes 2.4 million clinical consultations weekly across 110 languages, fine-tuned the open NVIDIA Parakeet V2 speech recognition model on 1,500 hours of curated clinical audio using the NVIDIA NeMo framework and 8x H100 GPUs, replacing its closed-source vendor ASR. The in-house Nemotron-based ASR stack cut end-to-end transcription latency from about 3.0 seconds to 0.7 seconds (75%+ improvement), reduced word error rate from 13% to 9.4%, and cut operating costs by 64% by eliminating per-minute API pricing, while giving Heidi full ownership of model weights for data sovereignty.
Was this helpful?
Your feedback helps us improve our use case database