clinical_documentation · healthcare · workflow
Key Learnings to Elevate the Quality of Doctolib's AI-powered consultation assistant
Doctolib faced a 'chicken and egg' dilemma building their AI consultation assistant: effective AI requires user feedback, but meaningful feedback requires a reasonably functional AI that earns user engagement.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Speech-to-text transcription
Speech recognition converts consultation audio into text.
Tools used
large language model (LLM)speech recognitionICD-10
Outcome
The Consultation Assistant launched to widespread adoption with overwhelmingly positive feedback exceeding all expectations, following over a year of continuous improvement with beta testers and medical experts.
What failed first
Commonly used NLP evaluation metrics — ROUGE, BLEU, and BERT scores — proved less effective than expected at correlating with actual summary quality and were discarded.
Results
Running sinceLast fall
Grounding & classification
Source type: technical build writeup
23 fields verified against source quotes.
data extractionspeech to textsummarizationcall recordingclinical notebuilder submittedhuman review describednamed customerproduction runtime claimedtools describedworkflow describedhealthcareemployee productivitytechnical build writeupclinical documentationmedical records processingai draft human approvaldocument to record