United StatesHealthcare and life sciences2024 – ongoingOntada (McKesson)
ON.Genuity platform to extract data from oncology documents
Ontada uses Azure OpenAI to read 150 million oncology documents and cuts time to market to one week
Problem
Ontada needed to analyze about 150 million unstructured oncology documents. Manual review was slow, error-prone and too costly.
Approach
It built the ON.Genuity platform on Azure AI Foundry and the Azure OpenAI Batch API. Language models target nearly 100 oncology data elements, with Azure Databricks and Document Intelligence handling the data.
Results
Takeaway
Ontada reports that the 150 million documents were processed in three weeks. Its language models extracted targeted data elements from unstructured records.
Categories
- Size
- Large enterprise
- Industry
- Healthcare and life sciences
- Business function
- IT and R&DInternal work and knowledge management
- Innovation type
- Product and service innovation
- AI technology
- Generative AI
- Adoption
- Co-developed with a partner
- Evidence
- Vendor's case study
Sources
Source summaries
Microsoft explains how Ontada mines unstructured cancer records with Azure OpenAI. It gives speed and volume figures.
Full details are in the original sources.
