Ontada Streamlines Oncology Data Processing for Better Patient Insights
Ontada, a McKesson business specializing in oncology technology and real-world data, partnered with Microsoft to process over 150 million unstructured oncology document components using Azure AI and Azure OpenAI Service. The collaboration addresses the significant challenge that 80% of vital healthcare data remains unstructured and often goes unanalyzed, hindering patient care improvements. Ontada's data science team deployed Large Language Models (LLMs) via Azure OpenAI Service's Batch API, targeting nearly 100 critical data elements across 39 cancer types. The solution leverages Microsoft's cloud resources to extract clinical data from multiple sources, enhancing data quality, accuracy, and the ability to visualize entire patient journeys. The ON. Genuity platform integrates proprietary EHR data (iKnowMed) and scalable AI, producing robust datasets for informing research, clinical decision-making, and improving oncology outcomes. This initiative enables healthcare providers to access more comprehensive and actionable insights, supporting personalized treatment plans and advancing oncology care quality. With improved real-world data generation, Ontada helps accelerate oncology innovation and research for life sciences partners.
- Organization
- Ontada
- Industry
- Healthcare
- Location
- United States
- Published
- October 2024
Reported outcomes
Strategic outcomes
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Ontada
- Provider
- Microsoft
- Maturity
- Scaled Production
- Linked source
- ontada.com
Significantly improved ability to analyze oncology data at scale
Primary read
Use case focus
Showing 3 of 3
- 1Automated Extraction of Clinical Oncology Data from Unstructured Documents
- 2Personalized Treatment Insights from Aggregated Oncology Data
- 3Scalable Oncology Real-World Data Generation with AI
- Processing and making sense of 150 million+ unstructured oncology data components.
- Vast majority (80%) of critical clinical data is unstructured, leading to underutilization (97% unused).
- Difficulties in extracting meaningful, actionable insights for treatment planning and research.
- Need for higher data quality and scalability in real-world oncology data use.
- Deployed Azure AI and Azure OpenAI Service (Batch API) for large-scale unstructured data processing.
- Applied LLMs to extract almost 100 critical data elements across 39 cancer types from clinical notes and EHRs.
- Integrated ON.Genuity platform with proprietary iKnowMed EHR, producing structured, high-quality real-world data.
- Leveraged scalable Microsoft cloud computing to accelerate data extraction and processing.
- Significantly improved ability to analyze oncology data at scale.
- Enhanced data accuracy and quality, supporting a richer view of patient journeys.
- Provided actionable clinical insights, aiding personalized treatments and advancing research.
- Strengthened capacity for oncology innovation and collaboration with life sciences companies.
Architecture
Ontada deployed Azure AI and Azure OpenAI Service's Batch API to extract nearly 100 data elements from 150 million unstructured oncology documents, integrating outputs into their ON.Genuity platform. This system brings data from proprietary iKnowMed EHR, processes and structures it using AI, and generates actionable insights for clinicians and researchers.
Implementation partners1
Sources & evidence2
- Customer explicitly identified
- Deployment status explicitly supported
- Technical implementation details available
- Multiple corroborating sources available
The same organization appears in newer AI deployment evidence.
- Same organization re-documented as recently as 2025.
Measures whether this deployment's public evidence persists — not whether the system is still in production.
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Was this useful?
Community
Comments
No published comments yet.