Ontada, Microsoft, and Azure AI: Collaborating to Transform Real-Word Data Processing in Oncology

In this episode of Exploring Artificial Intelligence in Oncology, Wanmei Ou, PhD, the Vice President of Product, Clinical Decision Support, & Analytics Data Platform at Ontada, shares more about Ontada’s collaboration with Microsoft to transform unstructured oncology data with Azure OpenAI technology. Her discussion with Dr. Waqas Haque highlights how AI is transforming clinical workflows, reducing documentation burdens, and driving improved patient outcomes.

This episode is also available as a podcast. Click here to listen!

Addressing Data Challenges in Oncology

Dr. Ou describes the complex data landscape in oncology, emphasizing the limitations of unstructured data in electronic health records (EHRs). While this data provides key insights, it often misses critical information such as staging, histology, and treatment details, which are commonly documented in unstructured formats like physician notes, scanned documents, or faxes.

Ontada, a business unit of McKesson Corporation, supports thousands of oncology providers using its EHR platform to manage data for over 1.4 million patients annually. However, this generates a massive repository of unstructured documents—over 150 million—highlighting the need for advanced AI to extract and utilize valuable clinical insights efficiently.

Leveraging AI to Enhance Data Utilization

To tackle this challenge, Ontada has developed nearly 100 AI models to extract actionable information from unstructured documents. These models focus on extracting critical data points such as diagnosis dates, treatment plans, and surgical records. Each model undergoes rigorous validation using manually annotated datasets created by clinical nurses. By cross-validating these annotations with multiple reviewers and resolving discrepancies, Ontada ensures high-quality ground truth data for training and validating AI models.

Dr. Ou shares a significant success story where these AI models were deployed to streamline the submission of oncology data to the White House Cancer Moonshot Initiative. This effort, in collaboration with the US Oncology Network and Compass Oncology, led to a 98% data completion rate—well above the 90% threshold set by the Centers for Medicare & Medicaid Services (CMS). The AI-driven workflow not only reduced the burden on clinical staff but also demonstrated the potential of AI in enhancing data accuracy and operational efficiency.

Collaboration with Microsoft Azure AI for Large-Scale AI Deployment

Ontada’s partnership with Microsoft Azure AI is playing a pivotal role in scaling their data extraction efforts. Dr. Ou explains how they overcame throughput challenges in processing 150 million documents. By collaborating with Microsoft, Ontada utilized a new Azure AI Batch service, which significantly accelerated data processing—from an estimated six months to just three weeks. This innovative solution also reduced costs by 50%, enabling efficient large-scale deployment.

Future Directions for AI in Oncology

Looking ahead, Dr. Ou envisions more advanced applications of AI in oncology beyond data extraction. She highlights the potential of AI to synthesize multimodal data—integrating EHR records, imaging results, patient-reported outcomes, and sensor data—to provide personalized treatment recommendations. AI could also analyze real-time patient data, external literature, and payer policies to optimize treatment decisions by balancing efficacy, safety, and cost.

Another promising area is predictive analytics, where AI could identify at-risk patients and enable timely interventions to prevent complications. By leveraging unstructured data alongside structured records, clinicians can gain deeper insights into patient trajectories and deliver more proactive care.

Transforming Oncology Care

Dr. Ou’s insights underscore the transformative potential of AI in oncology. By addressing long-standing challenges in data management and improving workflows, AI is empowering clinicians to focus more on patient care while advancing research and innovation in cancer treatment. As AI technologies continue to evolve, they promise to further enhance precision medicine, streamline operations, and improve outcomes for oncology patients worldwide.

About the Speakers

Waqas Haque, MD, MPH, is a Hematology/Oncology Fellow at the University of Chicago. He recently completed his Internal Medicine Residency at New York University (NYU) in a Clinical Investigator Track. Dr. Haque has balanced his patient care work with a variety of research projects. During his fellowship training at the University of Chicago, he plans to further his work in innovative clinical trial design, value-based care delivery to cancer patients, and clinical investigation.

Wanmei Ou, PhD, is the Vice President of Product, Clinical Decision Support, & Analytics Data Platform at Ontada. She is committed to leveraging digital technology to achieve a sustainable healthcare system. Dr. Ou’s experience spans the full healthcare continuum from providers, payers, and life science companies, having led multiple enterprise digital initiatives transforming the use of data to enable precision medicine, adjudicate value-based reimbursement, and accelerate biomedical research.