Using Lakehouse to Fight Cancer: Ontada’s Journey to Establish a RWD Platform on Databricks Lakehouse
Ontada, a business under McKesson, is dedicated to transforming cancer treatment by leveraging real-world data (RWD), evidence generation, and technology solutions. In line with its mission, Ontada decided to migrate its enterprise data warehouse (EDW) from an on-premise Oracle database to Databricks Lakehouse.
This migration has provided Ontada with the ability to consume data from various sources, including structured and unstructured data from electronic health records (EHR) and genomics lab results. By leveraging Databricks Lakehouse, Ontada has significantly reduced the time required to gain insights from data, enabling faster decision-making processes.
Furthermore, the adoption of the Lakehouse architecture has allowed Ontada to eliminate data silos, ensuring that the full potential of RWD can be realized. From running traditional descriptive analytics to extracting biomarkers from unstructured data, Ontada can now leverage the power of the Lakehouse to drive meaningful insights and research.
During the session, several topics will be covered. Firstly, the best practices and lessons learned from the migration process from Oracle to Databricks will be discussed. This will provide valuable insights for organizations planning similar migrations.
The session will also focus on the importance of people, processes, and tools in expediting innovation while safeguarding patient information. Ontada will share its experience in using Unity Catalog to facilitate secure and efficient data access, ensuring compliance and privacy protection.
Additionally, the session will highlight how Ontada maximizes the potential of Databricks Lakehouse across various areas, from business intelligence (BI) analytics to genomics research. By consolidating all analytics on a single platform, Ontada achieves a unified and streamlined approach to data analysis and insights.
Finally, the session will explore the hyperscale abstraction of biomarkers from large unstructured data. Ontada will showcase how it reduces manual efforts by leveraging spaCy and John Snow Lab NLP libraries to extract biomarkers from medical notes, scanned documents, and faxed documents. This automated approach accelerates the biomarker extraction process, leading to improved efficiency and accuracy.
In summary, Ontada’s migration to Databricks Lakehouse has empowered the organization to leverage diverse data sources, eliminate data silos, and extract valuable insights from structured and unstructured data. Through the use of Unity Catalog and advanced NLP libraries, Ontada has expedited innovation while ensuring patient privacy and compliance.
