PurpleLab Expands Healthcare Data Access via Snowflake and Databricks
Healthcare analytics firm PurpleLab is expanding access to its real-world data by integrating its platform with both Databricks and Snowflake. The company combines data from medical claims, electronic medical records, and social determinants of health to enable more precise risk stratification and predictive modeling. This cross-platform approach highlights the trend of using specialized platforms for different stages of the data and AI lifecycle in regulated industries.
- Through the Snowflake and Databricks marketplaces, PurpleLab will offer access to its CLEAR Claims dataset and data on 7 million healthcare practitioners and 2 million healthcare organizations. This allows customers to sample the data directly within their cloud environments before purchasing. - A common architectural pattern for healthcare organizations is to use both platforms, with Snowflake housing structured claims data for business intelligence and SQL-based analytics, and Databricks handling more complex AI and machine learning workloads on unstructured data. This hybrid approach leverages the strengths of each platform but can increase operational complexity. - PurpleLab's core offering is its HealthNexus™ no-code analytics platform, which sits on top of a data warehouse containing over 50 billion medical and pharmaceutical claims. This database covers more than 330 million patient lives and 98% of U.S. payers. - The company, founded in 2016 by CEO Mark Brosso, enhances its claims data by integrating Social Determinants of Health (SDOH) attributes to provide a more comprehensive patient view. These non-medical factors include data related to housing stability, economic health, education, and social isolation. - Brosso previously founded Health Market Science in 1999, a company that also focused on proprietary healthcare databases and analytics, which he led to an acquisition in 2007. - For data engineers, the key distinction between the platforms lies in their data handling and processing capabilities. Databricks, built on open-source technologies like Spark, excels at processing large volumes of both structured and unstructured data in near real-time, while Snowflake is optimized for high-performance SQL queries on structured data in a relational format. - Both Snowflake and Databricks are HITRUST CSF certified, a key compliance requirement for handling sensitive healthcare data under HIPAA regulations. - This move allows PurpleLab to reduce the time it takes for clients to get from data access to insights, a process that could previously take weeks or months. The direct integration into existing cloud workflows eliminates significant data engineering and procurement friction.
