How the largest US healthcare dataset in Hadoop enables patient-level analytics in near real time

The need to find efficiencies in healthcare is becoming paramount as our society and the global population continue to grow and live longer. Navdeep Alam shares his experience and reviews current and emerging technologies in the marketplace that handle working with unbounded, de-identified patient datasets in the billions of rows in an efficient and scalable way.

As healthcare data becomes more digitized, the opportunity to leverage electronic medical records, prescription data, medical billings, hospital, and other healthcare datasets to help improve health outcomes and lower the cost of care for patients in near real time is becoming a possibility. However, processing terabytes and petabytes of de-identified healthcare data requires the application of complex and ever-changing business rules. This impacts the ability to generate near-real-time insights and conduct research studies that could potentially influence how patients are treated. Today, the analysis of databases of this magnitude can take days or even weeks of processing; to be more effective for improving patient care, researchers need to be able to run processes on demand, returning result sets instantaneously. Navdeep Alam shares his experience at IMS Health in realizing this opportunity to influence patient health outcomes in minutes to seconds and reviews current and emerging technologies in the marketplace that handle working with unbounded, de-identified patient datasets in the billions of rows in an efficient and scalable way.