Customer Spotlight: Big Data Making a Big Impact in Healthcare and Life Sciences

Categories: Hadoop Use Case

In this Customer Spotlight, I’d like to emphasize some undeniably positive use cases for Big Data, by looking at some of the ways the healthcare and life sciences industries are innovating to benefit humankind. Here are just a few examples:

Mount Sinai School of Medicine has partnered with Cloudera’s own Jeff Hammerbacher to apply Big Data to better predict and understand disease processes and treatments. The Mount Sinai School of Medicine is a top medical school in the US, noted for innovation in biomedical research, clinical care delivery, and community services. With Cloudera’s Big Data technology and Jeff’s data science expertise, Mount Sinai is better equipped to develop solutions designed for high-performance, scalable data analysis and multi-scale measurements. For example, medical research and discovery areas in genotype, gene expression and organ health will benefit from these Big Data applications.

“We are at the cutting edge of disease prevention and treatment, and the work that we will do together will reshape the landscape of our field,” said Dennis S. Charney, MD, The Mount Sinai Medical Center.

Treato is applying large-scale digital and social media analysis to improve healthcare. is a consumer-oriented website that aggregates patient experiences from the internet and organizes them into usable insights for patients, physicians, and other healthcare professionals. This is a big deal because crawling the entire web for medicines, symptoms, side effects, and other health-related user generated content is difficult not only due to the sheer size of the web, but Treato also needs to process colloquial language combined with medical terminology and translate that into a “single version of truth.” Treato has aggregated and analyzed more than 1.1 billion online posts about over 11,000 medications and over 13,000 conditions from thousands of English language websites. The system can currently process 150-200 million user posts per day.

“It would have been impossible to accomplish Treato’s mission without a big data solution such as Hadoop,” explained Assaf Yardeni, head of R&D for Treato. “Treato is based on the concept of taking all the patient experiences already written and still being written each day, and aggregating and organizing them to expose meaningful insights. With the continuously growing number of pages and increasing volumes of health-related data on the web, Hadoop was the logical choice.”

RelayHealth, a subsidiary of McKesson, processes healthcare provider-to-payer interactions betwen 200,000 physicians, 2,000 hospitals, and 1,900 payers (health plans), according to a Forrester / Cloudera webinar. RelayHealth is in the business of expediting communications between these two groups to improve the patients’ experience and to ensure that healthcare providers get paid for their services efficiently, and they’ve turned to Hadoop to process those communications even faster. This ultimately saves customers money through better cash flow. In an era when our nation is struggling to provide affordable healthcare to our citizens, RelayHealth is adding a lot of value. RelayHealth’s Hadoop environment supports millions of transactions generated, thousands of files received, and over 150GB log data collected every single day.

“Healthcare is a very competitive, tight margin industry with increasing needs for compliance on data of massive scale,” said Marty Smith, Senior Director of Product Innovation, RelayHealth (McKesson). “RelayHealth processes millions of claims per day on Cloudera Enterprise, analyzing more than 1 million log files per day and integrating with multiple Oracle and IBM systems. As a result, we are able to assist our healthcare providers to get paid faster, improving their cost models and productivity.”

What are some other ways you’re seeing Big Data applied to benefit humankind? Share your thoughts, ideas, and examples here!

Karina Babcock is Cloudera’s Customer Programs & Marketing Manager.