Clouds can be found filled with data more than rain these days. Using systems from Tableau Software and Google Cloud Platform (GCP), the Colorado Center for Personalized Medicine (CCPM), is analyzing patient data to predict disease risk and develop targeted treatments based on an individual’s health history. The CCPM is a partnership of the University of Colorado Denver, UCHealth, Children’s Hospital Colorado, and CU Medicine.
The research examines the genetic makeup and health history of thousands of patients to reveal patterns showing how people with certain genetic profiles tend to get particular diseases and whether they can benefit from specific treatments. To address those concerns, CCPM relies on Health Data Compass, CCPM’s enterprise health data warehouse. Health Data Compass integrates patient genomic data from CCPM and electronic health records from UCHealth, Children’s Hospital Colorado, and CU Medicine, including external records such as insurance claims, public health records, and environmental data. Eventually, it will encompass data from social media, wearable devices, and more.
Health Data Compass previously used a traditional on-premises system to store and analyze data. But that approach proved costly to maintain and didn’t scale for the center’s current analytics needs or their projected growth. Following a comprehensive six-month pilot project, Health Data Compass migrated to the GCP and Tableau. Together, these partners can handle massive data sets and powerful visual data analyses while costing less and allowing for easy scalability as CCPM grows. Significant to CCPM’s decision was the ability of GCP, including Google BigQuery, to support HIPAA compliance per CCPM’s requirements.
Drilling down into genomic data
Health Data Compass uploads data from multiple sources to Google Cloud Storage, a less expensive and more scalable storage venue than Health Data Compass’s on-site storage. From Google Cloud Storage, data is routed to Google Genomics and Google BigQuery, where a wide range of analytics can be performed.
Google BigQuery provided an unexpected benefit for one of Health Data Compass’s key services: probabilistic record linkage algorithms. Information about patients comes from multiple sources, so Health Data Compass needs to ensure that records aren’t duplicated. For example, it must determine whether ‘Bobby Peterson’ treated as a youth at Children’s Hospital Colorado is the same as ‘Roberta Peterson’ treated as an adult years later at UCHealth. Compass holds records for nearly 6 million patients, so this algorithm requires tremendous processing power. Health Data Compass’s original on-premises infrastructure took eight hours to complete the job. With Google BigQuery, it is completed in 15 minutes at a fraction of the cost.
Health Data Compass is developing tools to drill deeper into this data to quickly find answers. It uses Tableau’s self-service visual analytics platform with optimized connectivity to Google BigQuery for live analysis directly against the data in Google BigQuery. Tableau enables role-based dashboards for clinicians and researchers who are not data scientists to get useful insights from the data in a governed and secure data environment. Health Data Compass also deployed their Tableau implementation in the cloud on Google Compute Engine.
Faster and better answers at less cost
Health Data Compass successfully completed its comprehensive pilot project using Google Cloud Platform and expects to capture considerable benefits when it goes into full production this year. Analysts can perform queries much faster with Google BigQuery than with the previous solution. As a result, they can iterate alternative data queries with clinicians and researchers to extract complex concepts. In addition, Health Data Compass expects to dramatically cut operating costs including software, hardware, maintenance and support.
With Google Cloud Platform, Health Data Compass scales quickly without having to add hardware. It can also more easily integrate data from new sources, because it doesn’t have to contend with complex issues such as opening up ports and firewalls and setting up FTP servers. In addition to the hospitals that University of Colorado partners with, such as UCHealth and Children’s Hospital Colorado, Health Data Compass also pulls in state public health department data, weather data, insurance claims data, and data from other sources.