(SPONSORED) Ketan Paranjape, Director of Personalized Medicine, Intel Corporation, discusses how visionary healthcare organizations around the world are using unstructured data and data analysis to deliver personalized medicine for their patients. Using innovative technologies and partnering with global leading-edge technology companies, these healthcare organizations are able to apply data analytics to unstructured data, as they meet their goals of creating a more efficient, cost-effective healthcare delivery system.

Paranjape’s role as Director of Personalized Medicine involves partnering with a virtual, cross-Intel team – from various business units, Sales and Marketing, Global Public Policy, Corporate A‑ airs and Intel Labs. The team’s goal is to help develop health IT strategies and devices for key healthcare customers, managing and driving results for multiple, simultaneous healthcare projects inside and outside of Intel that cover a wide range of topics from technology assessment to solution blueprints to public policy to innovation processes. In his 16 years at Intel, he has been part of products spanning the entire “Compute Continuum” from servers to embedded medical devices in roles encompassing architecture, design, strategy and marketing. He recently spent three years in Intel Research as the Chief of Staff and Technical Advisor to Intel Chief Technology Officer Justin Rattner.

Q: How can clinicians use distributed systems to turn unstructured patient data into meaningful clinical insights?

A: Much clinical information, such as age and gender, is available in structured formats. But often, the information that can tell doctors the most about a patient’s condition is in unstructured formats – patients’ free-text clinical notes (such as nursing notes, lab reports and radiology reports), which are generally difficult and time-consuming to analyze. A critical part of providing personalized medicine is being able to efficiently use this unstructured data to provide clinical insights. Intel has worked with many organizations around the world to help take this unstructured data and make it usable.

Leeds Teaching Hospitals in the U.K., identified an opportunity to be proactive in planning its care by analyzing the data it held on patients. By aggregating and making sense of the unstructured notes written on patients’ records, it was able to identify trends in injuries and conditions that patients present, and spot billing discrepancies that could be leaking funds. Leeds Teaching Hospitals worked with Intel, Ascribe, Two10degrees and Microsoft to run a pilot program that analyzed the patient data it held, so it could better understand how the Emergency Department operates. They found, among other things, that it could use the unstructured data in doctors’notes to identify peak times for certain injury categories and discrepancies in billing that could affect the funds available for future treatment.

China’s growing Regional Health Information Networks (RHINs) is beginning to show exciting opportunities for data analytics to help regional health authorities meet the Chinese Government’s ambitious health-improvement goals. With a registered population of approximately 3.1 million, the regional central city of Jinzhou decided to build city-based regional health data centers and cover the main business sectors of the RHIN by leveraging a resident health card. Data to be stored included relevant portions of resident health records, electronic medical records (EMRs), public health, integrated management and so on. UFIDA Medical and Health Information System Co., Ltd, the main constructor of the regional health data center of the healthy city strategy in Jinzhou, saw potential problems with regard to mass data and complicated and changeable data types, if a traditional relational database construct were to be used to build the regional health data center.

Mass data – The city-based regional health datacenter will store electronic health record, EMR and health management databases in a medium-sized city with a population of 3 million people, meaning its health data center will reach the petabyte level in 20 years. Traditional relational data has limitations for the realization of big data storage; a performance problem exists when more than 500GB data are stored in a “sheet” of a database table.

Complicated and changeable data types – The size of unstructured data generated by PACS images, ultrasound, pathologic analysis and other payloads vary greatly from hundreds of KB to hundreds of MB. Clinical EMR data are generally in standard XML fi le format of HL7 CDA. The fi le formats will keep evolving over time; and the complexity of medical and health business operations makes it difficult to develop unified data standards, bringing a new challenge to data access and exchange.

Intel and UFIDA Medical leveraged an Intel® Xeon® E5 processor-based platform and Intel® Distribution for Apache Hadoop software through repeated single business load tests, big data tests, optimizations and other technical means to successfully build a complete regional medical big data computing architecture. The architecture can meet performance requirements of high concurrency retrieval and real-time data analysis of mass data (with more than 100 million records).

The architecture based on Intel Xeon E5 processor-based platforms and Intel Distribution for Apache Hadoop provides a smart health cloud service platform for data processing, retrieval, analysis and other data services to meet Jinzhou’s healthy city goals.

For more information on how Intel helping to enable powerful and security mobile healthcare, please visit www.intel.com/healthcare/mobility.

Visit us at Booth #5845

About Intel: Intel Corporation’s vision is to deliver innovative computing technologies and solutions that will improve the quality of healthcare delivery and access while reducing unnecessary costs for billions of people worldwide. Intel teams with governments, healthcare organizations, and technology innovators worldwide to build tomorrow’s health IT tools and services.

We wanted to let you know about some of the key activities going on in the Intel Hospitality Suite during the three days of HIMSS14.

Our complimentary session will be digging deep into what’s new, such as from analytics, mobility, BYOx, cloud computing and more.  Click here to browse and register for the sessions that peak your interest.
 
The Intel Hospitality Suite
Room 340C, Convention Center
Suite 340C is located on Level III which can be accessed by using the West E/F Lobby escalator or elevator (on the main concourse).  The Suite is located at the North end.