Predictive Analytics of Multi-Dimensional Data Leads to Accurate & Personalized Treatment Recommendations for Patients and Lower Cost To Serve

Christos Tryfonas (VMware), Karthik Kannan (Cetas by VMware)
Average rating: **...
(2.00, 1 rating)

Healthcare industry generates 100’s of TBs of data in any given month and is the most regulated and documented. There is also the complex challenge of many silos of data (with different data formats) from a multiplicity of sources – Clinical data, Prescription data, Patient profiles, Treatment data, and more. Therefore the volume and variety of health related data are Big Data challenges.

Much of these data contain valuable insights into patient behavior, prescription trends, drug response patterns, clinical data findings, disease characteristics, insurance claims etc. If these are successfully mined, they can lead to successful more accurate treatment recommendations and will lower the cost to serve by observing macro trends while keeping the ability to personalize the treatment. In the healthcare industry, in particular, providing personalized patient care is partly about understanding what happened (history); the other part of increasing treatment effectiveness lies in knowing what’s going to happen – in other words, understanding patients’ responsiveness to different treatment options are crucial. Both of these have strong correlations with user demographics, doctor’s criteria for prescriptions and other characteristics with the ultimate goal to provide the best possible care at the lowest cost.

Hospitals, healthcare providers and insurance companies are looking for the following big data analytics solutions:

- Operational data analytics
- Claims data analytics: insurance providers want to understand patient behavior and match and compare patients in their network to predict their actions
- Clinical data analytics: The objective here is for various entities in the healthcare system to use this data to evaluate and understand which drug is useful for which patient and why.

Traditionally the industry has used standard statistical and Bayesian approaches for data modeling and predictive analytics. But these approaches fall short.

Given the Big Data business context, in order to use past data and predict future events, there needs to be sufficient technology that is not merely extrapolating events. Powerful machine learning algorithms in association with combinatorial and graph algorithms are imperative to make accurate predictions about patient responsiveness to different potential treatment options, based on cross-dimensional correlations of diverse sources of data, time-event correlations and recognizing patient response patterns that would not be identified or understood using standard statistical, AI or Bayesian techniques. Handling the scale and the complex relationships within the data requires purpose-built algorithms that are specially designed to handle the needs of personalized patient care & treatment.

In this session, we will talk about methods that will extract insights from large volumes of data from various sources and diverse types, machine learning and combinatorial algorithms that can effectively break-down and correlate key data, and predictive analytics techniques that can result in personalized recommendations.

Christos Tryfonas


Christos Tryfonas is CTO and Co-Founder of Cetas. A computer scientist, technologist and successful entrepreneur, he co-founded Cetas in 2010 with focus on driving the technology around the emerging area of analytics and Big Data. He has several years of experience as a computer scientist and architect in both academia and industry research labs, leading innovative projects ranging from information retrieval and large scale distributed systems, to storage networking, multimedia networking and network security.

In 2003, he co-founded Kazeon Systems, Inc. with focus on information classification, management, and retrieval where he was responsible for the technical leadership, the architecture and design of a complex distributed software product. Kazeon was acquired by EMC Corporation in September 2009. Prior to co-founding Kazeon Systems, Tryfonas was a Principal Member of Technical Staff at Sprint Advanced Technology Labs, where he was responsible for research and development in emerging networking and multimedia technologies. He contributed to several innovative Sprint services, and was part of the world-class IP research group at Sprint that provided accurate large-scale Internet measurements and analytics for worldwide IP capacity planning and traffic analysis to the Internet community. He has also worked at AT&T Bell Laboratories doing research and development in the area of traffic analysis. Christos holds several patents (issued and pending) in the areas of large-scale information classification, management, and retrieval, cloud services, distributed systems, congestion control in packet networks, and network transport of multimedia/video traffic.

Karthik Kannan

Cetas by VMware

Karthik Kannan is VP of Products at Cetas, a Big Data analytics start-up that was just acquired by VMware. At Cetas he is responsible for product strategy and building a partner ecosystem around cloud-based business analytics. Prior to Cetas, he was VP of Marketing and Business Development at Kazeon, a leading eDiscovery company which was acquired by EMC in 2009. Karthik’s background also includes leading product management at NetApp where he was responsible for setting product strategy for the information management, compliance and near line storage areas. He also worked in Goldman Sachs in the technology arm of the Investment Banking Division, as well as has held several technology consulting positions. Karthik holds an MS Degree in Industrial Engineering from Louisiana Tech University and an undergrad in Engineering Technology from BITS, Pilani (India).


For information on exhibition and sponsorship opportunities at the conference, contact Sharon Pierce at (203) 304-9476 or

For information on trade opportunities with O'Reilly conferences contact mediapartners

For media-related inquiries, contact Maureen Jennings at

View a complete list of Strata Rx contacts