Patient Similarity Analytics for Personalized Healthcare

Big Data Evangelist, IBM

One of my favorite activities is exploring how big data can make people's lives better. High-quality, affordable, universally available healthcare is fundamental to that equation, and big data clearly has a strong role to play.

In late January 2013, I'll be co-presenting with Jianying Hu, IBM manager of Healthcare Analytics Research, at Personalized Medicine World Conference 2013 in Mountain View, Calif. We plan to discuss an important new IBM-developed data-driven decision support technology to personalize healthcare delivery, improve patient outcomes, and lower operational costs.

The innovative new technology is patient similarity analytics. It helps healthcare providers and payers answer the following critical question:

From historical data, which other types of patients were similar to a given patient – in characteristics, treatments, and outcomes – for the purpose of identifying the most appropriate physician and treatment plan for a particular condition faced by this specific patient?

Incorporated into the recently released IBM Patient Care and Insights solution, patient similarity analytics works as follows:

·   Analyzes aggregated demographic, social, clinical and financial factors along with unstructured data such as physicians’ notes

·   Factors the specific health history of each individual patient into the creation of a personalized healthcare delivery plan.

·   Enables healthcare professionals to examine thousands of patient characteristics at once to generate personalized treatment plans.

·   Identifies other patients with similar clinical characteristics to see what treatments were most effective or what complications they may have encountered.

·   Supports patient-physician matching so an individual is paired with a doctor that is optimal for a specific condition.

·   Allows healthcare professionals to better tap into the collective memory of the care delivery system to uncover new levels of tailored insight or "early identifiers" from historical/long term patient data

The tsunami of electronic healthcare record data powering patient similarity analytics flows from the care delivery network of healthcare providers and payers. In most real-world usage scenarios, the volumes of data involved, the variety of data sources, and the time-criticality of the analyses will push patient similarity analytics into big-data territory in no time.

Not just that, but the need for intensive ad-hoc queries, predictive analysis, patient stratification, and visual cohort refinement on patient data sets in excess of 10,000 features will create the need for massively parallel computation fabrics that only big data platforms can provide.

Also, the analytics pipeline for calculating customized similarity patterns, with learned context and endpoint-specific distance metric tailored to specific purpose (outcome, diagnosis, utilization, etc.) will require some high-powered computational muscle.

In our presentation, Jianying and I plan to discuss the application of patient similarity analytics to treatment personalization. We will outline the decision support scenarios that similarity analytics supports at the point of delivery. We will also describe how the technology factors the specific health history of each individual patient into the creation of a personalized healthcare delivery plan.

We hope to see you there.

Follow James on Twitter: @jameskobielus