Clinical Data Mining

The nontrivial extraction of implicit, previously unknown, and potentially useful information from data…A process by which a clinical database is used to describe mathematically the likelihood of outcome events, given a set of variables on a new patient.

Definition and purpose of data mining

January 16, 2013 – In Medinnovation blog,  I’ve been writing about data mining and health reform since 2007. I’m now about to write a book on  Electronic Health Records and Data Mining.  One goes with another.  Data miners extract their information from EHRs.  There is nothing trivial about data mining,  it extracts useful  clinical information, to establish what works best and what has the best outcomes at lower costs.

In March 2007,  I wrote an article in Health Leaders Media,  “Data Mining, Predictive Modeling, and Innovation: Keys to U.S. Health Reform,”  In that piece, I noted these kinds of data mining.

·         Medicare data mining

·         Pharmaceutical data mining

·         Printed word data mining

·         Health plan data mining

The underlying purpose behind  much of this data mining is to establish a rational basis for what works best and who gets paid for what.

Stephen Baker, in a 2007 book, Numerati,”explained whydata mining is so prevalent.

“The world is buried in data, great banks and drifts of the stuff. In recent years, a new technology has emerged – computer programs that will drill through it all to pick out patterns and trends – information that may be useful to marketers, employers, doctors, matchmakers or national security analysts. Such programs are extraordinarily sophisticated, and their creators need to be very clever indeed. A doctorate in math or computer science is pretty much required. These whizzes are called the ‘Numerati,’ Using ‘data mining,’ they can seek out veins of useful ore in the mounds of facts that computers accumulate every day.”

But in health care, the question arises: How much data and from what sources?   It should surprise no one that the UnitedHealthGroup, Inc, America’s largest health insurer,  and the Mayo Clinic, with 5 million computerized clinical records,  have decided to collaborate to draw upon clinical claims for 109 million people and in-depth Mayo records to establish what constitutes “best outcomes for patients at lower costs.”  The effort, called Optum Labs, will be part of UnitedHealth’s health service arm.  As David Brailer, MD,  President George Bush’s national HIT coordinator ,  observed of the United-Mayo effort,”It’s a sign of the times. Data has moved center stage, and now it’s time for it to show what it can do.”

Tweet: UnitedHealth and Mayo Clinic will mine claims data from 109 million people and 5 million  Mayo clinical records to see what works best.