Big Data for Healthcare: Why are we collecting all this data?

Big Data for Healthcare: Why are we collecting all this data?

Moving Into Uncharted Big Data Territory

Sarianne Gruber MPH, MS
SG Healthcare Analytics LLC

The induction of electronic health records, the building of health information exchanges and moving big data to the cloud seemed unconceivable for most.  And for many the words healthcare technology, data and analytics strike a sense of etherealness.  All this time and investment in data and where it is leading us to?  The latest news in Health IT has started to present some optimistic signs for healthcare providers and hospitals and patients too validating why healthcare organizations have boosted up their resources and technology.

Breakthrough Knowledge of Disease

Just as our nation looked in awe of Neil Armstrong’s walk on the moon, the dream of space exploration became a reality. Today we are looking at huge volumes of digital data to extract knowledge and insights about disease and treatment. By huge, we mean a terabyte or even larger, moving towards a petabyte (a thousand terabytes) of data. Within less than year of the National Institutes of Health receiving $200 million in funding for the International 1000 Genomes Project, researchers were able to validate a scientific discovery related to Alzheimer’s disease.  This “big data” project is expected to contain the world’s largest set of data on human genetic variation, and aims to sequence the entire genome of 2,600 people from around the world. The data is supported by a cloud storage system hosted by Amazon Web Services.  A cloud up in sky?  Not exactly, the data is on hundreds of remote servers in off-site data centers.  With the genomic data publicly available to researchers on the cloud, a huge benefit is that information can be retrieved quickly and inexpensively. The AWS “big data cloud” is beginning to show signs of its true potential as biomedical data from genomics, imaging and electronic health records continues to grow. This past summer, Dr. Stephen Sherry, Chief of the National Center Biotechnology Information, was able to confirm a recent discovery of a rare genetic mutation that may offer protection against Alzheimer’s disease.   For 2013, NIH continues to promote innovative health informatics and in addition, seeks to hire a new Data Scientist.

It’s All About the Patient and Spend

The hospitals and the insurance companies are finally putting on their moon boots on and taking their first steps together into uncharted Big Data territory.  Last week, the Mayo Clinic and Optum, the health IT unit of UnitedHealth, announced they will share 5 million clinical records covering 15 years of medical treatments and claims data on 100 million patients going back 20 years. So far the Mayo-Optum “big data” project is the largest joint effort to fully understand the healthcare delivery system, with a focus on answer big healthcare questions on best practices, better patient care and affordable cost. Unlike other large healthcare organizations, Optum and the Mayo Clinic will publicly release all results to benefit patients everywhere.  Retrospective-longitudinal data tracks pre and post hospitalizations, and is pivotal for studying high cost conditions such as congestive heart failure. What is truly exciting is that such information story boards the patient care processes and disease triggers enabling researchers to understand why heart failure patients are readmitted.  Claims data tracks encounter-level activity such as what has been done to the patient and where have they gone for care, whereas clinical data is good for tracking the outcomes of those encounters  such as what is the condition of the patient and what has been the result of the encounters. Several research goals include finding optimal treatment protocols, studying variations in care and examining different patient care programs. Also high on the list is cost effectiveness of medical devices, Hepatitis C detection and understanding health disparities among the elderly.

Data Analytics: The Next Frontier.

“Landing a man on the moon and returning him safely to the earth” delivered by President John F. Kennedy in his Man on the Moon speech unprecedentedly challenged our nation to excel in aerospace technology because “in many ways [it] may hold the key to our future on earth.” Fifty years later, we are building healthcare databases and advanced analytics technology that will open the door for solutions to our healthcare delivery system.  On January 10, the Wall Street Journal reported that two New York University researchers could indeed use big data to reduce healthcare costs and improve outcomes.  Their study of 65,000 newly diagnosed type-2 diabetes patients matched with pharmacy and medical claims uncovered actionable patterns. One interesting finding revealed: People who start with a “lifestyle only” solution after diagnosis (no meds for up to six months) tend to have higher complication rates than those who go on a simple medication such as a Metformin, suggesting that delay may be costly. While some controlled studies suggest that lifestyle factors such as regular vigorous exercise may prevent the onset of diabetes, timely medication may be more effective after its onset than relying on lifestyle alone. Why are we collecting data? We needBig data and predictive analytics to ask the questions.  Professor Vasant Dhar and Jon Maguire both from Stern’s Center for Business Analytics have landed on the answers, leading the way for others to follow.  Data Odyssey 2013 is here.

 1. Anthony Brino, NIH makes big deal of big data 01/14/2013
2. Ken Murphy, 07/26/2012;
3. Bernie Monegain White House launches ‘big data’ initiative 03/29/2012
4. Ken Terry, Optum, Mayo Join Forces to Exploit Big Data 01/16/2013
5. Erin McCann, Mayo Clinic launches data-sharing lab 01/16/2013
6. Big Data and Predictive Analytics Can Transform US Healthcare System, According to NYU Stern Study Published in Health Systems 01/10/2013