Where is most of your personal data stored? Think about it – who has the most critical, personal information about you? It’s not your bank, or your mortgage company or your Internet service provider. In fact, it’s a loosely connected network of healthcare entities: your doctor, the lab who does your tests, your local hospital and your health insurance provider.
While data mining for intelligence is a mature practice in most other industries, particularly financial services and telecom, this is not the case in healthcare. The reason is that your medical information is too spread out and inaccessible. It’s in doctors’ charts, hospital charts, paper lab results and pharmacy computer systems. “Big data” hasn’t really visited the healthcare industry in a large way.
This may be about to change. Along with many other mandates that come attached to the Affordable Care Act (ACA, or “Obamacare”), there are provisions for moving to electronic health records, a means that can save money and time and improve the quality of health care. Once health care information is standardized and digitally stored, it will be better suited for data mining.
Perhaps having your medical data mined makes you nervous. No one would blame you. But healthcare experts see benefits in allowing the collation and study of broad swathes of anonymous medical data. It’s a way to better study healthcare outcomes and treatments and determine what works and what doesn’t, using real-world data.
Marty Kohn, chief medical scientist for IBM Research and a former ER doctor, recently shared with Yahoo! some examples of how big data can transform healthcare:
Data-driven decisions: This is when new evidence, or secondary evidence, is drawn from existing data. Big data can search for patient similarities through thousands of characteristics to help diagnose a problem.
Stream computing: In stream computing, data is not collected and stored. It uses “near real-time,” or the time minus minimal processing delays. Kohn offers an example in the Hospital for Sick Children in Toronto, in which every baby in the neo-natal ICU has vitals monitored, allowing personnel to predict an upcoming problem before it happens. Hospital staff can be alerted to a life-threatening infection up to 24 hours earlier than current practices, which improves the outcome for premature babies.
Patient care and insight: Using predictive data analysis solutions, healthcare organizations could make predictions and better understand potential outcomes for high-risk patients.
Big data analysis of healthcare info won’t be without challenges, patient security and permissions at the forefront. But it seems almost certain that with the progression of electronic health records, so too will come “Big Medical Data.”
Edited by
Alisen Downey
