Find out why the electronic medical record (EMR), which is supposed to function as a big data repository that knows everything about a patient, is where healthcare is stumbling.
There are nearly 20 medical specialty areas for healthcare professionals, and the act of a primary care provider referring a patient to a specialist for a particular condition is routine. This is great for patients who require care from experts, but not so great when it comes to coordinating overall patient care or a holistic approach to patients that looks at underlying causes of diseases, and not just treating symptoms.
Consequently, it hasn't surprised me that for the many industry verticals I have consulted with on IT, nowhere is there a greater disconnect on communications coordination and information management than in healthcare. There are reasons why this is the case.
The high degree of specialization in the industry creates many information silos that are difficult to reconcile in the push for a universal electronic medical record (EMR). There are also a high number of mergers within the industry that leave the unfinished business of disparate and incompatible medical systems to the end.
All of this naturally begs the question of whether big data can help healthcare improve performance and become more patient-centric.
Healthcare institutions recognize the importance of patient centrism, as evidenced by the growth of patient-centered medical home initiatives intended to transform care coordination and communication to "what patients want it to be."
Unfortunately, these initiatives are stymied if data can't be amalgamated to show the entirety of a patient's care so as to preclude the daily misses of medical communication—like the orthopedic doctor who prescribes a cortisone shot for an arthritic knee without knowing that the patient is already on heavy doses of high blood pressure medicine as prescribed by his heart doctor, and which could be adversely affected by the cortisone. This is where a universal, all-inclusive information source like the EMR is supposed to function as a big data repository that knows everything about a patient; it is also where healthcare is stumbling.
The good news is that, even though the U.S. lags other countries in EMR implementation, over 80 percent of U.S. primary care physician now use an EMR. Equally important to medical practitioners is being able to troubleshoot patient medical records on both a very granular basis and as part of a broader trends basis.
At Memorial Sloan Kettering Cancer Center in New York, patient information is fed into an EMR and is then run through an IBM Watson database of thousands of medical journals, industry association guidelines, and hospital best practices to provide a list of treatment options (accompanied by confidence scores) and clinical trials for which the patient might be eligible. "Watson's capability to analyze huge volumes of data and reduce it down to critical decision points is absolutely essential to improve our ability to deliver effective therapies and disseminate them to the world," said Dr. Craig Thompson, president and CEO of Memorial Sloan Kettering.
In Cleveland, cloud solutions provider Explorys publishes medical trends information gleaned from its big data analytics.
The information enables healthcare providers to better understand the
conditions of individual patients, and even to determine how a particular
patient is likely to respond to a specific treatment. (Note: The Explorys article is published on The Profitable Practice, which is produced by Software Advice.)
Big data solutions are also being deployed to track and evaluate patient outcomes of treatment—an overlooked area in the past that is extremely significant, since 20 percent of hospital admissions are patients who were discharged within the past 30 days.
"Physicians have traditionally used their judgment when making treatment decisions, but in the last few years there has been a move toward evidence-based medicine, which involves systematically reviewing clinical data and making treatment decisions based on the best available information," said McKinsey director Nicolaus Henke. "Aggregating individual data sets into big-data algorithms often provides the most robust evidence, since nuances in subpopulations (such as the presence of patients with gluten allergies) may be so rare that they are not readily apparent in small samples."
There's the potential to transform healthcare with big data, but the industry must still answer two fundamental questions going forward:
- Can big data improve the quality of care and the success of treatment outcomes for patients?
- Does big data have the power to cure broken healthcare information systems?