It's "still early days" for effectively harnessing big data in healthcare, though there are signs of progress, according to a Harvard Business Review article.
The authors, Nilay D. Shahan and Jyotishman Pathak, both from the Mayo Clinic, point to advancement in three key areas:
- Integrating data. Information about patients' health comes from myriad sources and in multiple forms. Truly integrating all that data will require public and private leadership and collaboration, they say. At the same time, they point to efforts such as the National Institutes of Health's Big Data to Knowledge Initiative (BD2K); the National Patient-Centered Research Network (PCORnet), a planned "network of networks" for comparative effectiveness research; and the Optum Labs research collaborative as concerted efforts to pool data to improve care.
- Generating new knowledge. While the move to predictive analytics remains a work in progress in healthcare, the industry is catching up with other sectors that already are harnessing new methods, they say, including graph analytics to study multiple, complex variables; natural language processing and other artificial intelligence methods. The Mayo Clinic, for instance, has employed IBM's Watson technology in matching patients to clinical trials.
- Translating knowledge into practice. This will be the key to success, they say. While much research never filters down to clinical practice, the industry will have to figure out how to apply the knowledge learned from data.
Randomized controlled trials have been the gold standard, but "it will be critical to identify where the evidence generated by big data is adequate enough to change practice. In other cases, big data may generate new paradigms for increasing the efficiency of randomized clinical trials," the authors write.
They expound on the potential of Optum Labs's 15 partner organizations--including the Mayo Clinic, UnitedHealth, Merck, the Harvard Medical School Department of Health Care Policy and others--to effectively collaborate to drive innovation in care. Its priority, they say, is to "enable clinicians to connect insights from big data directly to the care of an individual patient."
Optum Labs's research is based on a "high-quality, integrated, up-to-date" database of de-identified claims and clinical data covering 10 years for more than 150 million people.
To learn more:
- check out the article