For more case studies in predictive healthcare, see Predictive Analytics World for Healthcare, October 2015 in Boston.
As data sources and technology advance, algorithms will be able to deliver better, personalized care. Though personalized medicine has yet to deliver on the promise of its powers, its precursor, predictive analytics, has proven effective in many industries and is now focused on transforming healthcare. Dozens of new digital health products have hit the market and $1.9B has flowed into the space since 2011—but what does it take for an algorithm to accurately and reliably impact care?
Rock Health’s latest report, Predictive Analytics: The Future of Personalized Health Care explores this question and how the overabundance of big data and widespread availability of tools has catalyzed the growth of predictive analytics in healthcare. The scope of the report only includes companies using algorithms to directly impact patient care such as clinical decision support, readmission prevention, adverse event avoidance, disease management and patient matching.
Personalizing care through predictive analytics represents a significant opportunity to reduce costs in the healthcare system. Key findings of the report include:
– Of the venture-backed companies claiming to use predictive analytics, nearly three quarters of them are focused on just healthcare professionals and practically ignore patients.
– Healthcare data is expected to exponentially grow from 500 petabytes in 2012 to 25,000 petabytes in 2020 (AMIA). That’s the equivalent of 500 billion four-drawer filing cabinets.
– Most predictive analytics companies continue to leverage clinical and claims data for their algorithms. However, there is an emerging group of companies that are using patient-generated (e.g., digital medical devices and wearables) and patient-reported data to help better predict care.
– Even if we had the technology to address interoperability issues, solve privacy concerns, and process unstructured data, hundreds of thousands of facts influence health – many of which medical science cannot explain.
– Health outcomes are not instantaneous. Without an effective, closed-feedback loop, algorithms struggle to continue to learn and improve. – Predictive analytics has no value if providers, physicians and patients do not act on these recommendations.
For more information, see the full report below
By: Fred Pennic
Originally published at http://hitconsultant.net
 |
 |
 |
