While health analytics can help improve quality outcomes, increase patient satisfaction and reduce costs, allowing healthcare organizations to draw specific actionable conclusions, they must embrace predictive analytics to realize the promise of personalized care.

The problem is that currently most healthcare organizations are extensive users of “descriptive” analytics, using reporting tools and applications to understand what has happened in the past and to classify and categorize historical, usually structured data. According to Rock Health, which funds and supports early stage healthcare companies, the industry must move to a model of “predictive” analytics—the process of learning from historical data in order to make predictions about the future, which in the case of healthcare means “enabling the best decisions to be made, allowing for care to be personalized to each individual.”

As data sources and technology advance, the firm concludes in a new report released today that algorithms will be able to improve the odds that a certain treatment will result in a favorable outcome for a specific individual. And, although personalized medicine has yet to deliver on its promise, the precursor to personalized medicine—predictive analytics—has proven effective in other industries and is now impacting healthcare.

The good news, Rock Health reveals, is that dozens of new digital products have hit the market and $1.9 billion has flowed into companies that purport to use predictive analytics since 2011. The bad news: 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 while most predictive analytics companies continue to leverage clinical and claims data for their algorithms.

Nonetheless, the firm acknowledges that new data streams—including those direct from patients—are beginning to be used by companies for predictive analytics with an emerging group that are using patient-generated (e.g., digital medical devices and wearables) and patient-reported data to help better predict care. Analyzing disparate data from across a health organization is becoming increasingly important.

Healthcare is starting to take advantage of predictive models and analytics to drive better decision making, take more effective action, and apply new insights from the valuable data already at its fingertips. According to Rock Health, the building block for developing “non-obvious” predictions is aggregating, cleansing and labeling data from disparate sources. And, the firm asserts that using new data sources creates an opportunity to “surface” better (more accurate, timely) predictors.

“The benefits of using predictive analytics are the same as many categories of digital health: better care and lower costs. The difference is that the path to realizing these benefits—through personalized care—is only possible by implementing these technologies,” states the report.

However, one of the biggest challenges to the adoption of predictive analytics in healthcare is regulation, says the firm, which argues that the industry might be waiting to implement these technologies as the U.S. Food and Drug Administration decides how to regulate clinical decision support. Rock Health concludes its report by asking: How will the FDA regulate the practice of medicine when algorithms prove more accurate than clinicians? 

Register or login for access to this item and much more

All Health Data Management content is archived after seven days.

Community members receive:
  • All recent and archived articles
  • Conference offers and updates
  • A full menu of enewsletter options
  • Web seminars, white papers, ebooks

Don't have an account? Register for Free Unlimited Access