It did not take long for analytics to become commercialized as a big business. Perhaps this is the first step in developing Preferred Patterns in developing algorithms. Leaders such as the Mayo Clinic, and perhaps other university centers will have a sweepstakes of algos for outcomes and big data in health care. That would be wonderful and would save the rest of us from pouring limited resources into Medicare’s edicts about outcomes. Who will be next ?
Benefits of Sharing Algorithms
Mayo Clinic’s decision to offer its algorithms through Apervita empowers health enterprises everywhere to leverage Mayo’s portfolio of algorithms, which includes a large number of specialties, such as cardiovascular, pulmonology, and oncology. “At Mayo, one of our most scalable assets is our knowledge. We have found sharing knowledge significantly improves the efficacy of care delivery, improving quality and driving down costs. Sudden cardiac arrest is a leading cause of death among adults over the age of 40,” said Paul Friedman, MD Vice-chair, Cardiovascular Medicine, and Director, Cardiac Electronic Implantable Device Lab at Mayo Clinic in a statement. For example, Mayo is sharing an algorithm that can automatically identify patients at risk for sudden cardiac arrest for an appropriate consultation.
How It Works
Apervita empowers health professionals and enterprises to capture and share health knowledge, allowing them to easily author, publish and use health analytics, such as algorithms, quality and safety measures, pathways, and protocols. The Apervita health analytics market liberates this knowledge and makes it readily accessible so that every health professional can take advantage of it. Health enterprises no longer need to hard code analytics into their existing systems or buy siloed analytic systems. By selecting trusted analytics from globally renowned institutions, health enterprises can readily improve their workflow, inserting insight where it is most needed.
Example uses of Apervita’s health analytics market for providers include:
- Create a patient safety dashboard. Use your own measure data and choose public measures from the Apervita marketplace. Share it with your safety taskforce.
- Using the latest medical algorithms, providers can detect readmission risks across your populations. Monitor high risk patients at admission and discharge, by disease.
- Quickly identify outliers and deteriorating patients. Providers can choose evidence-based algorithms from the marketplace or create your own. Take action early to avoid unnecessary harm.
Other companies have taken note of opportunities for analytics in health care.
Rock Health: How Predictive Analytics Impacts Patient 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 and register for Rock Health’s live webinar on Thursday where they will explore the details of the report.
The future of algorithms may very well be standardized, so that regional
comparisons would be valid.