Let's Keep the Conversation Going

Predictive analytic solutions, which span the continuum from simple rubrics to complex neural net models, share a common boundary problem. At some point, the predictive model reaches a point where it is no longer accurate at identifying at-risk individuals. No matter how clean the data is or complex the math, all predictive models will reach this point.

Every new technology comes with an adoption gap: that space between technological capability and human adaptation. This disconnect handicaps the inherent power of new tools and our ability to effectively and quickly realize value. The gap widens for emerging technologies like cognitive science. With cognitive machines, we have tremendous potential that, when applied, can positively impact the health and lives of millions; but, the newness and sophistication of the solutions can act as speed bumps to adoption.

Sometimes, major inflection points happen when we take what is working within other industries and calibrate it to address the challenges that we face within healthcare. This is what is happening today with the Jvion Machine. Based on intent-driven, proven search engine technology, we can answer incalculable questions about patient health. When will I end up in the emergency room? Will my grandmother get a pressure ulcer while she is in the hospital? What post-acute care is best for me? More importantly, we can tell you what to do to stop these things from happening. All of this capability is enabled by the same kind of perpetually learning, constantly expanding cognitive capability that knows when you want to take a vacation, what shoes you like to wear, and the exact quote on the exact page of the exact book that you are searching for.

We asked our clients to share their thoughts on the solutions and approaches that they evaluated against Jvion's Cognitive Clinical Success Machine. C-level executives from administration, quality, IT, finance, and clinical operations representing hospitals ranging in size from multi-facility integrated delivery networks to 150-bed organizations participated. And these systems use multiple platforms including Epic, Cerner, MEDITECH, and Allscripts. Three general flavors of comparison solution categories emerged during the discussion: enterprise data warehouses (EDWs)/data lakes, scoring methods, and electronic health/medical record (EH/MR) models. The following provides a summary of key findings.

Predictive analytics as a solution category has become so empty that it does little to help providers understand or estimate the value of a predictive analytic tool. There are two broad trends that have led us here: the flood of vendors claiming to have a predictive solution and the loose standards used to evaluate predictive analytics.

This July 1, 2017, 1127 hospitals will be included in the Centers for Medicare and Medicaid Services (CMS's) Cardiac Bundle. Of those, 475 will also participate in the Cardiac Rehabilitation Program. Like other mandated retrospective bundled payment programs, these new models are aimed at controlling costs while ensuring quality for what are often expensive and complex procedures. In the case of the Cardiac Bundle, Acute Myocardial Infarctions (heart attacks) and Coronary Artery Bypass Grafts (CABG or bypass surgery) are at aim. Cardiac Rehabilitation has been added to a selection of participating hospitals to test the effectiveness of rehab programs in driving down risk and cost for AMI and CABG patients. Taken together, the bundle is part of a broader program driven by CMS to prevent cardiovascular disease, which causes one in three deaths within the U.S. and costs more than $300 billion each year.