Enter your text here...
The rising costs of healthcare have become unaffordable and unsustainable across the globe. A number of forces continue to propel these numbers upward, including health industry consolidation, prolonged hospital stays, the introduction of expensive complex biologics, and wasteful spending associated with the overuse of medical services. However, the primary drivers continue to be the demands for increased medical services related to the aging global population. The rapid growth of an older population more likely to face several chronic conditions simultaneously and immediate needs for frequent care, costly diagnostic healthcare procedures, and extensive prescription medication needs is helping to drive the skyrocketing costs of healthcare.
As older adults live into their eighties and beyond, they are more likely to be afflicted with multiple chronic health problems – multi-morbidities – requiring the use of multiple medications simultaneously – polypharmacy. The average Medicare patient (65+ years of age and older) is afflicted with three chronic conditions and is taking five medications. Managing the complex interactions between demographic factors, drug interactions, and disease behaviors is a daunting task that even the most skilled and experienced geriatricians admit is mostly trial and error. Add the presence of implanted medical devices to the equation and it becomes almost impossible for the unaided human brain to evaluate without the use of Advanced Analytics to provide metrics, options, and recommendations that inform medical professionals' treatment plans.
Patient PREDICT™, powered by Pythia, focuses on the complexity, safety, and economics related to medical device usage in the older population, typically with multiple chronic conditions taking multiple medications. The synergy achieved through the integration of MedDev PREDICT™ and Patient PREDICT™ produces a complete prediction for the interaction of all aspects of patient demographics and treatment modalities using massive amounts of data from a wide variety of sources, collected and stored in our Intelligent Data Lake, an organized, well-governed HIPAA-compliant repository of anonymized patient claims and outcomes records for thirty-five million plus patients sourced from CMS (the Centers for Medicare and Medicaid Services) dating back to 1999, as well as all obtainable data from sources including relevant medical registries, insurance claims files, social media, and professional literature and research studies.
We leverage various sets of predictive and prescriptive Machine Learning models to weigh all the risk factors, costs, demographics, best practices, research, and guidelines required to analyze similar patients who are experiencing better outcomes and predict which treatments will best support our at-risk population. The interaction of medical devices considered in conjunction with all the other medical factors is something that has never been done before and provides not only superior patient outcomes but a distinct competitive advantage for the device manufacturer with providers, payers, and consumers.
© 2018, eHealthAnalytics