Atlanta, GA (PRWEB) August 24, 2014
Recognized for financial waste predictive technologies, Jvion has furthered its reach and gained traction in applying Big Data within healthcare to address clinical waste and improve patient-level health outcomes. The launch of the firm’s first financial use case in 2011 gained significant market share with more than 2100 hospitals and clinics using the solution. Last fall, following the release of Jvion’s full clinical Big Data predictive analytics solution RevEgis, the firm has seen major traction within the healthcare industry and specifically within the provider community.
As a result of their success, Jvion released insights into how to make Big Data work for healthcare providers. During a recent interview with Ritesh Sharma, Jvion’s COO, the firm shared their five biggest “lessons from the field,” which focus on eliminating barriers while delivering more accurate and actionable predictive insights.
1. Implementation has to be fast and non-intrusive: hospitals are already overstretched. Between mandates, compliance activities, and day-to-day operations, providers do not have the resources available to support the implementation of an enterprise data warehouse (EDW) or infrastructure intensive solution.
2. The outputs must be accurate: if the outputs of the predictive solution are not accurate, they won’t be trusted or adopted. One of the big factors playing into accuracy is coverage. Simply put, higher coverage results in lower accuracy and lower coverage results in higher accuracy. Big Data solutions designed for use in the provider setting have to account for the converse relationship between coverage and accuracy to deliver results that are meaningful and applicable across the provider environment. Moreover, the solution should be more than just hardware and software. An effective predictive analytic solution for healthcare should start producing results “out-of-the-box;” a provider shouldn’t have to wait for a vendor to tune algorithms or data to reach a critical threshold to start to produce meaningful and actionable predictive insights.
3. The solution should use readily available data: the Big Data solutions that will be successful within the provider setting will use data that is already produced and easily pulled from existing EHR platforms. The solution should also be able to accommodate disparate data such as social media feeds if a provider wants to use these kinds of data sources to drive additional depth into the predictive insights.
4. The solution has to be flexible: there are a lot of solutions that focus on one disease or occurrence. Providers require a Big Data solution that can be scaled quickly to address the specific illnesses and conditions that have the highest impact and risk to their patient population. Having this kind of flexibility better positions providers for value-based purchasing contracts and accountable care structures. In addition, successful Big Data solutions have to integrate quickly into existing EHRs and account for use on mobile devises.
5. Deep machine learning should be at the core of the solution: Big Data, predictive analytics, and machine learning are convoluted terms within the Big Data in Healthcare discussion. A Big Data solution that delivers patient-level outcomes has to be built around a deep machine learning engine that uses algorithms and rules to look across millions of data points to arrive at an accurate patient-level prediction. And this engine must become smarter with every new data element fed through the system. This is the only way to achieve accurate predictions about a specific disease or illness on an individual patient.
To learn more about Jvion and their Big Data predictive analytic solutions for healthcare, please visit http://www.jvion.com.
Jvion is a healthcare technology company that develops software designed to predict and prevent patient-level disease and financial losses leading to increased waste. The company offers a suite of big-data enabled solutions that combine clinical intelligence with deep machine learning to help providers protect their revenues while improving patient health outcomes. Their objective is simple—stop the waste of resources and lives by predicting and stopping losses before they ever happen.