A leading healthcare provider wanted to reduce claim payment errors and fraud and recapture lost revenue as well as improve the overall patient experience. The technical challenges for both of these business needs were that they had siloed data sources and no real-time access to the data for their multiple business units.
This diversified health care company provides health benefits and services to more than 85 million people worldwide through state Medicaid programs, employer sponsored and individual health benefits plans, Medicare, and veterans programs.
The company wanted to improve the efficiency and accuracy of claims processing and improve the overall patient experience.
Their current practice of processing claims, based on daily and monthly batch jobs, was inefficient. Processing nearly 2 million claims per day, this method was slow and opened opportunities for fraud. They were also unable to recover distributed payments due to lack of pre-adjudication. They wanted a new system that could reduce claim payment errors and fraud, and recapture lost revenue.
The organization also wants to improve the patient experience. This is partially driven by the federal Five-Star Rating System that rates every health care provider on patient care and satisfaction, health outcomes, and patient feedback. A high star rating maximizes bonus payments with the Centers for Medicare and Medicaid Services (CMS). Their goal is to have a 360-degree view of the patient in near real-time so they can consistently offer high levels of care and service.
The technical challenges for both of these business needs were that they had siloed data sources and no real-time access to the data for their multiple business units. This was made even more difficult with the organization’s constant growth. Every time there was an acquisition, it added another data source and more complexity.
MapR enables the healthcare provider to bring together all the disparate data sources into one data lake that is accessible to multiple business units in real time.
Their goal is to bring together all of the disparate data sources into one data lake that can serve as a data hub for multiple business units. MapR was chosen for its data protection, NFS, multi-tenancy, and security features.
Multiple data sources are being brought together in the MapR platform to automate processing. NFS helps ingest a variety of different data sources related to payments into a single data lake. Machine learning algorithms can then help in supporting more real-time adjudication of claims. MapR Database is key to help support a more agile and near real-time claims processing system. The organization supports many different programs and business units. Multi-tenancy helps segregate data, users and groups for each program.
With this new solution in place, the goal is to capture an incremental 20% of fraud, waste, and abuse within the claims environment. To improve patient experience, they are using big data to track and predict federal star ratings so they can increase their ratings by proactively addressing areas of patient care that need improvement.