MultiPlan’s mission is to deliver affordability, efficiency and fairness to the U.S. healthcare system using sophisticated technology and data solutions. As part of this strategy, MultiPlan looked inward and identified opportunities for machine learning to streamline high-touch areas of its business.
Due to many complexities in the healthcare industry ranging from data privacy to emerging mandates and compliance to complex provider/payor networks, plus member/patient needs and considerations, it can be challenging to balance complexities with innovation. But MultiPlan is doing just that with its award-winning negotiation prioritization tool, recently selected as the “Healthcare Data Solution of the Year” by Data Breakthrough and a winner of the prestigious 2022 CIO 100 Award.
The Challenge
MultiPlan recognized its negotiators needed a tool fueled by machine learning to streamline claims before they reach the negotiator’s desk. By gauging internal capacity and current processes, the data team considered criteria such as the claim due date and the last time each claim had been touched in determining a solution.
When determining the type of tool to build, MultiPlan factored in the negotiators’ current process – i.e. they would receive between 100 and 600 claims each day and had to decide which to work first. They could carry as many as 1500 claims in their work queue at times. Prioritizing which to work first was time-consuming and required negotiators to review provider history at the claim level to estimate the amount of potential savings and to determine which claims would have the greatest likelihood of a successful negotiation.
Each negotiator had their own method to decide what was ‘most important’ and ‘most probable for success’. They spent hours each week sorting their queue as claims were worked and new claims came in. The process was frustrating and had variable success based on the negotiator’s experience and their ability to identify patterns for a successful negotiation. Moreover, time spent prioritizing the negotiation queue was time spent not negotiating claims. MultiPlan saw an opportunity to make the process more efficient.
The Solution
MultiPlan developed a negotiation prioritization tool aimed at helping negotiators streamline their workflow and quickly identify the next best claim to work. The team conceived and deployed a highly effective internal tool that immediately delivered on enhancing productivity.
The negotiation prioritization process uses a combination of machine learning and business rules to provide an optimized order for negotiators to work claims. Machine learning calculates a claim score based on two key factors; Savings, the estimated savings that will be achieved on a claim, and Success, the probability of successfully negotiating a claim. The machine models make use of the financials of a claim, its clinical factors, MultiPlan’s history of negotiating with a particular provider, and claim data elements submitted by clients to assign a claim priority score that is used to automatically rank claims within the queue. Even the most experienced negotiators could not examine all the factors that would result in a successful negotiation, whereas the model can and is highly predictive.
When building the tool, MultiPlan also accounted for operational requirements. Five key business rules work alongside the machine model to balance business needs with success factors. The tool considers criteria such as the claim due date and the last time each claim had been touched. By combining these rules with the machine model, the team is able to deliver successful outcomes for all claims, not just those deemed best opportunities by the machine model. Business criteria can be customized based on evolving needs, making the tool a flexible solution that can evolve as needed.
Beginning with its team of 350+ claims negotiators, MultiPlan quickly launched and implemented its negotiation prioritization project to streamline workflow, drive efficiency and increase ROI. Using machine learning to rank claims with the highest potential for success, negotiators were given a clear roadmap, cutting down on wasted administrative time and significantly increasing productivity and yield.
By advancing machine learning techniques around payor/provider fee negotiation in a hybrid cloud environment, the company is playing a critical role in helping:
- Drive down patient/member costs in healthcare.
- Find new ways to deploy machine learning and data science techniques to solve complex fee and reimbursement challenges.
- Improve operational efficiency and effectiveness (both in time and in dollar savings) for teams and departments across business and operational lines at MultiPlan.
- Maintain a market leadership position in payor cost containment and payment/revenue integrity.
In the long run, MultiPlan clients benefit when the fee negotiations team is more productive in prioritizing work. Paired with MultiPlan’s innovative solutions tailored to meet each client’s individual needs, this is a win/win for all involved.
CIO 100 Award
CIO Magazine named MultiPlan a CIO 100 award winner for its negotiation prioritization project that implemented advanced machine learning techniques to streamline this high-touch area of its business, generating greater customer value while improving efficiency. For more than 30 years, the CIO 100 awards from CIO Magazine have recognized innovative organizations around the world that exemplify the highest level of strategic and operational excellence in IT.
Data Breakthrough Award Winner
Named the “Healthcare Data Solution of the Year” award in the annual Data Breakthrough Awards program conducted by Data Breakthrough, MultiPlan was specifically recognized for its negotiation prioritization tool that helps its claims negotiators quickly identify the next best claim to work, leading to greater savings for customers and increased throughput for negotiators. The annual Data Breakthrough Awards is the premier awards program founded to recognize the data technology innovators, leaders and visionaries from around the world.