Case Study: Healthcare
The solution
Faster TAT and even faster determination
In collaboration with the client, the Sagility team works directly on the client’s Epic system, which enables faster turnaround time (TAT) on billing and claim resubmissions. But Sagility saw an opportunity to introduce a propensity-to-pay solution and strategy, for even faster determination of claims payment probability. This solution gets to the heart of optimized payments structure, claims management, and forecasting.
Predictive analytics
Sagility developed a predictive analytics model using tree-based machine learning algorithm to classify the claims into four priority groups or clusters in terms of their probability of getting paid (High, Medium, Low and Not payable). This ML algorithm was integrated with Sagility’s Claims Management System workflow tool and enabled the operations team to prioritize work assignment to the team, thereby improving the ability to realize the cash faster from the prioritized claims.
The model uses key variable combinations to predict the probability of payment and expected collections. Next, the model groups the payments into aforementioned clusters.
The 40-person Sagility team
includes analytics and technical experts with ML programming capabilities, domain RCM experts, and project managers. Our analytics integrates with our Claims Management System to operate on all claims and optimize bandwidth of this solution.
Results
As a result of our propensity-to-pay technology, people, and processes, Sagility delivered these breakthrough results within 90 days:
15% increase
in the cash collections on claims
within 90 days from the date of placement.
28.5% cash collection rate
exceeded the client’s benchmark of 25% from the claim placement date 0 – 90. Sagility is now operating at 28.5%.
The Sagility team helped the client turn a corner in challenging times, with best-in-class SLAs benchmarked by the client. The client has acknowledged this consultative value from Sagility—and the future is bright for more innovation.