Success Stories

Use of Artificial Intelligence in Improving
Eligibility of Pharmaceutical Claims

Background/Problem Statement:

The US federal government has several Pharmacy reimbursement programs that require drug manufacturers to provide outpatient drugs to eligible health care organizations and covered entities at significantly reduced prices. These programs cover entities to stretch scarce federal resources as far as possible, reaching more eligible patients and providing more comprehensive services. These Govt. Pharmacy programs were established in order to provide discounted drugs for covered entities, such as “high-Medicaid public and private non-profit hospitals, community health centres’, and other safety net provider to help those facilities to deliver pharmacy services to those underinsured or uninsured outpatient populations Each of these processes comprise of several activities/forms and lot of manual work is involved that are time consuming but critical for to reduce costs to Insurance companies. The objective of the project was to improve the acceptance of Insurance claims under 340B federal program thereby decrease insurance reimbursement costs due to high levels of uninsured patient. . Therefore, after a detailed analysis and research, Ai labs developed and implemented a Proof of Concept (POC) using its proprietary engine Minsky to predict the claim eligibility for these programs for individual patient claims.

Solution Overview:

After a comprehensive evaluation of the client‘s challenges/data, we used Minsky to accurately model the historical data which comprised patient related claims data such as Patient ID, Patient DOB, Pharmacy ID, Pharmacy Name, Prescriber ID, Prescriber Address, Drug Name, Patient Paid Amount, Total Amount Paid, Total Claim amount etc. Once the detailed modelling was performed by Minsky for the selected Algorithms, historical data used by Minsky was separately analysed to predict the claim eligibility for a specific Govt Pharmacy program based on real time data for individual patient Claims

Key Benefits (Minsky™):

User-Friendly cloud based AI platform
Scalable across various domains/data.
Provides you a list of % dependency features that can be used to optimize the outcomes.
Ability to fine tune or optimize the models by trying different algorithms / prediction attributes
Easy integration with other third party solutions such as TABLEAU for data visualization

Project Results:

For the above project data we used two Ai techniques for getting better model accuracy by performing advanced data cleansing techniques and model optimizations to achieve > 95% Model Accuracies. Based on the data, our analysis shows that ADA Boost Classifier (99%) gave the highest model accuracy for both techniques. In terms of the attributes data, for both (i), (ii) Ai techniques Pharmacy Dispensary fees information played a major role and showed the highest dependency cause for the eligibility criteria for a specific Govt. pharmacy program followed by Cost Savings information.

Need For Solution:

This Ai powered project enabled our client to find out three things in their existing process
i. To improve the chances of eligibility claims
ii. To predict which claim will be ineligible
iii. For the ineligible claims, to find which feature importance attributes from Minsky models needs be fine tuned to improve the claims acceptance prior to submission.

Benefits:

Improve revenues by ensuring that majority of the claims are accepted under the Ferderal 340b program.
Improved process efficiency.
Optimized Claims Management for Reduced Costs and Operational Risks.
Faster and Reliable service.
Better employee time-utilization.

PHARMACY CLAIMS