Intelligent Transaction Filtering for Prior Authorization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional systems for electronic prior authorizations in the pharmacy benefits management (PBM) sector are highly manual and inefficient, particularly when handling billions of prescriptions, as they lack automation and rely on inadequate standards for codifying questions and answers, leading to inefficiencies in processing and approving prior authorizations.
Innovation Solution
An intelligent transaction filtering system that uses machine learning models to predict the likelihood of automatic adjudication for transaction requests, allowing for automatic approval or denial based on clinical data, thereby reducing the need for manual review and optimizing network resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual review processes are used for electronic prior authorizations, then accuracy and control are maintained, but processing time and operational efficiency deteriorate significantly when handling billions of prescriptions
Solution Approach 1:
The patent segments the prior authorization process into two distinct pathways: an automated adjudication pathway for straightforward cases and a manual review pathway for complex or high-risk cases. This segmentation allows the system to handle the majority of prescriptions through automated processing while reserving manual review for cases requiring human judgment, thereby resolving the contradiction between maintaining accuracy and improving processing speed.
Solution Approach 2:
The system implements self-service automated adjudication where the system automatically evaluates and approves or denies prior authorization requests based on pre-defined criteria and clinical guidelines. This eliminates the need for manual review of routine cases, dramatically improving processing speed while maintaining consistent application of authorization policies.
2Reliability
If all transaction requests are processed through manual review, then thorough evaluation is achieved, but network and processing resources are wasted on cases that could be automatically adjudicated
Solution Approach 1:
The system performs preliminary automated evaluation of all prior authorization requests before they reach manual review. By pre-processing requests and identifying those that meet clear authorization criteria, the system eliminates the need for manual review of routine cases, conserving network and processing resources while ensuring thorough evaluation through automated clinical guideline assessment.
Solution Approach 2:
The patent applies different processing qualities to different transaction requests based on their characteristics. Straightforward cases receive automated adjudication with full clinical guideline evaluation, while only complex or ambiguous cases are escalated to manual review. This local differentiation of processing quality optimizes resource utilization while maintaining evaluation thoroughness where needed.
3Productivity
If automated adjudication is implemented for all transactions, then processing efficiency improves, but the ability to handle complex cases requiring human judgment deteriorates
Solution Approach 1:
The system dynamically routes each prior authorization request to the appropriate processing pathway based on its complexity and risk characteristics. The routing decision is made in real-time, allowing the system to maximize automated processing for routine cases while ensuring complex cases receive human expert evaluation, thus achieving both high processing efficiency and adaptability to case complexity.
Solution Approach 2:
The patent introduces an intermediary routing mechanism that acts as a mediator between automated adjudication and manual review. This intermediary evaluates transaction characteristics and directs cases to the most appropriate processing pathway, ensuring that automated efficiency is maximized for suitable cases while complex cases are seamlessly transferred to human reviewers who can provide the necessary judgment and adaptability.
Data Source
AI summary
Methods, systems, and apparatuses are described for filtering a transaction over a network, according to embodiments. In an example system, a transaction request is retrieved over a network. A model that is configured to predict a likelihood associated with automatic adjudication of transactions is accessed. Based at least on the transaction request and the model, a likelihood that the transaction request can be adjudicated automatically is determined. If the likelihood that the transaction request can be adjudicated automatically is above a threshold, one or more actions are performed, such as generating an indication that a portion of the transaction request can be adjudicated automatically or generating an automatic adjudication indicating whether the transaction request should be approved. In response to generating the indication or the automatic adjudication, the transaction request and the indication or the automatic adjudication are forwarded over the network to an endpoint associated with the transaction request.