Rule-Based Preprocessing for AI Prescription Next Best Action
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current pharmacy workflows are inefficient due to their sequential nature, leading to delays in prescription fulfillment as issues in one step can cause cascading delays, and there is a lack of comprehensive solutions for managing and optimizing the prescription fulfillment process.
Innovation Solution
An artificial intelligence system using rule-based preprocessing and machine learning models to identify and resolve issues proactively, determining the next best action for prescription fulfillment by processing parameter sets through a rules engine and machine learning models to optimize the workflow and reduce computational resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a sequential process is used for prescription fulfillment, then each step can be completed in order, but delays occur when issues are identified in later steps requiring backtracking to earlier steps
Solution Approach 1:
The system performs preliminary actions by evaluating multiple potential problems and their resolutions before actually executing the fulfillment process. It proactively identifies stock issues, insurance coverage problems, and other exceptions in advance, determining all necessary corrective actions before submission, thereby eliminating the need for sequential backtracking and reducing overall fulfillment time while maintaining complete problem identification
2Reliability
If comprehensive problem evaluation is performed before fulfillment, then all issues can be identified and resolved proactively, but computational resources and processing complexity increase
Solution Approach 1:
The system segments the comprehensive problem evaluation into distinct, manageable modules: stock availability checking, insurance coverage verification, formulary compliance validation, and resolution strategy generation. Each module handles a specific aspect of problem identification and resolution, allowing the system to perform thorough evaluations without overwhelming computational complexity, as each segment can be processed independently and efficiently
Solution Approach 2:
The system introduces an intermediary processing layer that acts as a mediator between the prescription submission and the fulfillment execution. This intermediary layer pre-evaluates all potential problems and coordinates the necessary resolutions before fulfillment, simplifying the overall system architecture by centralizing the complex evaluation logic in a dedicated intermediate stage rather than distributing complexity throughout the entire fulfillment process
Data Source
AI summary
Systems and methods for using rule-based preprocessing to improve artificial intelligence prediction of next best actions are disclosed. Prescription information may be used to identify a parameter set for a machine learning model. The parameter set may first be processed through a rules engine having a first rule set configured to conditionally determine the next best action service call without processing through the machine learning model. The machine learning model may then selectively process the parameter set to determine the next best action service call if the first rule set did not meet a next best action condition in the rule set. The next best action service call may be initiated to execute the next best action. For example, in response to rejection from insurance adjudication, the next best action may change the prescription information for automatically resubmitting the prescription to insurance adjudication.