Machine Learning Prescription Order Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Medical suppliers face significant manual effort in handling rejected medical prescription orders due to third-party payor rejections, which results in lost opportunities and reduced time for direct customer care.
Innovation Solution
Implementing a system that uses machine learning to automatically modify and adjust rejected prescription orders, trained on past examples of rejected and subsequently approved orders, to increase approval rates without manual intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual handling of rejected orders is used, then flexibility in addressing complex rejection reasons is maintained, but labor effort and time cost increase significantly
Solution Approach 1:
The patent replaces manual mechanical processing of rejection orders with an automated machine learning system. The ML model automatically analyzes rejection reasons, determines appropriate actions, and modifies orders without human intervention, thereby eliminating time-consuming manual handling while maintaining effective rejection management capabilities
Solution Approach 2:
The system enables self-service automation where the machine learning model independently processes rejected orders by analyzing rejection codes, determining necessary modifications, and submitting corrected orders back to payors. This self-service capability reduces dependency on manual labor for routine rejection handling
2Extent of automation
If pre-determined rules are applied to correct rejections, then automation level increases, but ability to handle novel or complex rejection scenarios decreases
Solution Approach 1:
The patent replaces rigid pre-determined rule systems with a machine learning-based automated system. The ML model learns from historical data of rejected and approved orders, enabling it to handle novel and complex rejection scenarios that would exceed the scope of fixed rules, while maintaining high automation levels
Solution Approach 2:
The system transitions from static rule-based parameters to dynamic machine learning models that adapt to changing rejection patterns. The ML model continuously learns from new data, allowing it to adjust its decision-making parameters to handle evolving payor requirements and complex rejection scenarios effectively
3Productivity
If machine learning is used to process rejections, then processing speed and automation increase, but system complexity and initial implementation cost increase
Solution Approach 1:
The patent implements machine learning to automatically process rejected orders, dramatically increasing processing speed and productivity. The system automatically analyzes rejection reasons, determines corrections, and resubmits orders, eliminating manual processing bottlenecks and accelerating the entire rejection handling workflow
Data Source
AI summary
Example systems, methods and apparatus to process medical prescription order rejections are disclosed. An example computer-implemented method, executed by one or more processors, to process a medical prescription order rejection may include: submitting, using one or more processors, a first order for a medical prescription to a third-party entity for payment; and when a rejection of the first order is received from the third-party entity: processing, with a trained machine learning model, the first order to form a second order for the medical prescription, wherein the machine learning model is trained by one or more processors based on training data representing a plurality of rejected orders for prescriptions and a plurality of approved orders for prescriptions by updating the machine learning model based on computed differences between (i) orders for medical prescriptions determined by the machine learning model, and (ii) associated approved and rejected orders; and submitting, using one or more processors, the second order for the medical prescription to the third-party entity for payment.