Medical Claims Data Compression for Parallel Fraud Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current medical claim fraud detection methodologies require significant human review and processing resources, leading to time-consuming claim review processes that often occur after claims have been paid, due to the vast amount of data generated by each claim and the sheer volume of claims received daily, making real-time processing infeasible with existing technologies.
Innovation Solution
The implementation of a system that compresses and standardizes medical claims data into a common data input object, allowing for parallel execution of fraud detection analytics, which reduces latency by utilizing compressed historical and provider-specific parameters to quickly identify potential fraudulent claims.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional sequential processing methods are used for medical claims data, then processing accuracy can be maintained, but processing time becomes excessively long and resources are consumed inefficiently
Solution Approach 1:
The patent divides the medical claims data into multiple compressed data objects, each representing different aspects or dimensions of the claim data. This segmentation allows parallel processing of different data segments through multiple analytics, significantly improving processing speed while managing system complexity through structured data organization
Solution Approach 2:
The patent introduces a new dimension of data representation by compressing medical claims data into a multi-dimensional common data object structure. This dimensional transformation enables parallel analytics to process different facets of the same claim simultaneously, resolving the contradiction between processing speed and system complexity
2Measurement precision
If comprehensive data analysis is performed on all claims data, then detection accuracy improves, but processing resources are excessively consumed
Solution Approach 1:
The patent extracts only the essential and relevant features from comprehensive medical claims data, compressing them into a condensed common data object. This extraction process maintains fraud detection accuracy by preserving critical fraud indicators while removing redundant information, thereby reducing processing resource consumption
Solution Approach 2:
The patent transforms the data representation parameters by compressing raw claims data into a standardized common data object format with optimized data structures. This parameter change enables efficient processing while maintaining detection precision, as the compressed format preserves essential fraud detection parameters in a resource-efficient manner
3Loss of time
If real-time processing is implemented for fraud detection, then latency is reduced, but processing resources become overwhelmed by the volume of data
Solution Approach 1:
The patent performs preliminary compression and standardization of medical claims data into common data objects before fraud detection analytics are applied. This preliminary action reduces the data volume that needs to be processed in real-time, enabling low-latency processing without overwhelming system resources
Solution Approach 2:
The patent creates a compressed common data object that serves as a simplified copy or representation of the original comprehensive claims data. This copy contains only the essential information needed for fraud detection, allowing real-time processing with reduced resource requirements while maintaining detection effectiveness
Data Source
AI summary
An analytics platform for analyzing medical claims with low latency is configured to compress medical claims records into common data input objects that may be usable by a plurality of independent and parallel program analytics. The common data input objects are then passed as input to all of those program analytics, which are then configured to retrieve at least one compressed parameter file for use in processing data elements of the common data input object in accordance with a framework of a respective program analytic. The program analytics generate respective outputs based at least in part on data elements of the common data input objects, and the analytics platform combines those outputs into a single combined common output object.