Provider Performance Scoring Using Claim Clustering and ML
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Insurance companies face challenges in efficiently determining the performance of healthcare providers due to the variability and volume of claim data, making it difficult to implement automated systems that accurately assess provider performance across unique claims.
Innovation Solution
A system using a combination of supervised and unsupervised machine learning models to predict provider performance by clustering similar claims and providers, integrating structured and unstructured data, and selecting models based on claim processing stages to reduce computational resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If an automated system is implemented to compare claims and determine provider performance, then productivity is improved, but device complexity increases due to the need to process diverse data types and large volumes of claim data
Solution Approach 1:
The system segments the claim data processing into distinct clusters based on similarity metrics. Claims are grouped into clusters that share common characteristics, allowing the system to process and compare claims within homogeneous groups rather than handling all diverse claims uniformly, thereby reducing overall system complexity while maintaining automated assessment capability
Solution Approach 2:
The system introduces an intermediary clustering mechanism that acts as a mediator between raw claim data and provider performance evaluation. This intermediary layer organizes and pre-processes the diverse data into manageable clusters, simplifying the subsequent performance assessment process and reducing the computational complexity required for automated evaluation
2Productivity
If a single automated system processes all claim data for multiple providers, then productivity is improved, but difficulty of detecting and measuring increases due to isolating relevant information among dozens of providers per claim
Solution Approach 1:
The system segments the evaluation process by first clustering claims into groups based on their characteristics, then within those clusters identifying and isolating the specific claims and providers relevant to each evaluation. This segmented approach makes it easier to detect and measure provider-specific performance information without being overwhelmed by the full complexity of all claims and providers
Solution Approach 2:
The system applies local quality analysis by focusing the evaluation on specific local clusters of claims and providers rather than treating all data uniformly. Within each cluster, the system identifies and measures the relevant provider performance metrics, making the detection and measurement of provider-specific information more manageable and accurate
Data Source
AI summary
A system and a method are disclosed for a tool that generates a provider score corresponding to a predicted performance of a provider based on data of claims involving the provider. For a given claim, the tool provides the data as input into a supervised machine learning model and receives as output from the supervised machine learning model a predicted performance of the claim. The tool also inputs the data of the claim into an unsupervised machine learning model that is selected based on a stage of claim processing that the claim belongs to and receives as output from the unsupervised machine learning model an identification of a cluster of candidate claims to which the claim belongs. The tool combines the outputs of the supervised machine learning model and the unsupervised machine learning model to generate the provider score.