Predictive Queue Prioritization for Healthcare Fraud Investigation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Healthcare fraud, waste, and abuse (FWA) investigation systems face challenges in prioritizing leads and allegations efficiently, leading to delayed investigations and potential missed opportunities due to the large volume of leads from various sources, which can result in missed deterrents and convictions.

Innovation Solution

A data processing queue prioritization system that uses a predictive data model based on a base data table generated from text fields of data objects, removing punctuation, date, and stop-words, and applying natural language processing to calculate risk scores, adjusts the queue order of data objects for timely action.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If investigators process leads in the order they are received, then the queue management is simple, but high-risk leads may be delayed and missed opportunities occur

Engineering Contradiction:

Improveinvestigation success rateVSAvoidqueue management complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies parameter changes by transforming the queue ordering criterion from simple reception time to a calculated risk score based on multiple parameters (data completeness, source reliability, allegation severity). This allows high-risk leads to be prioritized while maintaining systematic queue management through automated scoring.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent replaces the mechanical manual prioritization process with an automated predictive data model that calculates risk scores. This substitution eliminates the need for manual assessment of each lead's priority while improving reliability through consistent, objective scoring.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If investigators manually assess and prioritize each lead, then prioritization accuracy improves, but processing time increases and productivity decreases

Engineering Contradiction:

Improverisk assessment accuracyVSAvoidlead processing throughput

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces manual human assessment with an automated predictive data model that processes leads rapidly while maintaining high accuracy. The model uses natural language processing and multiple data sources to generate risk scores automatically, eliminating the trade-off between accuracy and speed.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-service by automatically calculating risk scores and reordering the queue without human intervention. The predictive data model continuously processes new leads and adjusts priorities based on calculated metrics, enabling high throughput while maintaining assessment accuracy.

Inventive Principle:

Principle #25Self-service

3Reliability

If the system processes all leads thoroughly, then investigation quality is high, but the time lag between lead receipt and investigation increases

Engineering Contradiction:

Improveinvestigation qualityVSAvoidinvestigation delay

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent applies preliminary action by calculating risk scores and prioritizing leads before full investigation begins. The predictive data model assesses leads quickly using available information, allowing the system to prepare and queue high-risk leads for immediate investigation, reducing the time lag while maintaining quality.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system changes the processing parameter from uniform thorough investigation to risk-based prioritized investigation. By using risk scores to differentiate lead priorities, the system can allocate investigation resources more efficiently, reducing delays for high-risk leads while maintaining quality across all investigations.

Inventive Principle:

Principle #35Parameter changes

4Speed

If the queue is reordered based on risk scores, then high-risk leads are processed faster, but the system complexity increases

Engineering Contradiction:

Improveprocessing speed of high-risk leadsVSAvoidprioritization system complexity

Core Design Contradiction:

SpeedVSDevice complexity

Solution Approach 1:

The patent replaces complex manual prioritization judgment with an automated predictive data model that calculates risk scores systematically. While the model itself is complex, it automates the process, making the system manageable and scalable without requiring manual intervention for each lead's prioritization.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11763233B2Method, apparatus and computer program product for prioritizing a data processing queue

Publication Date: 2023.09.19 OPTUM SERVICES IRELAND LTD

AI summary

Methods, apparatus, systems, computing devices, computing entities, and/or the like for programmatically prioritizing a data processing queue are provided. An example method may include retrieving a plurality of data objects in the data processing queue, generating a base data table based at least in part on the plurality of data objects, determining a predictive data model based at least in part on the base data table, and adjusting a queue order of the plurality of data objects in the data processing queue based at least in part on a risk score calculated by the predictive data model.