AI Dental Claim Flagging From Clinical Images and Periodontal Charts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Dental claim adjudication is labor-intensive and prone to errors due to the limitations of X-ray images in providing color and spatial information, leading to inefficiencies and potential fraud in reimbursement processes.
Innovation Solution
A multi-AI model framework processes clinical images to identify dental procedure codes and extracts periodontal chart data, using bounding boxes to associate outputs and store information in a computer-readable format, enhancing the adjudication process with improved accuracy and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual adjudication is used to review dental claims, then accuracy in determining medical necessity is maintained, but labor intensity and cost increase significantly
Solution Approach 1:
The patent replaces manual mechanical review processes with an automated AI-based system that processes clinical images and periodontal charts to determine medical necessity, eliminating the need for human adjudicators to manually review each claim while maintaining accuracy through sophisticated image analysis algorithms
Solution Approach 2:
The system enables self-service adjudication where the AI model automatically evaluates claim attachments, extracts relevant information, and determines medical necessity without requiring human intervention, allowing the system to service itself and significantly improving processing speed
2Loss of information
If X-ray images are used for procedure verification, then basic dental anatomy and pathology are visible, but color and spatial information are lost
Solution Approach 1:
The patent merges multiple types of clinical images (including color photographs and X-rays) into a comprehensive evaluation system where each image type contributes different information - color photos provide material and spatial details while X-rays provide structural anatomy - creating a complete evidentiary record that overcomes the limitations of any single image type
Solution Approach 2:
The system makes the clinical image evaluation process universal by accepting and processing multiple image formats and types through a single AI framework, where different image types serve different functions - color images for material identification and spatial relationships, X-rays for anatomical structure - ensuring comprehensive procedure verification
3Reliability
If multiple clinical images and periodontal charts are collected for complete procedure verification, then evidentiary support is improved, but complexity of the adjudication process increases
Solution Approach 1:
The patent replaces complex manual analysis of multiple documents with an automated AI system that simultaneously processes clinical images and periodontal charts, extracting and correlating information from all sources without requiring adjudicators to manually navigate through multiple complex documents
Solution Approach 2:
The AI model acts as an intermediary that bridges the gap between the complexity of multiple required attachments and the need for comprehensive verification, automatically parsing, extracting, and correlating information from all image types and periodontal charts to produce a unified evaluation
Data Source
AI summary
A method includes receiving, by one or more processors, a clinical image associated with a dental procedure; identifying, by the one or more processors, one or more dental procedure codes based on processing the clinical image using a plurality of AI models; receiving, by the one or more processors, a periodontal chart image; processing, by the one or more processors, the periodontal chart image using optical character recognition to obtain pocket measurements associated with a plurality of teeth along with positional coordinates of each of the pocket measurements; identifying, by the one or more processors, a submitted dental procedure code in a dental claim for the dental procedure; determining, by the one or more processors, whether the submitted dental procedure code corresponds to a visibly detectable procedure; determining, by the one or more processors, whether the submitted dental procedure code matches any of the one or more dental procedure codes based on processing the clinical image when the submitted dental procedure code corresponds to a visibly detectable procedure; and flagging, by the one or more processors, the dental claim when at least one of the submitted dental procedure code does not match any of the one or more dental procedure codes based on processing the clinical image, the submitted dental procedure code does not correspond to a visibly detectable procedure, or the pocket measurements do not support the submitted dental procedure code.