AI Medical Imaging Workflow Status Claiming and Rule-Based Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The integration of AI systems in medical imaging workflows leads to conflicts such as resource wastage, billing issues, and double reads due to AI systems being computationally intensive and sometimes unable to process studies in a timely manner, causing inefficiencies and conflicting opinions.
Innovation Solution
Implementing a system that allows AI systems to claim image studies for review, reject studies if they cannot be processed timely, and report status, using inclusion and exclusion rules to determine suitability for processing, thereby optimizing resource use and coordinating workflows between AI and manual reviewers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If AI systems process image studies, then diagnostic accuracy is improved, but processing time increases and resource consumption increases
Solution Approach 1:
The system performs preliminary actions by having AI systems claim studies in advance and apply inclusion/exclusion rules before full processing begins. This allows the system to pre-screen studies, reject inappropriate ones early, and prepare only those that meet criteria for AI processing, thereby reducing overall processing time while maintaining diagnostic accuracy for eligible studies.
Solution Approach 2:
The processing workflow is segmented into distinct phases: claim status assignment, inclusion/exclusion rule application, and full AI processing. This segmentation allows the system to handle studies at different stages independently, parallelize processing where possible, and avoid wasting resources on studies that will ultimately be rejected, thus reducing total processing time while preserving accuracy for studies that proceed through all stages.
2Reliability
If AI systems process all image studies, then comprehensive review is improved, but computing resource consumption increases
Solution Approach 1:
The system extracts and removes studies from the processing queue that do not meet inclusion criteria or meet exclusion criteria through rule-based filtering. By taking out inappropriate studies before they consume AI computing resources, the system maintains comprehensive review coverage for eligible studies while significantly reducing overall computing resource consumption through selective processing.
Solution Approach 2:
The system changes the parameter of study eligibility by applying inclusion and exclusion rules that transform the processing queue from containing all studies to containing only those studies appropriate for AI processing. This parameter change ensures comprehensive review of suitable studies while optimizing resource consumption by excluding unsuitable ones.
3Productivity
If multiple AI systems process studies simultaneously, then productivity is improved, but conflicts and resource wastage increase
Solution Approach 1:
The claim status mechanism acts as an intermediary that coordinates between multiple AI systems and the study queue. By assigning claim status to studies, the system mediates access rights, preventing multiple AI systems from simultaneously processing the same study. This intermediary mechanism enables high productivity through parallel processing of different studies while avoiding resource wastage from duplicate processing or conflicts.
4Reliability
If AI systems wait for physician workflow coordination, then billing conflicts are reduced, but processing delays increase
Solution Approach 1:
The system performs preliminary actions by assigning claim status to studies before AI processing begins and updating this status throughout the workflow. This preliminary coordination with the physician workflow system allows billing information to be prepared in advance, reducing billing conflicts while minimizing processing delays through proactive rather than reactive coordination.
Data Source
AI summary
Systems and methods for selectively processing image studies with an artificial intelligence system. One system includes an electronic processor configured to select an image study awaiting review and update a workflow status of the image study to a first status indicating that the image study has been claimed for review by the artificial intelligence system. The electronic processor is also configured to apply at least one of the plurality of rules to the image study to determine whether the image study is applicable for processing by the artificial intelligence system, and, in response to determining the image study is not applicable for processing by the artificial intelligence system based on the at least one of the plurality of rules, update the workflow status associated with the image study to a second status to make the image study available for claiming by a manual reviewer or another artificial intelligence system.