Voice-Linked Finding Extraction for Endoscopy Reporting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
During endoscopic examinations, doctors rely heavily on memory to enter diagnosis reports, leading to increased workload and potential errors due to the lack of an effective mechanism for assisting in the reporting process.
Innovation Solution
A medical information processing system that includes an examination image storage, voice processing unit, and association processing unit to extract and associate voice input information with image-capturing time, allowing for the grouping and association of examination images with finding information, thereby assisting in the preparation of endoscopic examination reports.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If doctors rely on memory to enter diagnosis reports manually, then the reporting process can be completed, but the workload increases and errors such as missed entry occur
Solution Approach 1:
The system automatically extracts finding information from voice recordings and associates it with examination images without requiring manual data entry by doctors. The voice processing unit and association processing unit enable the system to self-serve by automatically populating report fields, reducing both workload and errors
Solution Approach 2:
The manual mechanical process of typing and entering diagnosis information is replaced by an automated voice-based system. The voice input unit captures spoken findings, which are then processed and associated with images automatically, substituting the manual typing mechanism with voice recognition and automated processing
2Productivity
If voice recording is continuously captured during examination, then finding information can be extracted automatically, but data processing complexity increases
Solution Approach 1:
Voice recordings are captured and stored during the examination process itself, before the report is finalized. This preliminary capture of finding information allows for automated extraction and association later, improving report preparation efficiency without requiring complex real-time processing during the final report generation
Solution Approach 2:
The system introduces a voice processing unit as an intermediary between the doctor's spoken findings and the final report. This intermediary component automatically extracts key finding information from voice recordings and associates it with examination images, simplifying the overall process despite the added processing step
Data Source
AI summary
An examination image storage stores a plurality of examination images having image-capturing time information. A voice processing unit extracts information regarding a finding by recognizing voice that is input to a microphone, and an extracted information storage stores the extracted information regarding the finding and voice time information in association with each other. A grouping processing unit groups a plurality of examination images into one or more image groups based on the image-capturing time information. An association processing unit associates the information regarding the finding stored in the extracted information storage with an image group based on the voice time information. When one examination image is selected by a user, a finding selection screen generation unit generates a screen that displays information regarding a finding associated with an image group including the examination image that is selected.