Clinical Trial Data Recording via Generative AI EMR-to-EDC Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The integration of electronic medical record (EMR) and electronic data capture (EDC) systems is hindered by privacy concerns and human errors during manual data input, leading to inefficiencies such as source data verification (SDV) in clinical trials.
Innovation Solution
A method and system utilizing a clinical trial data management system that includes a clinical data acquisition unit, structured data generation unit, and clinical data recording unit to automatically acquire, generate structured data, and record key-value data, leveraging generative AI models like ChatGPT for data conversion and mapping.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual data input from EMR to EDC system is performed by CRC, then data transfer between systems is achieved, but human errors such as typos occur and efficiency is reduced
Solution Approach 1:
The patent replaces the mechanical manual data input process with an automated optical character recognition (OCR) system. The OCR technology captures images of data from the EMR system and automatically converts it into structured data for the EDC system, eliminating manual typing and associated errors while significantly improving data input efficiency.
Solution Approach 2:
The patent creates visual copies of the EMR data through image capture and uses OCR to extract text from these copies. This copying approach allows the system to transfer data without direct manual intervention, maintaining accuracy while improving efficiency through automated image-to-text conversion.
2Ease of operation
If manual data input is performed, then data can be transferred between EMR and EDC systems, but source data verification (SDV) procedures are required adding time consumption
Solution Approach 1:
The patent performs preliminary data capture and OCR conversion before the data transfer process. By capturing images and converting them to structured data in advance, the system prepares verified data for EDC import, eliminating the need for subsequent SDV procedures and reducing verification time.
Solution Approach 2:
The patent replaces the manual SDV process with automated OCR technology that captures and converts data with high accuracy. This substitution eliminates the need for separate verification procedures, as the automated system maintains data integrity throughout the transfer process.
3Productivity
If automated OCR and generative AI are used for data conversion, then data input efficiency is improved, but system complexity increases
Solution Approach 1:
The patent divides the data processing system into distinct functional modules: an image capture module, an OCR processing module, and a generative AI integration module. This segmentation allows each component to perform its specific function independently, improving overall processing efficiency while managing system complexity through modular design.
Solution Approach 2:
The patent introduces an intermediary structured data format that bridges the EMR and EDC systems. This intermediary format serves as a standardized interface between the OCR extraction process and the EDC data requirements, simplifying the integration of automated processing while maintaining compatibility with existing systems.
Data Source
AI summary
According to one aspect of the present invention, there is provided a method for recording clinical trial data, the method comprising the steps of: acquiring clinical trial data included in an area specified by a user; generating structured data using the clinical trial data; and recording key-value data included in the structured data as data on an item corresponding to the key.