Clinical eBinder Workflow for Secure EDC Data Population
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current clinical trial data processing methods are inefficient, prone to transcription errors, and lack comprehensive systems to meet FDA requirements for electronic source data capture, while also failing to protect personal identifiable information (PII) and ensure secure data transmission and storage.
Innovation Solution
An eBinder system that automates the processing of clinical trial source data by encrypting, masking PII, converting images to machine-readable text using OCR, and utilizing NLP/GPT to populate EDC systems, ensuring secure and efficient data transfer and verification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual data entry from source data collection forms to electronic CRFs is performed, then data can be captured in EDC systems, but transcription errors occur and efficiency is extremely low
Solution Approach 1:
The patent replaces the manual mechanical process of data transcription with an automated optical character recognition (OCR) system. The OCR module captures source data directly from images or documents and converts it into machine-readable text, eliminating the need for manual typing and thereby removing transcription errors while dramatically improving data entry efficiency.
Solution Approach 2:
The patent creates an exact digital copy of source data through OCR technology. Instead of manually re-entering data, the system captures and replicates the original source data digitally, preserving accuracy while enabling efficient processing and storage in the EDC system.
2Reliability
If manual source data verification is performed by clinical research associates, then data quality can be ensured, but the process is tedious, time-consuming, and costly
Solution Approach 1:
The patent replaces manual verification by clinical research associates with an automated verification system using OCR and digital processing. The system automatically captures, converts, and validates source data against the protocol, maintaining data quality assurance while eliminating the time-consuming and costly manual verification process.
Solution Approach 2:
The system performs self-verification by automatically comparing captured source data against the study protocol and case report form requirements. This automated self-checking mechanism ensures data quality without requiring extensive manual review, significantly reducing verification time and costs.
3Productivity
If source data is transmitted and stored electronically, then efficiency is improved, but personal identifiable information must be protected according to HIPAA and GDPR
Solution Approach 1:
The patent extracts and separates personal identifiable information (PII) from the source data during the OCR processing stage. By identifying and isolating PII elements, the system can apply specific protection measures such as masking or encryption only to sensitive portions while maintaining efficient processing of the remaining clinical data.
Solution Approach 2:
The patent introduces an intermediary security layer between data storage and access. This includes implementing role-based access controls, encryption mechanisms, and audit trails that mediate between the need for efficient electronic data processing and the requirement to protect patient privacy under HIPAA and GDPR regulations.
Data Source
AI summary
The present invention provides a method and system for automatically and seamlessly processing clinical trial source data into electronic data capture (EDC) systems. In one embodiment, a file structure is defined for an electronic binder system (eBinder); source data is uploaded to the eBinder; the source data is encrypted, Patient Identifiable Information in the source data is masked; the source data is converted into machine readable plain text in the JavaScript Object Notation (JSON) format using Natural Language Processing (NPL) technologies; the JSON data is converted into tabulated machine readable data in the HyperText Markup Language (HTML) format using NPL technologies; the HTML data is converted into machine understandable data using NPL technologies; the machine understandable data is populated into EDC datasets using NPL technologies; the source data and converted data are displayed side-by-side for source data verification; and a platform is provided for regulatory data verification or auditing.


