Automated EDC Build Model for Clinical Trial Setup

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The existing Electronic Data Capture (EDC) system setup process is time-consuming, labor-intensive, and prone to human errors, delaying clinical trials and compromising data quality.

Innovation Solution

An EDC build model is trained to understand study protocol documents in textual form and generate a machine-readable specification for the EDC system, automating the process of creating data structures such as electronic case report forms, edit checks, and folder structures.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If manual processes are used to design and configure EDC systems for each clinical trial, then flexibility and customization to specific study requirements can be achieved, but the process becomes time-consuming (8-10 weeks) and labor-intensive

Engineering Contradiction:

Improvecustomization to study requirementsVSAvoidsetup speed

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The system creates templates from previously executed clinical trials that capture standard EDC configurations. These templates can be copied and adapted for new trials, preserving customization needs while dramatically reducing setup time from 8-10 weeks to a fraction of that time.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The system performs preliminary analysis of study protocol documents using NLP to automatically extract trial-specific requirements and pre-configure EDC system parameters, data structures, and validation rules before the manual setup phase begins, reducing the actual configuration time needed.

Inventive Principle:

Principle #10Preliminary action

2Adaptability or versatility

If manual configuration is used to adapt EDC systems to diverse trial requirements, then customization capability is maintained, but human errors and inconsistencies increase

Engineering Contradiction:

Improvestudy-specific configurationVSAvoiddata quality

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system incorporates automated validation that continuously checks configured EDC parameters against the study protocol requirements, providing feedback loops that identify and correct inconsistencies or errors before data collection begins, ensuring both customization and data quality.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system replaces manual manual configuration activities with automated NLP-based extraction and configuration processes that read study protocols and automatically generate appropriate EDC settings, eliminating human error while maintaining the ability to adapt to diverse trial requirements.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Extent of automation

If standardized approaches like CDISC standards are implemented, then some automation is achieved, but the process still relies heavily on manual effort and does not fully resolve the time-consuming nature of EDC setup

Engineering Contradiction:

Improvestandardization levelVSAvoidsetup duration

Core Design Contradiction:

Extent of automationVSLoss of time

Solution Approach 1:

The system uses dynamic NLP processing to adaptively extract and configure EDC parameters based on the specific content of each study protocol, going beyond static standardization to provide intelligent, context-aware automation that reduces setup time while maintaining accuracy.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system automatically adjusts EDC configuration parameters based on extracted study characteristics, transforming the static template configuration process into a dynamic, protocol-driven automation that significantly reduces manual intervention time while maintaining study-specific customization.

Inventive Principle:

Principle #35Parameter changes

4Reliability

If conventional manual methods are used to implement real-time data validation rules, then data quality control is achieved, but the process requires careful design and testing that extends the already lengthy setup timeline

Engineering Contradiction:

Improvedata validationVSAvoidvalidation implementation time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary extraction of validation requirements from study protocols and pre-configures real-time validation rules during the automated setup phase, so that validation capabilities are already in place when data collection begins, eliminating the need for separate validation implementation and testing phases.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentEP4530920A1Systems and methods for building an electronic data capture system

Publication Date: 2025.04.02 MEDIDATA SOLUTIONS INC

Figure 1
Figure 2
Figure 3

AI summary

Disclosed are methods and systems for building an electronic data capture (EDC) system. The method includes forming a training dataset from a set of protocol documents and corresponding EDC builds. The method includes using the set of protocol documents and corresponding EDC builds of the training dataset to fine tune a pre-trained language model to produce an EDC build model. The method includes inputting a protocol document to the EDC build model to produce an EDC build prediction. The method includes generating data structures of the EDC system based at least in part on the EDC build prediction.