System and method for constructing electronic data acquisition system

By building trained EDC construction models, the construction process of EDC system is automated, and the problem of time-consuming and prone to human errors in the existing technology is solved, and the rapid and accurate EDC system construction is achieved, which improves data quality and system scalability.

CN119694476APending Publication Date: 2025-03-25MEDIDATA SOLUTIONS INC
0 Cites 0 Cited by

Patent Information

Application Number
CN202411315357.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-09-22
Filing Date
2024-09-20
Publication Date
2025-03-25

AI Technical Summary

Technical Problem

Existing electronic data acquisition (EDC) systems require a lot of manual operation and expertise when designing and managing clinical trials, which leads to time-consuming, prone to human errors and inconsistencies, affecting the quality of data and the integrity of clinical trials.

Method used

By building a trained EDC construction model, the model can understand the research plan documents in text form and generate machine-readable specifications to automate the construction process of the EDC system.

Benefits of technology

It significantly reduces the time and manual operation required to set up new clinical trials in the EDC system, improves the accuracy and consistency of data structures, enhances the scalability of the system, and shortens the time to market for new therapies.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

Methods and systems for constructing an electronic data acquisition (EDC) system are disclosed. The method includes forming a training data set from a scheme document set and a corresponding EDC build. The method includes trimming the pre-trained language model using a scheme document set of the training dataset and a corresponding EDC build to generate an EDC build model. The method includes inputting the scheme document into an EDC build model to generate an EDC build prediction. The method includes generating a data structure of the EDC system based at least in part on the EDC build prediction.
Need to check novelty before this filing date? Find Prior Art