Real-World Data Linkage Research Platform
Trial statusNot yet recruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
AgeNot listed
SponsorBeijing Friendship Hospital
About this trial
This study aims to address the lack of intelligent governance tools in clinical data management to promote efficient governance and secure sharing of real-world health data. To achieve this, a self-adaptive, automated governance intelligent agent will be developed based on a High-Order Programming (HOP) architecture, integrating Large Language Models (LLMs) and deep learning techniques. The agent will continuously monitor and correct data quality issues in real time, improving data accuracy and usability.
In parallel, the project will establish a trusted data-sharing framework by integrating AI Confidential Computing (AICC) with Trusted Data Matrix (TDM) technologies. This framework will enable secure, real-time cross-institutional data exchange and collaborative computation while protecting sensitive information.
Overall, the study aims to transform fragmented clinical data into high-quality, standardized, and securely accessible resources, thereby facilitating the circulation of data value and advancing collaborative medical research.
Eligibility criteria
This trial accepts healthy volunteersQualifiers
Availability of any health-related data generated from routine clinical care, health examinations, or disease surveillance systems, regardless of disease type or health status.
Presence of at least one type of usable data, including but not limited to diagnostic information (structured or unstructured), laboratory results, imaging data, or basic demographic information.
Records contain sufficient information (appropriately anonymized) to allow data organization and, where feasible, linkage at the individual level across time points or data sources.
Disqualifiers
Records lacking minimal essential information required to distinguish individual records or support basic analysis (e.g., completely missing identifiers or time information).
Records confirmed to be invalid, including system-generated test data, corrupted entries, or records that do not represent real clinical or health-related events.
Exact duplicate records that cannot be resolved through standard data processing (only one record will be retained when duplicates are identifiable).
Trial population
This study establishes a multicenter, observational real-world data platform integrating longitudinal health data from multiple sources across China, including routine health examinations, electronic medical records, and disease registries. The platform is designed to support population-level research without restriction to specific diseases or conditions, enabling inclusive and continuous assessment of health status, disease risk, progression, and outcomes in real-world settings. All available individuals with usable health-related data are eligible for inclusion, with minimal restrictions to maximize data coverage and representativeness. Both retrospective and prospective data will be incorporated and linked at the individual level using standardized protocols within a secure data governance and privacy protection framework.
Trial design
Design model
Cohort
Time perspective
Retrospective
Treatments tested in this trial
This is an observational study. No intervention will be applied.
Other interventionThis is an observational study. No intervention will be applied.
Treatment groups
300,000 Participants
are divided into 1 treatment groupGroup A: Data-Link Cohort1 intervention
Trial outcomes
Primary outcomes
1
Accuracy Rate of Automated Data Governance
Using a manually curated gold-standard dataset, the effectiveness of the intelligent agent in improving data accuracy will be evaluated by measuring the proportion of data values that correctly match the gold-standard reference after automated data governance. The accuracy rate will be calculated as the percentage of correctly recorded or corrected data elements among all evaluated data elements. Values range from 0% to 100%, with higher values indicating better data accuracy.
Time frame
2026.5.30 to 2028.12.312
Completeness Rate of Automated Data Governance
Using a manually curated gold-standard dataset, the effectiveness of the intelligent agent in improving data completeness will be evaluated by measuring the proportion of required data fields that are complete after automated data governance. The completeness rate will be calculated as the percentage of non-missing required data elements among all required data elements. Values range from 0% to 100%, with higher values indicating better data completeness.
Time frame
2026.5.30 to 2028.12.31Secondary outcomes
1
Correction Accuracy of Automated Data Governance
Using a manually curated gold-standard dataset, the effectiveness of the intelligent agent in resolving identified data quality issues will be evaluated by measuring correction accuracy. Correction accuracy will be calculated as the percentage of identified data quality issues (e.g., missing values, format inconsistencies, and logical conflicts) that are correctly resolved after automated data governance, compared with the gold-standard reference dataset. Values range from 0% to 100%, with higher values indicating better correction performance.
Time frame
2026.5.30 to 2028.12.312
Data Standardization Rate of Automated Data Governance
Using a manually curated gold-standard dataset, the effectiveness of the intelligent agent in standardizing data will be evaluated by measuring the proportion of data elements that conform to predefined data standards, terminologies, and formatting rules after automated data governance. The data standardization rate will be calculated as the percentage of evaluated data elements that meet standardized data specifications among all assessed data elements. Values range from 0% to 100%, with higher values indicating better data standardization.
Time frame
2026.5.30 to 2028.12.313
Cross-institutional Data Usability of Automated Data Governance
Using datasets derived from participating institutions, the effectiveness of the intelligent agent in improving cross-institutional data usability will be evaluated by measuring the proportion of governed datasets that can be successfully integrated, interpreted, and used across different institutions according to predefined interoperability and usability criteria after automated data governance. Cross-institutional data usability will be calculated as the percentage of datasets meeting prespecified usability criteria among all evaluated datasets. Values range from 0% to 100%, with higher values indicating better cross-institutional usability.
Time frame
2026.5.30 to 2028.12.31Sponsors and contacts
Click on the lead sponsor to view all of their trials.
Beijing Friendship Hospital
Lead sponsor
Shenzhen Third People's Hospital
Collaborator
First Affiliated Hospital Xi'an Jiaotong University
Collaborator
Source ClinicalTrials.gov
This trial is not recruiting at the moment. You can still explore other options: