Data Auditing and Quality Assurance in a Federated Learning Consortium; Getting the Best of Both Worlds from Cross-Institutional and In-House Data Quality Inspection
- 1Maastricht University
Abstract
IntroductionRare and heterogeneous disease research increasingly relies on privacy-enhancing technologies such as federated learning (FL) to enable cross-institutional collaboration across fragmented datasets. However, data quality assurance in FL can be limited, as individual-level data may not be directly accessible. While schema-dependent inspection offers a partial solution, it requires standardised schemas or resource-intensive frameworks, hindering scalability and collaboration. To address these challenges, we implemented two complementary dashboards and evaluated their interplay.
MethodologyWe adapted a recognised data quality control framework for re-use of electronic health record (EHR) data using breast cancer records from Centre Leon Berard into two dashboards: (1) an in-house dashboard for intra-clinic quality assessment, and (2) a federated dashboard for inter-clinic quality assessment. Artificial inconsistencies were introduced into distributed datasets mirroring the inhouse source to evaluate detection capabilities.
ResultsThe in-house dashboard provided granularity and reliability, pinpointing individual-level inconsistencies, while the federated dashboard enabled cross-institutional pattern detection - trade-offs inherent to their designs. The federated system revealed ecosystem-wide trends inaccessible to single-institution tools, whereas the in-house dashboard provided local validation and thoroughness.
DiscussionOur findings confirm a complementary relationship: FL dashboards provide scalable, collaborative oversight but may require additional quality checks, while in-house tools ensure thoroughness at the cost of scalability. A combined model seemingly offers the optimal balance, accommodating both institution-specific needs and collaborative research requirements in evolving, multi-institutional ecosystems.
Related
- An LLM-Based Auditing Framework for Targeted Quality Assurance in Cancer Registries
- Prediction of patient-specific quality assurance for volumetric modulated arc therapy using machine log files
- Laboratory methods and quality assurance in the National Longitudinal Study of Adolescent to Adult Health Waves V and VI
- Multidimensional Assurance of an Electronic Health Record Embedded Generative Artificial Intelligence Summarization Tool
- Real-world outcomes of mosunetuzumab use in relapsed/refractory indolent lymphomas: a CUBIC consortium analysis
BibTeX
@misc{hogenboom2026data,
title = {{Data Auditing and Quality Assurance in a Federated Learning Consortium; Getting the Best of Both Worlds from Cross-Institutional and In-House Data Quality Inspection}},
author = {J. Hogenboom and N. Perez and Q. Filori and A. Sans and A. Lobo Gomes and A. Dekker and W. van der Graaf and O. Husson and H. Crochet and L. Wee and V. Gouthamchand},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.08.26361592},
url = {https://www.medrxiv.org/content/10.64898/2026.09.08.26361592v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Data Auditing and Quality Assurance in a Federated Learning Consortium; Getting the Best of Both Worlds from Cross-Institutional and In-House Data Quality Inspection
AU - J. Hogenboom
AU - N. Perez
AU - Q. Filori
AU - A. Sans
AU - A. Lobo Gomes
AU - A. Dekker
AU - W. van der Graaf
AU - O. Husson
AU - H. Crochet
AU - L. Wee
AU - V. Gouthamchand
PY - 2026
DA - 2026/09/08
PB - medRxiv
DO - 10.64898/2026.09.08.26361592
UR - https://www.medrxiv.org/content/10.64898/2026.09.08.26361592v1
AB - IntroductionRare and heterogeneous disease research increasingly relies on privacy-enhancing technologies such as federated learning (FL) to enable cross-institutional collaboration across fragmented datasets. However, data quality assurance in FL can be limited, as individual-level data may not be directly accessible. While schema-dependent inspection offers a partial solution, it requires standardised schemas or resource-intensive frameworks, hindering scalability and collaboration. To address these challenges, we implemented two complementary dashboards and evaluated their interplay. MethodologyWe adapted a recognised data quality control framework for re-use of electronic health record (EHR) data using breast cancer records from Centre Leon Berard into two dashboards: (1) an in-house dashboard for intra-clinic quality assessment, and (2) a federated dashboard for inter-clinic quality assessment. Artificial inconsistencies were introduced into distributed datasets mirroring the inhouse source to evaluate detection capabilities. ResultsThe in-house dashboard provided granularity and reliability, pinpointing individual-level inconsistencies, while the federated dashboard enabled cross-institutional pattern detection - trade-offs inherent to their designs. The federated system revealed ecosystem-wide trends inaccessible to single-institution tools, whereas the in-house dashboard provided local validation and thoroughness. DiscussionOur findings confirm a complementary relationship: FL dashboards provide scalable, collaborative oversight but may require additional quality checks, while in-house tools ensure thoroughness at the cost of scalability. A combined model seemingly offers the optimal balance, accommodating both institution-specific needs and collaborative research requirements in evolving, multi-institutional ecosystems.
ER -