Opportunities and challenges in pooling health-related quality-of-life data for prediction modeling in breast cancer across Europe: lessons from the EORTC BALANCE project

Background
Health-related quality of life (HRQoL) is a crucial outcome for cancer patients, providing a comprehensive measure of patient well-being beyond traditional clinical endpoints. While HRQoL data are increasingly available from real-world data (RWD), randomized controlled trials (RCTs), and observational studies, they remain fragmented, limiting their utility for large-scale analysis. The European Organisation for Research and Treatment of Cancer (EORTC) Quality of Life Group’s BALANCE project aims to address this by pooling and harmonizing international HRQoL datasets for breast cancer patients.

Materials and methods
This article describes the challenges of pooling international HRQoL datasets, including the process of dataset identification, acquisition, and harmonization within the BALANCE project.

Results
We successfully pooled and harmonized six datasets, representing 6500 patients and over 30 000 observations from diverse RCTs, observational studies, and RWD sources. The resulting database includes 142 variables across demographic, clinical, and HRQoL domains. Challenges included various interpretations of the General Data Protection Regulation across Europe, related to data protection and ownership. Furthermore, inconsistent data collection and resource limitations (e.g. funding or personnel) required iterative negotiations and customized harmonization. This led to the exclusion of 17 datasets containing an estimated number of 20 000-22 500 patients.

Conclusions
The BALANCE project demonstrates the feasibility of pooling international HRQoL data by overcoming key barriers and creating one of the largest HRQoL datasets for breast cancer. It lays the groundwork for upcoming publications focused on developing and validating prediction models. Future research should focus on adopting standardized data models, including secondary use clauses in consent forms, and establishing RWD registries to facilitate data sharing.