Developing Predictive Models for Breast Cancer Using Clinical Trial Data Sharing Platforms

Strategic Insights -

Researchers have developed a tumor growth inhibition- overall survival (TGI-OS) model for hormone receptor-positive (HR+)/human epidermal growth factor receptor 2 negative (HER2-) breast cancer using clinical trial data available through Vivli, a clinical trial data sharing platform. The TGI-OS model, a parametric model linking TGI metrics and baseline predictors of survival outcomes, showed successful internal qualification, including the prediction of the survival difference between two dose groups. The model also showed potential as a tool to support drug development decisions, despite some limitations in its ability to accurately predict overall survival.

Key Takeaways:

  • Researchers developed a TGI-OS model for HR+/HER2- breast cancer using data from the CONFIRM study, PALOMA-3, and SANDPIPER Phase 3 studies.
  • The TGI-OS model linked TGI metrics and baseline predictors of survival outcomes, showing successful internal qualification.
  • The model predicted the survival difference between two dose groups and showed potential as a tool to support drug development decisions.
  • However, the model underestimated overall survival for the PALOMA-3 study.
  • Integrating shared clinical trial data from multiple sources, facilitated by platforms like Vivli, is crucial for advancing predictive modeling efforts.
  • Caution should be exercised when such models are applied for new studies, especially when there are breakthroughs in the treatment landscape.
  • The CONFIRM study, PALOMA-3, and SANDPIPER Phase 3 studies were used to develop and qualify the TGI-OS model.
  • The model was developed using data from the CONFIRM study, which was used for model development, and the PALOMA-3 and SANDPIPER Phase 3 studies, which were used for external model qualification.

Statistics:

  • The TGI-OS model showed successful internal qualification, based on data from the CONFIRM study.
  • The model predicted the survival difference between two dose groups in the CONFIRM study.
  • The model underestimated overall survival for the PALOMA-3 study by a certain percentage (not specified in the article).
  • The CONFIRM study involved a Phase 3 comparison of fulvestrant 250 vs. 500 mg.
  • The PALOMA-3 and SANDPIPER Phase 3 studies involved the use of palbociclib and taselisib.
  • The TGI-OS model has the potential to support drug development decisions.

Sources:

  • "Disease Modeling and External Model Evaluation Through Clinical Data Sharing Platform for HR+/HER2- Breast Cancer," CPT, 2025
  • "Data on Breast Cancer Reported by Rene Bruno and Colleagues (Disease Modeling and External Model Evaluation Through Clinical Data Sharing Platform for HR+/HER2- Breast Cancer)," Information Technology Newsweekly, July 29, 2025
  • "Nature Publishing Group - www.nature.com/"
  • "CPT - www.nature.com/psp/"
  • Rene Bruno, Clinical Pharmacology, Genentech-Roche, Marseille, France