New publication in European Urology Oncology: PSA dynamics and survival

Red Door Analytics published research using joint models of longitudinal and survival data to examine associations between PSA trajectories and overall survival in patients with metastatic hormone-sensitive prostate cancer. The study found that a strong decline in PSA was associated with reduced mortality, with each doubling of the decline rate linked to a 29% lower risk of death.

Sara, a researcher on the project, discussed the work's significance. She explained that modelling the entire PSA trajectory over time provided deeper understanding compared to traditional single time-point measurements. Joint models offer advantages by linking longitudinal biomarker data with survival outcomes while accounting for individual variation and informative dropout — when patients who die stop contributing biomarker measurements.

The methodology has broader applications beyond prostate cancer. Joint models can be applied to biomarkers tracked over time across various contexts, including kidney function, blood glucose, tumour size, and quality-of-life assessments.