The value of post radiotherapy prostate specific antigen dynamics for prostate cancer risk stratification models

Background and purpose Risk-stratification at diagnosis of prostate cancer does not always predict risk of biochemical recurrence (BCR). Fully utilizing post-radiotherapy follow-up Prostate Specific Antigen (PSA) data could offer earlier and higher prognostic value than pre-treatment risk-stratification. We investigate whether PSA dynamics in the first three-years of follow-up can re-stratify risk of treatment failure after radical radiotherapy, allowing for targeted intervention. Materials and methods Retrospective analysis of repeat follow-up PSA measurements from men with mixed-risk prostate cancer treated in two separate radical radiotherapy techniques (n = 446, 2005–2007). PSA trajectories were modelled between zero and three-years follow-up using Gaussian Process regression. Models were sampled and clustered using hierarchical clustering to define characteristic post-radiotherapy PSA trajectories. Kaplan-Meier analysis compared dichotomising by pre-treatment risk-group and characteristic PSA trajectory. Cox proportional-hazard models with and without follow-up PSA information compared using Akaike Information Criterion (AIC). Results PSA trajectories were characterized as stable, steady-rise, and unstable. Kaplan-Meier analysis showed that pre-treatment risk-group was not prognostic of BCR (p > 0.05), however characteristic PSA trajectory was (p < 0.001). PSA trajectory improved multivariable model performance when added to baseline prognostic variables. Unstable PSA had highest BCR. Results were validated across two cohorts and sensitivity analysis, suggesting results were robust. However, analysis excluded patients with BCR within three-years follow-up due to lack of data. Conclusion PSA dynamics within the first three-years of post-radiotherapy follow-up for prostate cancer were more prognostic of BCR than pre-treatment risk-groups, suggesting PSA dynamics could be used to re-stratify BCR risk during early follow-up.