Abstract
PURPOSE An accurate risk model is critical for risk-stratified cancer care and delivery. We developed a survival decision tree (SDT) model as a risk stratification tool to categorize patients into distinct groups and compared the model performance with other methods through a benchmarking design. METHODS Data were obtained from the Northwell Health cancer registry for patients with breast cancer who were initially diagnosed and first seen at one of the nine Northwell facilities between 2018 and 2021. The SDT model was constructed to segment patients into different risk groups, and their recurrence-free survival (RFS) probabilities were compared using the log-rank test. We compared the SDT with the Cox proportional hazards model and random survival forest (RSF). Model performance was assessed using the c-index, calibration intercept and slope, and integrated Brier score. RESULTS A total of 5,919 patients diagnosed with invasive breast cancer were analyzed, and four risk groups were identified: low risk, medium risk, high risk, and very high risk. There was a significant difference in RFS across groups ( P < .001). The pruned SDT model showed similar or better performance than the benchmarking methods; however, the RSF may be useful in the subgroup of patients with two or more comorbidities, where a more complex relationship may exist. CONCLUSION Risk stratification can be accurately modeled via a tree-based method. Future research should layer in other outcomes, such as comorbidity, ongoing treatment toxicities, or risk of delayed treatment, to improve risk-stratified care and effective use of health care resources.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call