Using machine learning, general regression, and Cox proportional hazards regression to predict the effectiveness of treatment in patients with breast cancer.

The objective of this feasibility study is to introduce machine learning algorithms in the combination of general regression and cox proportional hazards regression to predicate the outcome of disease management. By using the delay in the receipt of adjuvant chemotherapy and SEER-Medicare databases as proof-of-principle, we conclude that general regression and Cox proportional hazards regression following the feature selection could identify factors that predict the delay and the impact of delay on survival outcome.