Breast Cancer Survival Analysis and Mortality Prediction Under Different Treatment Combinations

Abstract

In this paper, a combination of breast cancer treatment procedures is considered, and its impact on breast cancer survival is precisely observed. Both statistical and neural network procedures are used to predict the breast cancer survival time. The results indicate that treatment procedures that use surgical options improve breast cancer survival. In the case of non-surgical options, hormone therapy appears to be the best. Additionally, the results suggest that radiation and chemotherapy combination lead to lower survival rates. The dataset used in this research had limited cases where the chemotherapy option was prescribed. Chemotherapy alone was a confounding cancer treatment option for non-node-positive cancer. For node-positive cancer cases, chemotherapy seems to work best where the surgery option is not considered or is viable. The experiments with neural networks show that neural networks can help predict the event of death, but these techniques could not accurately predict the length of survival.

Received: 30 September 2024 | Revised: 2 December 2024 | Accepted: 30 December 2024 

Conflicts of Interest

The authors declare that they have no conflicts of interest to this work.

Data Availability Statement

The data that support the findings of the study are openly available in GitHub at https://github.com/Parag8219/BreastCancerSurvival/blob/main/GHdata.csv.

Author Contribution Statement

Parag C. Pendharkar: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Supervision, Project administration. James A. Rodger:  Investigation, Resources, Data curation.