Applying Cumulative Survival Functions to Age Comparison Data Sets on Breast Cancer

Abstract A comparative examination of breast cancer survival between two data sets from the Kurdistan area of Iraq and a corresponding data set from Germany is the aim of this paper. Using breast cancer data from the Kurdistan area of Iraq, both censored and unfiltered, we developed a methodology in a previous publication (2016) for predicting survival probabilities and hazard functions in a health context when a significant fraction of participants are lost to the research. This study follows earlier research (2023) where we had to use unique estimation methods to address the two Iraqi datasets' filtering problems. In particular, the data from Nanakaly hospital in the city of Erbil and Hewa hospitals in the city of Sulamani involved problems with hidden censoring affecting the survival time, leading to significant biases in survival curves generated using standard methods, and we had developed new Markov chain-based methods for generating survival curves providing adjusted Kaplan Meier analyses. Due to the availability of a reliable survival function, we chose to work with a German data set from the W. Sauerbrei Institute for Medical Biometry and Informatics, University of Freiburg—Germany. Our data analysis leads us to the conclusion that younger German women had a higher breast cancer survival rate than patients from the Kurdistan Region of Iraq.