• Regina Lourdhu Suganthi

The human body is made up of trillions of basic units called ‘Cells’. These cells tend to grow and divide during our lifetime in order to form new cells based on the body’s requirement. Cancer begins when genetic mutations that interfere this normal process and cells begin to grow uncontrollably. There are more than hundred distinct types of cancer that causes the death of nearly Ten million people around the world. Cancer can develop anywhere in the body and the particular type of cancer is named after the part of the body where it originated. Esophageal cancer develops in the cells on the inner lining of the long, hollow tube that transports food and liquid from the throat to the stomach called esophagus and starts spreading outward through the other layers of the esophagus. It is one of the top six common cancer types that cause death worldwide. This study focuses on survival analysis of the patients prone to esophageal cancer with the help of Machine Learning Techniques. The dataset used is clinical data on Esophageal/Stomach cancer. The relevant features such as mutation count, Microsatellite instability (MSI) score, tumor grade and tumor purity are used for the analysis. Machine Learning algorithms namely Support Vector Machines, K-Nearest Neighbor, Decision Tree and Random Forest are applied on this clinical data to train the binary classification models that predict the likelihood of death of a patient. These models are then evaluated using performance metrics like precision, recall, specificity and F1 score for presenting a comparative study of the Machine Learning algorithms.

Esophageal Cancer, Machine Learning, Binary Classification, Survival Analysis, Support Vector Machines, K-Nearest Neighbor, Decision Tree, Random Forest

"COMPARATIVE STUDY OF MACHINE LEARNING ALGORITHMS FOR ESOPHAGEAL CANCER SURVIVAL ANALYSIS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 4, page no.b458-b463, April-2022, Available :http://www.jetir.org/papers/JETIR2204162.pdf

"COMPARATIVE STUDY OF MACHINE LEARNING ALGORITHMS FOR ESOPHAGEAL CANCER SURVIVAL ANALYSIS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 4, page no. ppb458-b463, April-2022, Available at : http://www.jetir.org/papers/JETIR2204162.pdf