click here to download project abstract
–
ABSTRACT
Sound health is indispensable for every individual to live a robust life. To lead a
conventional and healthy life, an individual is supposed to diagnose their physiques
constantly. The lung is one of the vital organs which contributes predominantly to the
process of respiration. In particular for lung cancer, it is not well understood which
types of techniques would yield more predictive information, and which data
attributes should be used in order to determine this information. Lung carcinoma is
now mutated into a miserable routine among mankind. In accordance with the
American Cancer Society, 235,760 new instances of lung cancer are evaluated for
the year 2021 which also incorporates 131,880 deaths. It has been claimed that
cancer is curable when it is diagnosed in the initial stage. The proposed system
assists oncologist in predicting patient survival using miscellaneous machine learning
algorithms.
As part of this study, a number of supervised learning techniques were applied to the
SEER database to classify lung cancer
patients by survival, including logistic regression, decision trees, shallow neural
network, support vector machines, and an ensemble. Key data attributes were tumor
size, stage, age, genetic risk, smoker and Gender. Based on the evaluation, logistic
regression provided an accuracy of 96%. The target of the system is to estimate the
most accurate algorithm to classify the lung cancer patient survival period.
