Validating and Strengthen the Prediction Performance Using Machine Learning Models and Operational Research for Lung Cancer

Cancer is a condition in which abnormal cells develop uncontrollably and infest healthy cells in the body. Lung cancer causes a cell imbalance that affects the lungs. Lung cancer prediction is critical in the early stages, especially in densely populated and low-income nations. Traditional clinical techniques such as blood tests and other medicines are used by specialists. The artificial intelligence era has begun, and it is now possible to construct computer aided diagnosis mechanisms using machine learning algorithms. In this paper, we used seven machine learning algorithms IBk, AdaBoostM1, LogitBoost, Random Forest, J4S, Logistic and Support Vector Machine to predict lung cancer at early stages. For this, state-of-the-art parameters for several algorithms are assessed and evaluated on a lung cancer dataset. Accuracy as a prime parameter is evaluated and compared for all-the seven algorithms. As per experimental result, Logistic is best learning algorithm with accuracy of 93.20%. Further Saw-Score is evaluated for all the algorithms and compared. Logistic model achieved highest accuracy and saw-score in experiment conducted.