Efficient Machine Learning Techniques to Predict Lung Cancer
Rahul Deb Mohalder, Juliet Polok Sarkar, Khandkar Asif Hossain, Laboni Paul, M. Raihan · 2022
One of the most difficult to diagnose and one of the deadliest diseases is lung cancer. A big reason for this is that it takes a long time to identify at an early stage. For treatment, a rapid and precise diagnosis of nodules is very crucial. In order to identify cancer in its early stages, a variety of techniques have been employed. Machine learning approaches were used in this work in order to identify lung cancer nodules. We used machine learning algorithms such as LightGBM, XGBoost, K-Nearest Neighbors, Support Vector Machines, Naïve Bayes, and Random Forest to discover anomalous data. We compared all of the approaches. The results of the experiments reveal that LightGBM produces the greatest outcomes with 99.91 percent accuracy, 0.001261 loss and XGBoost outcomes with 99.86 percent accuracy, 0.001446 loss.