Prediction and Segmentation of Heart Disease Boosting-Based Machine Learning Algorithms

Recent advances in imaging and sequencing technologies have led to significant advancements in clinical research on lung cancer. However, the amount of information that the human brain can properly digest and utilize is limited. Lung cancer has been extensively detailed by integrating and analyzing this vast and complex amount of data from a variety of perspectives. Machine learning-based technologies are essential to this process. This study tests multiple Boosting algorithm models on a lung cancer dataset to determine a particular lung cancer disease prediction. The aim of this work is to determine the best cross-validation methods and boosting algorithms to enhance performance in lung disease predicting. The effectiveness of the method is evaluated using a number of performance metrics, such as recall, accuracy, precision, F-score, ROC AUC score, and cross validation score. The famous Lung Cancer Dataset is used in this academic paper to test a number of machine learning classification techniques based on boosting algorithms, including Gradient Boost (GB), Extended Boost - XGBOOST (XGB), Adaptive Boost (ADABOOST), Categorized Boost (CATBOOST), and Light Gradient Boost (LGBM). many Kfold cross-validation techniques. The impact of the ADASYN as a data balancing approach on the precision of lung cancer prediction employing algorithms is investigated through hybrid combinations of cross validation and boosting procedures. This study presents a hybrid approach that could accurately predict the incidence of lung cancer. This study discovered that a hybrid integration of the Cross-validation approach with data balancing and the Boosting based ML Models built utilizing machine learning-based modeling category worked well to produce more accurate predictions regarding lung cancer.