A Stacking Approach Based on Machine Learning Techniques for Lungs Cancer Prediction in Healthcare Systems

Lung cancer poses a serious risk to life and causes death of both males and females in the world. Survival rate and reduced death rate can be improved if breathed at the first stage. The proposed approach utilizes machine-learning techniques such as ensemble learning techniques known as stacking to enhance the predictive accuracy of a classification model. The methodology used dataset downloaded from Kaggle website, which contain 16 attributes and 309 records. We divide the dataset into train and test sets. The model is train the multiple diverse base models, by using various algorithms, such as Random Forest, AdBoost, SVM, Decision Tree are used as base models are then employed to generate predictions on a validation dataset. Subsequently, a meta-model, exemplified by Logistic Regression, will train from base model predictions. By taking the outputs of the base models used as input for the meta-model, the ensemble stacking classifier creates a more robust and accurate model. The effectiveness of this ensemble or Stacking model or Lung cancer diagnosis (SLCD) will demonstrate through evaluating its performance on a testing dataset, resulting in an accuracy score that validates its potential to enhance predictive outcomes compared to individual models. The approach serves as a practical strategy that will leverage the strengths of the Stacking Lung Cancer diagnosis (SLCD) model to achieve superior predictive performance and will predict whether lung cancer is present or not in both males and females. The performance of our model will be measured by using performance matrices such as accuracy, precision, recall, F1 Scope. The propose model will easily incorporating in Electronic-healthcare systems for early diagnosis Lung cancer to ensure proper treatment and recovery.