Description

The prediction of lung cancer using a Gaussian Naive Bayes classifier is a statistical approach that leverages Bayes' theorem with an assumption of normal distribution for the input features. Lung cancer prediction using Gaussian Naive Bayes(GNB) classification models aims to develop a predictive model for detecting lung cancer in patients and identify patterns and correlations. Besides that, GNB can provide accurate assessments of a patient's risk of developing lung cancer.  The dataset used various columns such as gender, age, smoking, yellow fingers, anxiety, peer pressure, chronic disease, fatigue, allergy, wheezing, alcohol consuming, coughing, shortness of breath, swallowing difficulty, chest pain, and lung cancer. This research flow begins with pre-processing, model creation, and evaluation. The accuracy result of this method is 92% which proves that this method can be declared effective in detecting lung cancer. Besides that, this method is favored for its simplicity, efficiency, and ability to handle continuous data, making it a practical tool for early lung cancer detection and diagnosis.

Link of Final Project Report and PPT for presentation: https://drive.google.com/drive/folders/1Ao5LQw75yS34buQVGWXrc_4NmrP-byvq?usp=sharing