Personalized Cancer Drug Recommendation using GAN and Explainable AI

Through more accurate medication recommendations and increased treatment efficacy, machine learning has improved personalized cancer therapy. To support the treatment recommendation system for lung cancer, the study uses a Conditional Tabular Generative Adversarial Network (CTGAN) to generate synthetic patient data. Machine learning algorithms process data to recommend appropriate medications while LightGBM demonstrates superior performance to XGBoost by achieving 0.82 accuracy. Explainable AI (XAI) techniques produce greater transparency while supplying doctors with expanded treatment information. This approach aims to enhance patient treatment outcomes while establishing trust in AI-driven medical advice.