Lung Cancer Prediction Model to Improve Survival Rates

Abstract

The truth that lung cancer is still the essential cause of cancer-related fatalities around the world emphasizes how critical early distinguishing proof is. This paper utilizes machine learning methods to reckon the chance of lung cancer from persistent information, such as socioeconomics, therapeutic history, and imaging outcomes. The framework utilizes calculations, counting calculated relapse, choice trees, and bolster vector machines, with the objective of making strides in demonstrative accuracy and speeding up incite mediation. To ensure the model's steadfastness in clinical settings, its execution is surveyed utilizing measures counting exactness, exactness, and review. This strategy of treating lung cancer has the potential to improve understanding results and early discovery rates.