LUNG CANCER FORECASTING USING HYBRID OPTIMIZATION TECHNIQUE

Abstract

Lungs are body's oxygen delivery system, controlling the in and out of breath. They also act as air filters, decreasing the potential for dust or germs to enter the lungs. The lungs have natural defences to keep them safe. Nonetheless, they are insufficient to wholly avert the development of a number of lung illnesses. The lungs are vulnerable to infection, inflammation, and possibly the development of a malignant tumor. In this study, we used ML methods to create accurate models for forecasting lung cancer occurrence and progression, so that those at high risk may receive treatment sooner rather than later. In this paper, we propose a hybrid LSTM that outperforms the state-of-the-art models using standard metrics as precision, F-Measure, recall, & accuracy. In particular, experimental assessment demonstrated that the suggested model was superior with a 98.3% accuracy, F-Measure, precision, recall.