Lung cancer is the leading cause of cancer-related fatalities worldwide, owing mostly to its late detection and fast development.  Early and precise detection is crucial to increasing survival rates.  This research focuses on the conjecture and prediction of lung cancer using several deep learning models. Various DL architectures like CNN, GRU, LSTM and ANN are used for effective classification of lung cancer stages and types. These models were trained and evaluated using publicly available medical datasets, including radiological images and clinical data features. Feature extraction and selection techniques were applied to improve model performance and reduce overfitting. Experimental results demonstrate that deep learning models, particularly CNNs, outperform over sequential deep learning classifiers in terms of accuracy, sensitivity, and specificity. This research highlights potential of DL techniques for early speculation and diagnosis of lung cancer, paving the way for more efficient computer-aided diagnostic systems in the medical field.