Enhancing Lung Cancer Detection by Leveraging Machine Learning Algorithms

With concerning incidence rates, lung cancer continues to be a worldwide health emergency that necessitates efficient detection techniques to enhance patient outcomes. In order to stop the progression of the disease, lower mortality, and raise survival rates, early and precise diagnosis is essential. However, because of the non-intuitive correlation between characteristics like lymph node involvement and cancer diagnosis, it can be difficult to detect cancer in its early stages, even for skilled medical professionals. To overcome these obstacles, this work uses machine learning approaches. For the categorization of lung cancer, it uses algorithms such as Support Vector Machine, Logistic Regression, Naïve Bayes, k-Nearest Neighbors, and Decision Tree. These algorithms use a variety of features to analyzedata and detect the presence of cancer; preprocessing techniques like data slicing and feature scaling are applied. Performance matrices like accuracy, precision, recall and f1 score were taken into consideration. Support Vector machine outperformed other models by achieving an accuracy of 94% along with precision of 92% and recall being 97%. The outcomes highlight SVM's effectiveness in offering trustworthy diagnostic information. In order to effectively tackle this deadly disease, our study not only exhibits the promise of machine learning in early cancer diagnosis and also lays the groundwork for incorporating such approaches into clinical workflows.