Cancer Classification Using Gene Expression Data

Cancer poses a significant global health challenge, necessitating personalized therapeutic approaches. Genomic prediction, utilizing large-scale genomic data, has emerged as a powerful tool in cancer research. The proposed effort aims to create reliable machine learning models for cancer classification with the use of the UCI cancer dataset. The models will identify intricate patterns and correlations, enabling accurate classification of cancer subtypes and providing personalized treatment recommendations by integrating genomic and clinical data. The dataset is analyzed using machine learning techniques like k-nearest neighbors, support vector machines, random forest, and logistic regression. We found that k-neighbors classifier has an accuracy of 94.9, support vector machine has 95.6, random forest has 95.2, and logistic regression has the highest accuracy of 95.8.