This article reviews the application of machine learning (ML) techniques in cancer prognosis and prediction. The authors highlight the importance of classifying cancer patients into high or low risk groups to facilitate clinical management. Various ML techniques, including Artificial Neural Networks (ANNs), Bayesian Networks (BNs), Support Vector Machines (SVMs), and Decision Trees (DTs), have been widely used in cancer research to develop predictive models. These models aim to improve the accuracy of cancer susceptibility, recurrence, and survival predictions. The review discusses the integration of mixed data, such as clinical and genomic information, and the challenges of external validation. It also covers the performance evaluation methods, such as sensitivity, specificity, accuracy, and Area Under the Curve (AUC). The article presents recent studies that employ ML techniques for cancer prediction, focusing on the integration of different types of data and the evaluation of model performance. Despite the promising results, the authors emphasize the need for further validation and clinical application to ensure the reliability of these models.This article reviews the application of machine learning (ML) techniques in cancer prognosis and prediction. The authors highlight the importance of classifying cancer patients into high or low risk groups to facilitate clinical management. Various ML techniques, including Artificial Neural Networks (ANNs), Bayesian Networks (BNs), Support Vector Machines (SVMs), and Decision Trees (DTs), have been widely used in cancer research to develop predictive models. These models aim to improve the accuracy of cancer susceptibility, recurrence, and survival predictions. The review discusses the integration of mixed data, such as clinical and genomic information, and the challenges of external validation. It also covers the performance evaluation methods, such as sensitivity, specificity, accuracy, and Area Under the Curve (AUC). The article presents recent studies that employ ML techniques for cancer prediction, focusing on the integration of different types of data and the evaluation of model performance. Despite the promising results, the authors emphasize the need for further validation and clinical application to ensure the reliability of these models.