Data mining and machine learning in cancer survival research: An overview and future recommendations

Data mining and machine learning techniques are transforming the decision-making process in the medical world. From using nomograms and expert advice, scientists are now moving towards machine learning and deep learning techniques to make informed decisions for patients. The change in this aspect is mainly attributed to large amounts of digital data stored in hospitals. This study is focused on the transformation of cancer survival research in the past few years. A road map based on seven different aspects has been provided in this study utilizing various machine learning techniques, presenting a review of 62 articles published in the past 15 years. It was found that researchers are now moving to more clinical data even with less number of instances. Though most of the studies used traditional machine learning techniques for predicting cancer survival, researchers are now moving towards deep learning and hybrid approaches to gain some insights into survival prediction. Finally, this study presents ten new open research issues and possible future research plans to focus on for better results in cancer survival research. It is hoped that this review will be viewed by both apprentice and expert researchers as a valuable resource to understand the currently used practices and possible future recommendations to work.