Background: Cancer treatment is expensive and results in a lot of side effects, and thus survival prediction is necessary for the patients as well as the clinician. Data mining technology has been used in the medical domain to extract interesting information. Cancer prognosis is such an application in medicine.

Objective: This study focuses on identifying the technologies used in the recent past for predicting the survival of cancer patients. Supervised, semi-supervised and unsupervised techniques have been used over the years successfully for the survival prediction of different types of cancer.

Methods: A systematic literature review process has been followed in this study to discover the future directions of the research. This study focuses on uncovering the gaps in recent studies.

Results and Conclusion: It has been found that the present system lacks structured information of the patients. Also, there are a lot of different cancer types that are still unexplored in terms of survival prediction, mainly due to the unavailability of sufficient data. Hence a lot can be improved if researchers may get their hands on required data for the research.

背景：癌症治疗费用昂贵并且会导致许多副作用，因此对于患者以及临床医生而言，生存预测都是必要的。数据挖掘技术已在医学领域用于提取有趣的信息。癌症预后在医学中是这样的应用。

目的：本研究致力于确定最近用于预测癌症患者存活率的技术。多年来，已成功使用监督，半监督和无监督技术来预测不同类型癌症的生存率。

方法：本研究遵循系统的文献综述过程，以发现研究的未来方向。这项研究的重点是发现最近研究中的差距。

结果与结论：已经发现，本系统缺乏患者的结构化信息。同样，在生存预测方面，仍有许多不同类型的癌症尚待探索，这主要是由于缺乏足够的数据所致。因此，如果研究人员可以掌握研究所需的数据，则可以大大改善。