Machine Learning for Survival Analysis: A Survey

被引:353
作者
Wang, Ping [1 ]
Li, Yan [2 ]
Reddy, Chandan K. [1 ]
机构
[1] Virginia Tech, Dept Comp Sci, 900 N Glebe Rd, Arlington, VA 22203 USA
[2] Alibaba DAMO Acad, Machine Intelligence Res Sect, 500 108th Ave NE, Bellevue, WA 98004 USA
基金
美国国家科学基金会;
关键词
Machine learning; survival analysis; censoring; regression; hazard rate; Cox model; concordance index; survival data; ARTIFICIAL NEURAL-NETWORKS; CUSTOMER LIFETIME VALUE; VARIABLE SELECTION; PROGNOSTIC-FACTORS; BREAST-CANCER; CENSORED-DATA; REGRESSION; MODEL; REGULARIZATION; PREDICTION;
D O I
10.1145/3214306
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Survival analysis is a subfield of statistics where the goal is to analyze and model data where the outcome is the time until an event of interest occurs. One of the main challenges in this context is the presence of instances whose event outcomes become unobservable after a certain time point or when some instances do not experience any event during the monitoring period. This so-called censoring can be handled most effectively using survival analysis techniques. Traditionally, statistical approaches have been widely developed in the literature to overcome the issue of censoring. In addition, many machine learning algorithms have been adapted to deal with such censored data and tackle other challenging problems that arise in real-world data. In this survey, we provide a comprehensive and structured review of the statistical methods typically used and the machine learning techniques developed for survival analysis, along with a detailed taxonomy of the existing methods. We also discuss several topics that are closely related to survival analysis and describe several successful applications in a variety of real-world application domains. We hope that this article will give readers a more comprehensive understanding of recent advances in survival analysis and offer some guidelines for applying these approaches to solve new problems arising in applications involving censored data.
引用
收藏
页数:36
相关论文
共 134 条
[1]   NONPARAMETRIC INFERENCE FOR A FAMILY OF COUNTING PROCESSES [J].
AALEN, O .
ANNALS OF STATISTICS, 1978, 6 (04) :701-726
[2]  
Allison Paul., 2010, Survival Analysis Using SAS
[3]   Survival Analysis based Framework for Early Prediction of Student Dropouts [J].
Ameri, Sattar ;
Fard, Mahtab J. ;
Chinnam, Ratna B. ;
Reddy, Chandan K. .
CIKM'16: PROCEEDINGS OF THE 2016 ACM CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2016, :903-912
[4]  
Andersen K., 2012, Statistical Models Based on Counting Processes
[5]  
[Anonymous], 2005, Survival Analysis: Techniques for Censored and Truncated Data
[6]  
[Anonymous], 2011, Survival analysis
[7]  
[Anonymous], 2006, Survival Analysis: A Self-Learning Text
[8]  
[Anonymous], 2016, STAT-US
[9]   PPISURV: a novel bioinformatics tool for uncovering the hidden role of specific genes in cancer survival outcome [J].
Antonov, A. V. ;
Krestyaninova, M. ;
Knight, R. A. ;
Rodchenkov, I. ;
Melino, G. ;
Barlev, N. A. .
ONCOGENE, 2014, 33 (13) :1621-1628
[10]  
Ata N, 2007, HACET J MATH STAT, V36, P157