A deep survival analysis method based on ranking

作者：

Highlights：

• The proposed RankDeepSurv is superior to three state-of-the-art survival models.

• This paper proposes a loss function based on regression and rank constraints for survival analysis.

• RankDeepSurv and the Cox proportional hazard model used by clinicians to predict the recurrence of nasopharyngeal carcinoma. RankDeepSurv shows better concordance index in clinical practice.

• The nasopharyngeal carcinoma data set is published by this paper.

摘要

•The proposed RankDeepSurv is superior to three state-of-the-art survival models.•This paper proposes a loss function based on regression and rank constraints for survival analysis.•RankDeepSurv and the Cox proportional hazard model used by clinicians to predict the recurrence of nasopharyngeal carcinoma. RankDeepSurv shows better concordance index in clinical practice.•The nasopharyngeal carcinoma data set is published by this paper.

论文关键词：Survival analysis,Prognosis,Neural networks,Nasopharyngeal carcinoma

论文评审过程：Received 30 September 2018, Revised 15 April 2019, Accepted 5 June 2019, Available online 6 June 2019, Version of Record 12 June 2019.

论文官网地址：https://doi.org/10.1016/j.artmed.2019.06.001