A Deep Active Survival Analysis approach for precision treatment recommendations: Application of prostate cancer
作者：
Highlights：
• Proposed a novel survival analysis approach for high dimensional clinical data.
• Our survival analysis approach is based on deep learning and active learning.
• Developed a new sampling strategy for survival active learning.
• Applied our method on SEER-Medicare prostate cancer data for two racial groups.
• Results indicate that our method significantly improve the performance of baseline.
摘要
•Proposed a novel survival analysis approach for high dimensional clinical data.•Our survival analysis approach is based on deep learning and active learning.•Developed a new sampling strategy for survival active learning.•Applied our method on SEER-Medicare prostate cancer data for two racial groups.•Results indicate that our method significantly improve the performance of baseline.
论文关键词：Survival analysis,Deep learning,Active learning,Treatment recommendation,Electronic health records,Prostate cancer
论文评审过程：Received 10 May 2018, Revised 12 July 2018, Accepted 30 July 2018, Available online 31 July 2018, Version of Record 10 August 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.07.070
