DeephitTM:a Time-dependent Deep Learning Model for Medical Survival Analysis
Survival analysis is a health prediction method often used in medicine.More and more scholars start to use deep learning method to model survival analysis problems to get better prediction results.Currently,existing methods assume that the joint probability of risk and time is uncorrelated,but the actual results of survival analysis data contain time factors,which cannot guarantee that the risk probability obtained at different times is uncorrelated.This paper proposes a time-dependent deep learning model,DeephitTM,to improve the existing deep learning model Deephit.Experimental results show that the performance of our model can be improved by 1 to 3 percentage points compared with the original model on different data sets.
万方数据
维普
