Comparison of the performance of neural network methods and Cox regression for censored survival data

92 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Opportunities and obstacles for deep learning in biology and medicine (2017, background): “network, aimed to relax the linearity assumption, but performance gains were lacking [85].”
DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network (2016, result): “As previous research suggests, the Faraggi-Simon network has not been shown to outperform the linear CPH [10, 12, 13].”
Deep Survival : The Deep Cox Proportional Hazards Network (2016, methodology): “However, to the best of our knowledge, no research has shown that the Faraggi-Simon method outperforms the standard linear CPH [7, 8, 9].”
Time-to-Event Prediction with Neural Networks and Cox Regression (2019, unknown): “It was, however, found that the model generally failed to outperform regular Cox models (Sargent, 2001; Xiang et al., 2000).”
Predicting cancer outcomes from histology and genomics using convolutional networks (2017, methodology): “Neural network-based Cox regression approaches were explored in early machine learning work using datasets containing tens of features, but subsequent analysis found no improvement over basic linear Cox regression (28).”