Skip to main content


Fig. 1 | BMC Medical Research Methodology

Fig. 1

From: DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network

Fig. 1

Diagram of DeepSurv. DeepSurv is a configurable feed-forward deep neural network. The input to the network is the baseline data x. The network propagates the inputs through a number of hidden layers with weights θ. The hidden layers consist of fully-connected nonlinear activation functions followed by dropout. The final layer is a single node which performs a linear combination of the hidden features. The output of the network is taken as the predicted log-risk function \(\hat {h}_{\theta }(x)\). The hyper-parameters of the network (e.g. number of hidden layers, number of nodes in each layer, dropout probability, etc.) were determined from a random hyper-parameter search and are detailed in Table 3

Back to article page