Figure 3.

Architecture of proposed LSTM-based model

The concatenation of the medical event embedding vectors ($v_1,v_2,\cdots ,v_n$) and the corresponding time encoding vectors ($e_1,e_2,\cdots ,e_n$) are inputs to the BiLSTM model, which generates output vectors ($h_1,h_2,\cdots ,h_n$). All the output vectors are concatenated, then a global max pooling operation is performed to produce the patient representation vector. Finally, a fully connected layer and the sigmoid function are used to predict the probability of sepsis onset in the next 4 h.