A machine learning model to predict the risk of 30-day readmissions in patients with heart failure: a retrospective analysis of electronic medical records data

Fig. 1. Network architectures of deep neural network and deep unified networks. Demonstrates the network architecture of deep unified networks (right side) compared to deep neural networks (left side)

Fig. 2. Patient selection flowchart. Summarizes the patient selection process

Fig. 3. ROC curves of 10-fold CV. Demonstrates the ROC curve for each predictive modeling technique

Fig. 4. Layer importance of DUNs. Shows the boxplot distributions of the attention unit output (Y axis) against each layer number (X axis)

Fig. 5. Projected net savings from readmission reduction by using prediction models to select CCCP enrollees. Shows the net savings from readmission reduction, calculated by changing the number of CCCP enrollees along with the classification threshold, using the ROC curves of 10-fold CV of 1) DUNs, 2) maxout networks, 3) logistic regression, and 4) gradient boosting as shown in Fig. 3