Fig 1.
Total number of records for each hospital under study, and their respective readmission rates.
Fig 2.
Data breakdown by hospital admission year.
Table 1.
summary of the population under study.
Table 2.
Summary of extracted feature categories, and two sample features per category.
Fig 3.
Neural Network model architecture (Note: Layer sizes are assuming all features are used).
Fig 4.
Comparison of NN model performance (with retrospective validation) vs number of features.
Table 3.
Top most correlated features with 30-day readmission.
Table 4.
Comparison of the performance of our models with that of LACE, assuming a 25% intervention rate.
Table 5.
Performance of our model versus LACE on 2015 data when trained on data through 2014.
Fig 5.
Comparison of artificial neural network model with LACE in 4 different age brackets.
Fig 6.
Comparison of the model performance among top five Sutter Health hospitals by the number of inpatient records.
Fig 7.
Comparison of the neural network model’s performance among subgroups with varying medical conditions.
Table 6.
Comparison of performance of each feature group on the neural network model, tested by withholding one feature group at a time and measuring the impact on model AUC.
Fig 8.
The projected saving values as a function of the intervention rate, with the example parameters given for the cost-savings analysis in the results section.