ICU Outcome Prediction
PhysioNet 2012 Dataset and the mTAND Architecture
The PhysioNet dataset is on predicting patient mortality rates in ICU
Only 4000 datapoints
Up to 42 variables
Six of these variables are general descriptors (collected on admission)
Remainder are time series, for which multiple observations may be available.
Multi-Time Attention Networks for Irregularly Sampled Time Series (mTAND)
State of the art open source architecture on the PhysioNet Dataset at time of test
Perforated Backpropagation overfit when added to initial architecture
We then increased and decreased the width of the layers of the network by a constant factor X, giving “Net X” in the graph
No modifications were made to depth or anything else in the training pipeline
Graph shows Test AUC scores which is the metric used on the PhysioNet competition leaderboard, along with parameter counts of each network
Doubling the network width has very small effect on accuracy
Reducing width and adding Perforated AI reduced network to 9.3% the initial size while improving accuracy by 4%!
Each point shows the AUC score as cycles are run
