Deep Learning to Attend to Risk in ICU
This addresses a critical clinical problem for ICU patients by improving mortality prediction, though it is incremental as it builds on existing LSTM and attention methods.
The paper tackled the problem of predicting ICU mortality from irregular and missing physiological time-series data by proposing a deep learning architecture with layered attention mechanisms, achieving competitive results on the PhysioNet 2012 dataset.
Modeling physiological time-series in ICU is of high clinical importance. However, data collected within ICU are irregular in time and often contain missing measurements. Since absence of a measure would signify its lack of importance, the missingness is indeed informative and might reflect the decision making by the clinician. Here we propose a deep learning architecture that can effectively handle these challenges for predicting ICU mortality outcomes. The model is based on Long Short-Term Memory, and has layered attention mechanisms. At the sensing layer, the model decides whether to observe and incorporate parts of the current measurements. At the reasoning layer, evidences across time steps are weighted and combined. The model is evaluated on the PhysioNet 2012 dataset showing competitive and interpretable results.