Clinical Intervention Prediction and Understanding using Deep Networks

TL;DR

This paper develops deep learning models that integrate diverse ICU data sources to predict clinical interventions in real-time, achieving state-of-the-art accuracy and interpretability for critical care decision support.

Contribution

It introduces a comprehensive approach combining LSTM and CNN architectures for multi-intervention prediction using heterogeneous ICU data, with interpretability analysis.

Findings

Deep models outperform baselines in intervention prediction.

Models provide interpretable insights into ICU data.

Real-time predictions support clinical decision-making.

Abstract

Real-time prediction of clinical interventions remains a challenge within intensive care units (ICUs). This task is complicated by data sources that are noisy, sparse, heterogeneous and outcomes that are imbalanced. In this paper, we integrate data from all available ICU sources (vitals, labs, notes, demographics) and focus on learning rich representations of this data to predict onset and weaning of multiple invasive interventions. In particular, we compare both long short-term memory networks (LSTM) and convolutional neural networks (CNN) for prediction of five intervention tasks: invasive ventilation, non-invasive ventilation, vasopressors, colloid boluses, and crystalloid boluses. Our predictions are done in a forward-facing manner to enable "real-time" performance, and predictions are made with a six hour gap time to support clinically actionable planning. We achieve state-of-the-art results on our predictive tasks using deep architectures. We explore the use of feature occlusion to interpret LSTM models, and compare this to the interpretability gained from examining inputs that maximally activate CNN outputs. We show that our models are able to significantly outperform baselines in intervention prediction, and provide insight into model learning, which is crucial for the adoption of such models in practice.