Clinical Intervention Prediction and Understanding using Deep Networks

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.

References in corpus (7)

• Scikit-learn: Machine Learning in Python
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Learning to Diagnose with LSTM Recurrent Neural Networks
• Visualizing and Understanding Convolutional Networks
• Recurrent Neural Networks for Multivariate Time Series with Missing Values
• Deep Kalman Filters
• Multi-task Prediction of Disease Onsets from Longitudinal Lab Tests

Cited by in corpus (14)

• MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcare
• Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey
• ISeeU: Visually interpretable deep learning for mortality prediction inside the ICU
• Benchmarking Deep Learning Interpretability in Time Series Predictions
• Improving Hospital Mortality Prediction with Medical Named Entities and Multimodal Learning
• Learning Tasks for Multitask Learning: Heterogenous Patient Populations in the ICU
• Patient representation learning and interpretable evaluation using clinical notes
• Interpreting a Recurrent Neural Network's Predictions of ICU Mortality Risk
• Dropout Feature Ranking for Deep Learning Models
• Explaining Time Series Predictions with Dynamic Masks
• Identification of Pediatric Respiratory Diseases Using Fine-grained Diagnosis System
• What went wrong and when? Instance-wise Feature Importance for Time-series Models
• Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformer
• MMDF2018 Workshop Report