ISeeU: Visually interpretable deep learning for mortality prediction inside the ICU

Abstract

To improve the performance of Intensive Care Units (ICUs), the field of bio-statistics has developed scores which try to predict the likelihood of negative outcomes. These help evaluate the effectiveness of treatments and clinical practice, and also help to identify patients with unexpected outcomes. However, they have been shown by several studies to offer sub-optimal performance. Alternatively, Deep Learning offers state of the art capabilities in certain prediction tasks and research suggests deep neural networks are able to outperform traditional techniques. Nevertheless, a main impediment for the adoption of Deep Learning in healthcare is its reduced interpretability, for in this field it is crucial to gain insight on the why of predictions, to assure that models are actually learning relevant features instead of spurious correlations. To address this, we propose a deep multi-scale convolutional architecture trained on the Medical Information Mart for Intensive Care III (MIMIC-III) for mortality prediction, and the use of concepts from coalitional game theory to construct visual explanations aimed to show how important these inputs are deemed by the network. Our results show our model attains state of the art performance while remaining interpretable. Supporting code can be found at https://github.com/williamcaicedo/ISeeU.

References in corpus (13)

• Striving for Simplicity: The All Convolutional Net
• Learning Important Features Through Propagating Activation Differences
• Do Deep Nets Really Need to be Deep?
• Learning to Diagnose with LSTM Recurrent Neural Networks
• SOPHIE velocimetry of Kepler transit candidates XVII. The physical properties of giant exoplanets within 400 days of period
• Recurrent Neural Networks for Multivariate Time Series with Missing Values
• Do Deep Convolutional Nets Really Need to be Deep and Convolutional?
• GRAM: Graph-based Attention Model for Healthcare Representation Learning
• Investigating the influence of noise and distractors on the interpretation of neural networks
• Clinical Intervention Prediction and Understanding using Deep Networks
• Dynamic Mortality Risk Predictions in Pediatric Critical Care Using Recurrent Neural Networks
• Neural Document Embeddings for Intensive Care Patient Mortality Prediction
• Temporal Convolutional Neural Networks for Diagnosis from Lab Tests

Cited by in corpus (5)

• On Interpretability of Artificial Neural Networks: A Survey
• A New Approach for Interpretability and Reliability in Clinical Risk Prediction: Acute Coronary Syndrome Scenario
• Sequential Interpretability: Methods, Applications, and Future Direction for Understanding Deep Learning Models in the Context of Sequential Data
• A Factored Generalized Additive Model for Clinical Decision Support in the Operating Room
• ISeeU2: Visually Interpretable ICU mortality prediction using deep learning and free-text medical notes