RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records

Abstract

We have recently seen many successful applications of recurrent neural networks (RNNs) on electronic medical records (EMRs), which contain histories of patients' diagnoses, medications, and other various events, in order to predict the current and future states of patients. Despite the strong performance of RNNs, it is often challenging for users to understand why the model makes a particular prediction. Such black-box nature of RNNs can impede its wide adoption in clinical practice. Furthermore, we have no established methods to interactively leverage users' domain expertise and prior knowledge as inputs for steering the model. Therefore, our design study aims to provide a visual analytics solution to increase interpretability and interactivity of RNNs via a joint effort of medical experts, artificial intelligence scientists, and visual analytics researchers. Following the iterative design process between the experts, we design, implement, and evaluate a visual analytics tool called RetainVis, which couples a newly improved, interpretable and interactive RNN-based model called RetainEX and visualizations for users' exploration of EMR data in the context of prediction tasks. Our study shows the effective use of RetainVis for gaining insights into how individual medical codes contribute to making risk predictions, using EMRs of patients with heart failure and cataract symptoms. Our study also demonstrates how we made substantial changes to the state-of-the-art RNN model called RETAIN in order to make use of temporal information and increase interactivity. This study will provide a useful guideline for researchers that aim to design an interpretable and interactive visual analytics tool for RNNs.

Accepted at IEEE VIS 2018. To appear in IEEE Transactions on Visualization and Computer Graphics in January 2019

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Neural Machine Translation by Jointly Learning to Align and Translate
• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Brain Tumor Segmentation with Deep Neural Networks
• Visualizing and Understanding Recurrent Networks
• Learning to Diagnose with LSTM Recurrent Neural Networks
• Dipole: Diagnosis Prediction in Healthcare via Attention-based Bidirectional Recurrent Neural Networks
• Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
• RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records
• GRAM: Graph-based Attention Model for Healthcare Representation Learning
• Direct-Manipulation Visualization of Deep Networks
• Phenotyping of Clinical Time Series with LSTM Recurrent Neural Networks
• Exploring Dimensionality Reductions with Forward and Backward Projections

Cited by in corpus (48)

• Interpretability of machine learning based prediction models in healthcare
• Fast Parallel Hypertree Decompositions in Logarithmic Recursion Depth
• RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records
• explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning
• What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use
• A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?
• The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations
• Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologies
• Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics
• A Survey of Explainable Artificial Intelligence (XAI) in Financial Time Series Forecasting
• CarePre: An Intelligent Clinical Decision Assistance System
• DPVis: Visual Analytics with Hidden Markov Models for Disease Progression Pathways
• Time2Vec: Learning a Vector Representation of Time
• Building Interpretable Models for Business Process Prediction using Shared and Specialised Attention Mechanisms
• Diagnosing Concept Drift with Visual Analytics
• In Search of Patient Zero: Visual Analytics of Pathogen Transmission Pathways in Hospitals
• DRLViz: Understanding Decisions and Memory in Deep Reinforcement Learning
• ClinicalPath: a Visualization tool to Improve the Evaluation of Electronic Health Records in Clinical Decision-Making
• Explaining Time Series Predictions with Dynamic Masks
• Geo-Context Aware Study of Vision-Based Autonomous Driving Models and Spatial Video Data
• Modeling Long-term Dependencies and Short-term Correlations in Patient Journey Data with Temporal Attention Networks for Health Prediction
• Advancing Precision Oncology Through Modeling of Longitudinal and Multimodal Data
• Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion: A Mini-Review, Two Showcases and Beyond
• A Survey of Visual Analytics Techniques for Machine Learning
• Sequential Interpretability: Methods, Applications, and Future Direction for Understanding Deep Learning Models in the Context of Sequential Data
• DeepSI: Interactive Deep Learning for Semantic Interaction
• Progressive Disclosure: Designing for Effective Transparency
• Should We Trust (X)AI? Design Dimensions for Structured Experimental Evaluations
• What went wrong and when? Instance-wise Feature Importance for Time-series Models
• RAMPVIS: Towards a New Methodology for Developing Visualisation Capabilities for Large-scale Emergency Responses
• Survey on Visual Analysis of Event Sequence Data
• CURENet: Combining Unified Representations for Efficient Chronic Disease Prediction
• A Visual Analytics System for Multi-model Comparison on Clinical Data Predictions
• Do ML Experts Discuss Explainability for AI Systems? A discussion case in the industry for a domain-specific solution
• A Visual Analytics Framework for Explaining and Diagnosing Transfer Learning Processes
• HypperSteer: Hypothetical Steering and Data Perturbation in Sequence Prediction with Deep Learning
• VBridge: Connecting the Dots Between Features and Data to Explain Healthcare Models
• Design Patterns of Human-AI Interfaces in Healthcare
• Tempo: Helping Data Scientists and Domain Experts Collaboratively Specify Predictive Modeling Tasks
• Machine Learning on Biomedical Images: Interactive Learning, Transfer Learning, Class Imbalance, and Beyond
• ConVIScope: Visual Analytics for Exploring Patient Conversations
• VIGMA: An Open-Access Framework for Visual Gait and Motion Analytics
• Cardiac Complication Risk Profiling for Cancer Survivors via Multi-View Multi-Task Learning
• Risk factor identification for incident heart failure using neural network distillation and variable selection
• Explainable Adversarial Attacks in Deep Neural Networks Using Activation Profiles
• Comparative Visual Analytics for Assessing Medical Records with Sequence Embedding
• Visual Summary of Value-level Feature Attribution in Prediction Classes with Recurrent Neural Networks
• Revisiting the Modifiable Areal Unit Problem in Deep Traffic Prediction with Visual Analytics