Deepr: A Convolutional Net for Medical Records

Abstract

Feature engineering remains a major bottleneck when creating predictive systems from electronic medical records. At present, an important missing element is detecting predictive regular clinical motifs from irregular episodic records. We present Deepr (short for Deep record), a new end-to-end deep learning system that learns to extract features from medical records and predicts future risk automatically. Deepr transforms a record into a sequence of discrete elements separated by coded time gaps and hospital transfers. On top of the sequence is a convolutional neural net that detects and combines predictive local clinical motifs to stratify the risk. Deepr permits transparent inspection and visualization of its inner working. We validate Deepr on hospital data to predict unplanned readmission after discharge. Deepr achieves superior accuracy compared to traditional techniques, detects meaningful clinical motifs, and uncovers the underlying structure of the disease and intervention space.

References in corpus (9)

• Deep Learning in Neural Networks: An Overview
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Convolutional Neural Networks for Sentence Classification
• Text Understanding from Scratch
• Doctor AI: Predicting Clinical Events via Recurrent Neural Networks
• Recurrent Neural Networks for Multivariate Time Series with Missing Values
• Modeling Missing Data in Clinical Time Series with RNNs
• DeepCare: A Deep Dynamic Memory Model for Predictive Medicine
• Temporal Convolutional Neural Networks for Diagnosis from Lab Tests

Cited by in corpus (6)

• Secondary Use of Electronic Health Record: Opportunities and Challenges
• Obesity Prediction with EHR Data: A deep learning approach with interpretable elements
• GRAM: Graph-based Attention Model for Healthcare Representation Learning
• Identification of Pediatric Respiratory Diseases Using Fine-grained Diagnosis System
• Self-Attention Enhanced Patient Journey Understanding in Healthcare System
• BiteNet: Bidirectional Temporal Encoder Network to Predict Medical Outcomes