Deep EHR: Chronic Disease Prediction Using Medical Notes

Abstract

Early detection of preventable diseases is important for better disease management, improved inter-ventions, and more efficient health-care resource allocation. Various machine learning approacheshave been developed to utilize information in Electronic Health Record (EHR) for this task. Majorityof previous attempts, however, focus on structured fields and lose the vast amount of information inthe unstructured notes. In this work we propose a general multi-task framework for disease onsetprediction that combines both free-text medical notes and structured information. We compareperformance of different deep learning architectures including CNN, LSTM and hierarchical models.In contrast to traditional text-based prediction models, our approach does not require disease specificfeature engineering, and can handle negations and numerical values that exist in the text. Ourresults on a cohort of about 1 million patients show that models using text outperform modelsusing just structured data, and that models capable of using numerical values and negations in thetext, in addition to the raw text, further improve performance. Additionally, we compare differentvisualization methods for medical professionals to interpret model predictions.

arXiv commentMachine Learning for Health Care conference

References in corpus (7)

• Scikit-learn: Machine Learning in Python
• Convolutional Neural Networks for Sentence Classification
• Learning to Diagnose with LSTM Recurrent Neural Networks
• StarSpace: Embed All The Things!
• Multi-Label Classification of Patient Notes a Case Study on ICD Code Assignment
• Temporal Convolutional Neural Networks for Diagnosis from Lab Tests
• ShortFuse: Biomedical Time Series Representations in the Presence of Structured Information

Cited by in corpus (11)

• Deep Representation Learning of Patient Data from Electronic Health Records (EHR): A Systematic Review
• Improving Hospital Mortality Prediction with Medical Named Entities and Multimodal Learning
• Identification of Pediatric Respiratory Diseases Using Fine-grained Diagnosis System
• DeepHealth: Review and challenges of artificial intelligence in health informatics
• Improved Hierarchical Patient Classification with Language Model Pretraining over Clinical Notes
• Identifying Risk of Opioid Use Disorder for Patients Taking Opioid Medications with Deep Learning
• Dynamically Extracting Outcome-Specific Problem Lists from Clinical Notes with Guided Multi-Headed Attention
• Characterizing the Value of Information in Medical Notes
• Analysing Risk of Coronary Heart Disease through Discriminative Neural Networks
• SAVEHR: Self Attention Vector Representations for EHR based Personalized Chronic Disease Onset Prediction and Interpretability
• Improving Clinical Outcome Predictions Using Convolution over Medical Entities with Multimodal Learning