DeepCare: A Deep Dynamic Memory Model for Predictive Medicine

Abstract

Personalized predictive medicine necessitates the modeling of patient illness and care processes, which inherently have long-term temporal dependencies. Healthcare observations, recorded in electronic medical records, are episodic and irregular in time. We introduce DeepCare, an end-to-end deep dynamic neural network that reads medical records, stores previous illness history, infers current illness states and predicts future medical outcomes. At the data level, DeepCare represents care episodes as vectors in space, models patient health state trajectories through explicit memory of historical records. Built on Long Short-Term Memory (LSTM), DeepCare introduces time parameterizations to handle irregular timed events by moderating the forgetting and consolidation of memory cells. DeepCare also incorporates medical interventions that change the course of illness and shape future medical risk. Moving up to the health state level, historical and present health states are then aggregated through multiscale temporal pooling, before passing through a neural network that estimates future outcomes. We demonstrate the efficacy of DeepCare for disease progression modeling, intervention recommendation, and future risk prediction. On two important cohorts with heavy social and economic burden -- diabetes and mental health -- the results show improved modeling and risk prediction accuracy.

Accepted at JBI under the new name: "Predicting healthcare trajectories from medical records: A deep learning approach"

References in corpus (3)

• Sequence to Sequence Learning with Neural Networks
• On the difficulty of training Recurrent Neural Networks
• Recurrent Neural Network Regularization

Cited by in corpus (25)

• Recurrent Neural Networks for Multivariate Time Series with Missing Values
• Obesity Prediction with EHR Data: A deep learning approach with interpretable elements
• Deepr: A Convolutional Net for Medical Records
• DeepHealth: Review and challenges of artificial intelligence in health informatics
• Representation Learning for Electronic Health Records
• BEHRT: Transformer for Electronic Health Records
• Improved Hierarchical Patient Classification with Language Model Pretraining over Clinical Notes
• Incorporating Biological Knowledge with Factor Graph Neural Network for Interpretable Deep Learning
• A Self-Correcting Deep Learning Approach to Predict Acute Conditions in Critical Care
• Language Models Are An Effective Patient Representation Learning Technique For Electronic Health Record Data
• Learning Hierarchical Representations of Electronic Health Records for Clinical Outcome Prediction
• Embedding Complexity In the Data Representation Instead of In the Model: A Case Study Using Heterogeneous Medical Data
• Identify Susceptible Locations in Medical Records via Adversarial Attacks on Deep Predictive Models
• Deep Learning Models to Predict Pediatric Asthma Emergency Department Visits
• Deep Ensemble Tensor Factorization for Longitudinal Patient Trajectories Classification
• DeepSoft: A vision for a deep model of software
• CovidCare: Transferring Knowledge from Existing EMR to Emerging Epidemic for Interpretable Prognosis
• Predicting Opioid Use Disorder from Longitudinal Healthcare Data using Multi-stream Transformer
• Predicting Discharge Medications at Admission Time Based on Deep Learning
• Mixed Membership Recurrent Neural Networks
• Predicting pregnancy using large-scale data from a women's health tracking mobile application
• Leveraging Disease Progression Learning for Medical Image Recognition
• Recurrent Neural Networks based Obesity Status Prediction Using Activity Data
• Predicting Unplanned Readmissions with Highly Unstructured Data
• Time-Guided High-Order Attention Model of Longitudinal Heterogeneous Healthcare Data