Deep Mixed Effect Model using Gaussian Processes: A Personalized and Reliable Prediction for Healthcare
arXiv:1806.01551
Abstract
We present a personalized and reliable prediction model for healthcare, which can provide individually tailored medical services such as diagnosis, disease treatment, and prevention. Our proposed framework targets at making personalized and reliable predictions from time-series data, such as Electronic Health Records (EHR), by modeling two complementary components: i) a shared component that captures global trend across diverse patients and ii) a patient-specific component that models idiosyncratic variability for each patient. To this end, we propose a composite model of a deep neural network to learn complex global trends from the large number of patients, and Gaussian Processes (GP) to probabilistically model individual time-series given relatively small number of visits per patient. We evaluate our model on diverse and heterogeneous tasks from EHR datasets and show practical advantages over standard time-series deep models such as pure Recurrent Neural Network (RNN).
arXiv commentAAAI 2020
References in corpus (11)
- Prototypical Networks for Few-shot Learning
- Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
- Scalable Variational Gaussian Process Classification
- Modeling Missing Data in Clinical Time Series with RNNs
- An Improved Multi-Output Gaussian Process RNN with Real-Time Validation for Early Sepsis Detection
- A Framework for Individualizing Predictions of Disease Trajectories by Exploiting Multi-Resolution Structure
- Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier
- Improving Output Uncertainty Estimation and Generalization in Deep Learning via Neural Network Gaussian Processes
- Sparse Multi-Output Gaussian Processes for Medical Time Series Prediction
- Personalized Gaussian Processes for Future Prediction of Alzheimer's Disease Progression
- Personalized Risk Scoring for Critical Care Patients using Mixtures of Gaussian Process Experts