Nonstationary Multivariate Gaussian Processes for Electronic Health Records
arXiv:1910.05851
Abstract
We propose multivariate nonstationary Gaussian processes for jointly modeling multiple clinical variables, where the key parameters, length-scales, standard deviations and the correlations between the observed output, are all time dependent. We perform posterior inference via Hamiltonian Monte Carlo (HMC). We also provide methods for obtaining computationally efficient gradient-based maximum a posteriori (MAP) estimates. We validate our model on synthetic data as well as on electronic health records (EHR) data from Kaiser Permanente (KP). We show that the proposed model provides better predictive performance over a stationary model as well as uncovers interesting latent correlation processes across vitals which are potentially predictive of patient risk.
References in corpus (6)
- MCMC using Hamiltonian dynamics
- Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes
- An Improved Multi-Output Gaussian Process RNN with Real-Time Validation for Early Sepsis Detection
- Non-Stationary Gaussian Process Regression with Hamiltonian Monte Carlo
- A scalable end-to-end Gaussian process adapter for irregularly sampled time series classification
- Sparse Multi-Output Gaussian Processes for Medical Time Series Prediction