Patient-Specific Effects of Medication Using Latent Force Models with Gaussian Processes
This work addresses the problem of personalized medication effect prediction for clinicians, but it is incremental as it builds on existing multi-output Gaussian process frameworks.
The authors tackled the challenge of modeling short-term drug effects on patient physiological states by proposing a hybrid Gaussian process model that convolves patient physiology with latent force models for treatments, achieving competitive predictive performance on hospital data for three common drugs.
Multi-output Gaussian processes (GPs) are a flexible Bayesian nonparametric framework that has proven useful in jointly modeling the physiological states of patients in medical time series data. However, capturing the short-term effects of drugs and therapeutic interventions on patient physiological state remains challenging. We propose a novel approach that models the effect of interventions as a hybrid Gaussian process composed of a GP capturing patient physiology convolved with a latent force model capturing effects of treatments on specific physiological features. This convolution of a multi-output GP with a GP including a causal time-marked kernel leads to a well-characterized model of the patients' physiological state responding to interventions. We show that our model leads to analytically tractable cross-covariance functions, allowing scalable inference. Our hierarchical model includes estimates of patient-specific effects but allows sharing of support across patients. Our approach achieves competitive predictive performance on challenging hospital data, where we recover patient-specific response to the administration of three common drugs: one antihypertensive drug and two anticoagulants.