Patient-Specific Effects of Medication Using Latent Force Models with Gaussian Processes

TL;DR

This paper introduces a novel Gaussian process-based model that captures patient-specific physiological responses to medication interventions, enabling scalable and interpretable predictions in medical time series data.

Contribution

It presents a hybrid Gaussian process model with causal kernels that effectively model short-term drug effects and patient variability, improving predictive accuracy.

Findings

Achieves competitive predictive performance on hospital data

Recovers patient-specific responses to three common drugs

Provides analytically tractable cross-covariance functions

Abstract

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.