Individualized Dosing Dynamics via Neural Eigen Decomposition

TL;DR

NESDE is a novel neural differential equation method that offers personalized, noise-robust, and policy-generalizable modeling of biological dosing dynamics with fast, continuous predictions.

Contribution

It introduces NESDE, a neural eigen decomposition approach that enhances individualization, generalization, and robustness in medical dosing models.

Findings

Robust performance on synthetic and real medical data

Effective generalization to new treatment policies

Fast, continuous, closed-form predictions

Abstract

Dosing models often use differential equations to model biological dynamics. Neural differential equations in particular can learn to predict the derivative of a process, which permits predictions at irregular points of time. However, this temporal flexibility often comes with a high sensitivity to noise, whereas medical problems often present high noise and limited data. Moreover, medical dosing models must generalize reliably over individual patients and changing treatment policies. To address these challenges, we introduce the Neural Eigen Stochastic Differential Equation algorithm (NESDE). NESDE provides individualized modeling (using a hypernetwork over patient-level parameters); generalization to new treatment policies (using decoupled control); tunable expressiveness according to the noise level (using piecewise linearity); and fast, continuous, closed-form prediction (using spectral representation). We demonstrate the robustness of NESDE in both synthetic and real medical problems, and use the learned dynamics to publish simulated medical gym environments.