Forecasting Sleep Apnea with Dynamic Network Models

TL;DR

This paper introduces dynamic network models (DNMs) that combine probabilistic reasoning and time series analysis for improved forecasting, demonstrated on a medical sleep apnea prediction problem.

Contribution

The paper presents a novel methodology integrating belief networks with temporal reasoning to enhance forecasting accuracy and address limitations of traditional time series methods.

Findings

Effective forecasting of sleep apnea using DNMs

Ability to incorporate non-linear and non-normal relationships

Improved adaptation to exogenous influences

Abstract

Dynamic network models (DNMs) are belief networks for temporal reasoning. The DNM methodology combines techniques from time series analysis and probabilistic reasoning to provide (1) a knowledge representation that integrates noncontemporaneous and contemporaneous dependencies and (2) methods for iteratively refining these dependencies in response to the effects of exogenous influences. We use belief-network inference algorithms to perform forecasting, control, and discrete event simulation on DNMs. The belief network formulation allows us to move beyond the traditional assumptions of linearity in the relationships among time-dependent variables and of normality in their probability distributions. We demonstrate the DNM methodology on an important forecasting problem in medicine. We conclude with a discussion of how the methodology addresses several limitations found in traditional time series analyses.