Application of state-space model with skew-t measurement noise to blood test value prediction

Abstract

State-space models (SSMs) have been widely used for analyzing time-series data in the fields of economics and bioinformatics to express the dynamic behavior of data. Recently, filtering and smoothing algorithms applied to linear discrete SSMs with skewed and heavy-tailed measurement noise have been proposed for a more appropriate model because measurement noise does not often follow a Gaussian distribution. In this paper, we propose a linear SSM with skew-t measurement noise for predicting blood test values, along with a method for estimating their parameter values to ensure consistency with the data when using a generalized expectation-maximization (EM) algorithm. To validate the effectiveness of the proposed model and method, we analyze time-series blood test data using both Gaussian and skew-t measurement noise and compared their prediction accuracy for future values. Then, we predicted future blood test values of the unhealthy participant under his current and improved lifestyles. By comparing these predicted results under different lifestyles, we demonstrate that he will overcome lifestyle-related diseases with the improved lifestyle.