A new approach for physiological time series

TL;DR

This paper introduces an innovative method for analyzing physiological time series using iterative convolution filtering and feature extraction, effectively distinguishing between normal and abnormal systems, demonstrated on heart failure data.

Contribution

The paper presents a novel approach combining iterative convolution filtering and feature selection with support vector machines for physiological time series analysis.

Findings

Successfully differentiated normal and abnormal heart failure data

Effective feature extraction from time series components

Improved classification accuracy for physiological signals

Abstract

We developed a new approach for the analysis of physiological time series. An iterative convolution filter is used to decompose the time series into various components. Statistics of these components are extracted as features to characterize the mechanisms underlying the time series. Motivated by the studies that show many normal physiological systems involve irregularity while the decrease of irregularity usually implies the abnormality, the statistics for "outliers" in the components are used as features measuring irregularity. Support vector machines are used to select the most relevant features that are able to differentiate the time series from normal and abnormal systems. This new approach is successfully used in the study of congestive heart failure by heart beat interval time series.