Normalized Dynamic Time Warping Increases Sensitivity In Differentiating Functional Network Connectivity In Schizophrenia

Abstract

Our study advances the application of dynamic time warping (DTW) as a functional connectivity measure by introducing a normalization technique which enhances the detection of schizophrenia effects in comparison to both standard DTW and traditional correlation methods. By rigorously examining the statistical validity of DTW and our proposed normalized DTW measure, we show that it effectively captures interdependencies between fMRI signals beyond linear correlation, offering a more robust, complementary and informative approach to functional connectivity analysis. Through comprehensive evaluations, we demonstrate that normalized DTW is more sensitive to differences in functional brain network connections between schizophrenia and controls, highlighting its potential to provide deeper insight into clinical research. Clinical RelevanceThis study enhances our understanding of the functional specificity of schizophrenia by emphasizing the importance of nonlinear relationships through the introduction of a normalization technique for the DTW metric.