Traumatic Physiological Vital Sign Fusion: Insight from Composite Spatial Similarity Measure Modelling

Abstract

This paper develops a non-linear composite similarity-based framework for generating univariate physiological vital signs data from an input multivariate counterpart. The framework is built on mixture random variate using information provided by the inter-relationships among variables. This allows the latent one-dimensional data to be generated as a weighted linear combination of the multivariate data, providing an easy way to model the weights in terms of desirable data features of interest. Using variable specific non-linear composite similarity statistic to handle short, medium- and long-term auto-relationships, the framework provides a unified context for easy quantification and assessment of both vital sign and observation level relative relevance. With the above formulation, better calibration and indication of key vital signs in traumatic events is presented. An illustrative example using real physiological vital sign datasets on trauma and non-traumatic patients provides evidence on its utility in handling both key informative incident and non-incident vital sign-specific features, events and patterns for development of pragmatic health monitoring indicators.