Cluster analysis of trajectory data on hospital laboratory examinations.

Abstract

Large-scale cross-patient analysis of time series laboratory tests is a challenging task because of the temporal irregularity of data, coexistence of various events, and multidimensionalty of examinations. In this paper, we present a novel cluster analysis method for multidimensional, inhomogeneous time series based on the trajectory comparison technique. Application to the chronic hepatitis dataset delivered some interesting findings, for example, there existed some patterns in ALB-PLT trajectories that took similar temporal courses, and the clusters well corresponded to the fibrotic stages.