Visual Analytics of Multivariate Intensive Care Time Series Data

We present an approach for visual analysis of high-dimensional measurement data with varying sampling rates as routinely recorded in intensive care units. In care, most assessments not only depend on one single but a plethora mixed measurements over time. Even trained experts, efficient and accurate such multivariate remains challenging task. linked-view post hoc analytics application that reduces complexity by combining projection-based time curves overview small multiples details demand. Our supports the individual patients also ensembles adapting existing techniques using non-parametric statistics. evaluated effectiveness acceptance our through expert feedback domain scientists from surgical department real-world data: post-surgery study performed porcine surrogate model to identify parameters suitable diagnosing prognosticating volume state, clinical public database. The results show allows detailed changes patient state while summarizing temporal development overall condition.