Sequential versus concurrent computation of complex model systems for medical decision support

Abstract

Medical Decision Support Systems employ mathematical models to optimize therapy settings. The mathematical models are used to predict patient reactions towards alteration in the therapy regime. This prediction should not be limited to one detail but should feature a broad picture. A previously proposed framework is able to dynamically combine submodels of three model families (respiratory mechanics, gas exchange and cardiovascular dynamics) to form a complex, interacting model system. When concurrent computation of the combined submodels is employed, tests exhibited high computing costs. Therefore, a sequential computing approach is introduced. Thereby, direct interaction between the submodels is not applicable as all submodels are computed individually. To simulate submodel interaction, interface signals that are normally present in the concurrent approach were precalculated using reduced models of respiratory mechanics and cardiovascular dynamics. Evaluation of the new approach showed that results feature a discrepancy lower than 2.5% compared to the results computed by the concurrent approach. Simulation error could be decreased to 2% by improving the precalculation of the interface signals. Computing costs have been decreased by a factor of 17.