Dynamic selection of models

This dissertation develops an approach to high-stakes, model-based decision making under scarce computation resources, bringing together concepts and techniques from the disciplines of decision analysis, statistics, artificial intelligence, and simulation. A method is developed and implemented to solve a time-critical decision problem in the domain of critical-care medicine. This method selects models that balance the prediction accuracy and the need for rapid action. Under a computation-time constraint, the optimal model for a model-based control application is a model that maximizes the tradeoff of model benefit (a measure of how accurately the model predicts the effects of alternative control settings) and model cost (a measure of the length of the model-induced computation delay). This work describes a real-time algorithm that selects, from a graph of models (GoM), a model that is accurate and that is computable within a time constraint. The DSM algorithm is a metalevel reasoning strategy that relies on a dynamic-selection-of-models (DSM) metric to guide the search through a GoM that is organized according to the simplifying assumptions of the models. The DSM metric balances an estimate of the probability that a model will achieve the required prediction accuracy and the cost of the expected model-induced computation delay. The DSM algorithm provides an approach to automated reasoning about complex systems that applies at any level of computation-resource or computation-time constraint. The DSM algorithm is implemented in Konan, a program that performs dynamic selection of patient-specific models from a GoM of quantitative physiologic models. Konan selects models that allow a model-based control application (a ventilator-management advisor) to make real-time decisions for the control settings of a mechanical ventilator.