The design and implementation of a ventilator-management advisor.

VentPlan is an implementation of the architecture developed by the qualitative-quantitative (QQ) research group for combining qualitative and quantitative computation in a ventilator-management advisor (VMA). VentPlan calculates recommended settings for four controls of a ventilator by evaluating the predicted effects of alternative ventilator settings. A belief network converts clinical diagnoses to distributions on physiologic parameters. A mathematical-modeling module applies a patient-specific mathematical model of cardiopulmonary physiology to predict the effects of alternative ventilator settings. A decision-theoretic plan evaluator ranks the predicted effects of alternative ventilator settings according to a multiattribute-value model that specifies physician preferences for ventilator treatments. Our architecture allows VentPlan to interpret quantitative observations in light of the clinical context (such as the clinical diagnosis). We report a retrospective study of the ventilator-setting changes encountered in postoperative patients in a surgical intensive-care unit (ICU). We conclude that the QQ architecture allows VentPlan to apply a patient-specific physiologic model to calculate ventilator settings that are optimal with respect to a decision-theoretic value model describing physician preferences for setting the ventilator.

Dynamic selection of models for a ventilator-management advisor.

A ventilator-management advisor (VMA) is a computer program that monitors patients who are treated with a mechanical ventilator. A VMA implements a patient-specific physiologic model to interpret patient data and to predict the effects of alternative control settings for the ventilator. Because a VMA evaluates its physiologic model repeatedly during each cycle of data interpretation, highly complex models may require more computation time than is available in this time-critical application. On the other hand, less complex models may be inaccurate if they are unable to represent a patient's physiologic abnormalities. For each patient, a VMA should select a model that balances the tradeoff of prediction accuracy and computation-time complexity. I present a method to select models that are at an appropriate level of detail for time-constrained decision tasks. The method is based on a local search in a graph of models (GoM) for a model that maximizes the tradeoff of computation-time complexity and prediction accuracy. For each model under consideration, a belief network computes a probability of model adequacy given the qualitative prior information, and the goodness of fit of the model to the data provides a measure of the conditional probability of adequacy given the quantitative observations. I apply this method to the problem of model selection for a VMA. I describe an implementation of a graph of physiologic models that range in complexity from VentPlan, a simple model with 3 compartments, to VentSim, a multicompartment model with detailed airway, circulation and mechanical ventilator components.(ABSTRACT TRUNCATED AT 250 WORDS)

VentSim: a simulation model of cardiopulmonary physiology.

VentSim is a quantitative model that predicts the effects of alternative ventilator settings on the cardiopulmonary physiology of critically ill patients. VentSim is an expanded version of the physiologic model in VentPlan, an application that provides ventilator-setting recommendations for patients in the intensive care unit. VentSim includes a ventilator component, an airway component, and a circulation component. The ventilator component predicts the pressures and airflows that are generated by a volume-cycled, constant-flow ventilator. The airway component has anatomic and physiologic deadspace compartments, and two alveolar compartments that participate in gas exchange with two pulmonary blood-flow compartments in the circulatory component. The circulatory component also has a shunt compartment that allows a fraction of blood flow to bypass gas exchange in the lungs, and a tissue compartment that consumes oxygen and generates carbon dioxide. The VentSim model is a set of linked first-order difference equations, with control variables that correspond to the ventilator settings, dependent variables that correspond to the physiologic state, and one independent variable, time. Because the model has no steady state solution, VentSim solves the equations by numeric integration, which is computation intensive. Simulation results demonstrate that VentSim predicts the effects of a variety of physiologic abnormalities that cannot be represented in less complex models such as the VentPlan model. For a ventilator-management application, the time-critical nature of ventilator-setting decisions limits the use of complex models. Advanced ventilator-management applications may include a mechanism to select patient-specific models that balance the trade-off of benefit of model detail and cost of computation delay.

The design of a user interface for a ventilator-management advisor.

The lack of user acceptance for many medical decision-support systems should force medical software developers to rethink strategies for user interaction with decision-support programs. Participatory design is an emerging method for the development for computer applications that emphasizes user involvement in both the design and implementation phases. We have applied participatory design to the development of a user interface for VentPlan, an application that assists physicians in the management of artificial respiration of critically ill patients. In this paper, we present a case history of the participatory design process and describe the resulting interface for the VentPlan program. As a result of applying participatory design ideas, we gained insight as to how to implement VentPlan more effectively.