Monitoring of intratidal lung mechanics: a Graphical User Interface for a model-based decision support system for PEEP-titration in mechanical ventilation.

In mechanical ventilation, a careful setting of the ventilation parameters in accordance with the current individual state of the lung is crucial to minimize ventilator induced lung injury. Positive end-expiratory pressure (PEEP) has to be set to prevent collapse of the alveoli, however at the same time overdistension should be avoided. Classic approaches of analyzing static respiratory system mechanics fail in particular if lung injury already prevails. A new approach of analyzing dynamic respiratory system mechanics to set PEEP uses the intratidal, volume-dependent compliance which is believed to stay relatively constant during one breath only if neither atelectasis nor overdistension occurs. To test the success of this dynamic approach systematically at bedside or in an animal study, automation of the computing steps is necessary. A decision support system for optimizing PEEP in form of a Graphical User Interface (GUI) was targeted. Respiratory system mechanics were analyzed using the gliding SLICE method. The resulting shapes of the intratidal compliance-volume curve were classified into one of six categories, each associated with a PEEP-suggestion. The GUI should include a graphical representation of the results as well as a quality check to judge the reliability of the suggestion. The implementation of a user-friendly GUI was successfully realized. The agreement between modelled and measured pressure data [expressed as root-mean-square (RMS)] tested during the implementation phase with real respiratory data from two patient studies was below 0.2 mbar for data taken in volume controlled mode and below 0.4 mbar for data taken in pressure controlled mode except for two cases with RMS < 0.6 mbar. Visual inspections showed, that good and medium quality data could be reliably identified. The new GUI allows visualization of intratidal compliance-volume curves on a breath-by-breath basis. The automatic categorisation of curve shape into one of six shape-categories provides the rational decision-making model for PEEP-titration.

Automated mechanical ventilation: adapting decision making to different disease states.

The purpose of the present study is to introduce a novel methodology for adapting and upgrading decision-making strategies concerning mechanical ventilation with respect to different disease states into our fuzzy-based expert system, AUTOPILOT-BT. The special features are: (1) Extraction of clinical knowledge in analogy to the daily routine. (2) An automated process to obtain the required information and to create fuzzy sets. (3) The controller employs the derived fuzzy rules to achieve the desired ventilation status. For demonstration this study focuses exclusively on the control of arterial CO(2) partial pressure (p(a)CO(2)). Clinical knowledge from 61 anesthesiologists was acquired using a questionnaire from which different disease-specific fuzzy sets were generated to control p(a)CO(2). For both, patients with healthy lung and with acute respiratory distress syndrome (ARDS) the fuzzy sets show different shapes. The fuzzy set "normal", i.e., "target p(a)CO(2) area", ranges from 35 to 39 mmHg for healthy lungs and from 39 to 43 mmHg for ARDS lungs. With the new fuzzy sets our AUTOPILOT-BT reaches the target p(a)CO(2) within maximal three consecutive changes of ventilator settings. Thus, clinical knowledge can be extended, updated, and the resulting mechanical ventilation therapies can be individually adapted, analyzed, and evaluated.