A STUDY ON WEANING RESULTS OF VENTILATOR-DEPENDENT PATIENTS WITH AN ARTIFICIAL NEUROMOLECULAR SYSTEM

Abstract

Ventilator has been widely used to support the breathing needs of patients, and weaning is the process of removing ventilator from them. So far there is no positive answer about whether it will be successful to wean a patient off a ventilator. It may be of help if we develop an intelligent system to assist clinicians in making such a decision. In this paper, we apply an artificial neuromolecular system (ANM system), which is a selforganizing learning system, to a database of 189 weaned patients. The ANM system is a multi-level evolutionary learning architecture that captures the gradual transformability feature of structure–function relationship embedded in biological systems. Our experiments with the model show that the integrated system achieves a satisfactory result in separating those patients who have successful weaning results from those who do not, based on the 27 parameters that may affect their weaning results. Our parameter analysis shows that most of the parameters identified as significant by the system are the same as those by clinicians, but some are not. The finding of the latter should provide clinicians another dimension of information, in particular the effectiveness of each parameter in determining weaning results for patients.