SELF-ORGANIZING DISCOVERY, RECOGNITION AND PREDICTION OF HEMODYNAMIC PATTERNS IN THE INTENSIVE-CARE UNIT

To care properly for critically ill patients in the intensive care uni t (ICU), clinicians must be aware of haemodynamic patterns. In a typic al ICU, a variety of physiological measurements are made continuously and intermittently in an attempt to provide clinicians with the most a ccurate and precise data needed for recognising such patterns. However , the data are disjointed, yielding little information beyond that pro vided by instantaneous high/low limit checking. Although instantaneous limit checking is useful for determining immediate dangers, it does n ot provide much information about temporal. patterns. As a result, the clinician is left to sift manually through an excess of data-in the i nterest of generating information. in the study, an arrangement of sel f-organising artificial neural networks is used to automate the discov ery, recognition and prediction of haemodynamic patterns in real time. It is shown that the network is capable of recognising the same haemo dynamic patterns recognised by an expert system, DYNASCENE, without be ing explicitly programmed to do so. Consequently, the system is also c apable of discovering new haemodynamic patterns. Results from real cli nical data are presented.