DESIGN AND VALIDATION OF AN INTELLIGENT PATIENT MONITORING AND ALARM SYSTEM BASED ON A FUZZY-LOGIC PROCESS MODEL

The process of patient care performed by an anaesthesiologist during h igh invasive surgery requires fundamental knowledge of the physiologic processes and a long standing experience in patient management to cop e with the inter-individual variability of the patients, Biomedical en gineering research improves the patient monitoring task by providing t echnical devices to measure a large number of a patient's vital parame ters. These measurements improve the safety of the patient during the surgical procedure, because pathological states can be recognised earl ier, but may also lead to an increased cognitive load of the physician . Tn order to reduce cognitive strain and to support intra-operative m onitoring for the anaesthesiologist an intelligent patient monitoring and alarm system has been proposed and implemented which evaluates a p atient's haemodynamic state on the basis of a current vital parameter constellation with a knowledge-based approach. In this paper general d esign aspects and evaluation of the intelligent patient monitoring and alarm systemin the operating theatre are described. The validation of the inference engine of the intelligent patient monitoring and alarm system was performed in two steps. Firstly, the knowledge base was val idated with real patient data which was acquired online in the operati ng theatre. Secondly, a research prototype of the whole system was imp lemented in the operating theatre. In the first step, the anaesthetist s were asked to enter a state variable evaluation before a drug applic ation or any other intervention on the patient into a recording system . These state variable evaluations were compared to those generated by the intelligent alarm system on the same vital parameter constellatio ns. Altogether 641 state variable evaluations were entered by six diff erent physicians. In total, the sensitivity of alarm recognition is 99 .3%, the specificity is 66% and the predictability is 45%. The second step was performed using a research prototype of the system in anaesth esiological routine. The evaluation of 684 events yielded a sensitivit y, specificity and predictability of the alarm recognition of more tha n 99%. (C) 1997 Elsevier Science B.V.