Expert algorithms in the field of intelligent patient monitoring have rapidly revolutionized patient care thereby improving patient safety. Patient monitoring during anesthesia requires cautious attention by anesthetists who are monitoring many modalities, diagnosing clinically critical events and performing patient management tasks simultaneously. The mishaps that occur during day-to-day anesthesia causing disastrous errors in anesthesia administration were classified and studied by Reason [1]. Human errors in anesthesia account for 82% of the preventable mishaps [2]. The aim of this paper is to develop a clinically useful diagnostic alarm system for detecting critical events during anesthesia administration. The development of an expert diagnostic alarm system called ;RT-SAAM' for detecting critical pathological events in the operating theatre is presented. This system provides decision support to the anesthetist by presenting the diagnostic results on an integrative, ergonomic display and thus enhancing patient safety. The performance of the system was validated through a series of offline and real-time testing in the operation theatre. When detecting absolute hypovolaemia (AHV), moderate level of agreement was observed between RT-SAAM and the human expert (anesthetist) during surgical procedures. RT-SAAM is a clinically useful diagnostic tool which can be easily modified for diagnosing additional critical pathological events like relative hypovolaemia, fall in cardiac output, sympathetic response and malignant hyperpyrexia during surgical procedures. RT-SAAM is currently being tested at the Auckland City Hospital with ethical approval from the local ethics committees.

SummaryThreshold systolic arterial pressure alarms often use pre-operative values as a guide for intra-operative values. Recently, two systems (normalisation and principal component analysis) have been described that use the 'current' systolic arterial pressure and the change in systolic arterial pressure over a preceding time interval to generate an alarm based on units of standard deviation. Normalisation and principal component analysis techniques should prioritise alarms for clinically significant changes and hence reduce overall activation of alarms. Our aim was to measure the change in alarm activation using these techniques compared with standard threshold alarms. Systolic blood pressure data, collected from 10 patients (a total of 2177 min at 100 Hz), were cleaned and submitted to analysis using threshold alarms, normalisation and principal component analysis. With the threshold alarms set at 100 mmHg (low) and 140 mmHg (high), and a 5-min window, the alarms were activated for 557 min; using statistics-based thresholds the alarms were activated for 169 min (normalisation) and 155 min (principal component analysis), a reduction of approximately 70-72%.

No abstract