BACKGROUND Intraoperative blood pressure lability may be related to risk factors, hypovolemia, light anesthesia, and morbid outcomes, but the measurements of lability in previous studies have been limited by imprecise and infrequent data collection methods. Computerized intraoperative data acquisition systems have provided an opportunity to readdress the issue of intraoperative blood pressure lability with more abundant and precise data. This study sought to derive and validate an algorithm (expert system) to measure mean arterial pressure (MAP) lability. METHODS Two hundred thirty-nine computerized anesthesis records were reviewed retrospectively. Three anesthesiologists separately rated MAP as very stable, average, or very labile. The parameters of a computer algorithm that measured the change of median MAP between consecutive 2-min epochs were optimized to achieve the best possible agreement among the anesthesiologists. The algorithm was then validated on 229 additional anesthesia records. RESULTS The proportion of consecutive 2-min epochs in which the absolute value of the fractional change of median MAP exceeded 0.06 (i.e., 6%) correlated strongly with the anesthesiologists' ratings (r = 0.78; P < 0.0001). The optimal sensitivity and specificity of the algorithm for detecting MAP lability were 98% and 59%, respectively. CONCLUSIONS One potential application of expert systems to anesthesia practice is a "smart alarm" to detect blood pressure lability. It may also provide a better tool to assess the relation between lability and outcome than has been available previously.