An algorithm for assessing intraoperative mean arterial pressure lability
ABSTRACT 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.
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.
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.
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.
- Anesthesiology 01/1998; 87(6):1593-4. DOI:10.1097/00000542-199712000-00056 · 6.17 Impact Factor
Article: Expert systems in anesthesiology[Show abstract] [Hide abstract]
ABSTRACT: There are only a limited number of computer-based systems designed to support anesthesiologists in the operating room. This is evident from the very small number of publications on this topic. These systems may be classified by the functions they perform and include: intelligent anesthesia workstations (with current data acquisition, conditioning and analysis subsystems), systems to detect critical conditions in patients (including expert systems in smart alarm capacity), anesthesia management systems (for planning and management) and drug administration systems. Drug administration systems may be subdivided into open-loop and closed-loop systems. The techniques applied for design of such systems vary extensively. There are traditional rule-based expert systems and probability-based systems, and more recently developed artificial intelligence methods, such as neural networks and fuzzy logic. Computers are valuable tools that have the potential to assist anesthesiologists in carrying out cumbersome and monotonous processes. Future efforts may result in the development of sophisticated systems capable of assuming more responsibilities and of reducing human workload and stress.Drugs of today (Barcelona, Spain: 1998) 08/1998; 34(7):593-601. DOI:10.1358/dot.19126.96.36.1995257 · 1.00 Impact Factor
- [Show abstract] [Hide abstract]
ABSTRACT: Examination of overall hemodynamic stability in patients undergoing endovascular aortic repair (EAR) compared with open aortic repair (OAR). Retrospective study. University hospital setting. Seventy-two patients undergoing OAR and 17 patients undergoing EAR were studied. None. Physiologic parameters were extracted every 15 seconds from computerized anesthesia records. Median values were calculated for every 2-minute epoch, and the absolute value of the fractional change in median (|FCM|) from epoch to epoch was calculated for a maximum of 5 hours during the intraoperative period. The incidence of extremes in hemodynamic parameters was compared. Data are presented as median and interquartile ranges. The frequency of |FCM| greater than 0.06 for mean arterial pressure (MAP) was significantly greater in the OAR compared with the EAR group (0.37 [0.30, 0.46] vs 0.14 [0.11, 0.21], p < 0.0001), implying greater stability in MAP during EAR. Similarly, the mean pulmonary artery pressures (MPAPs) were significantly more stable during EAR compared with OAR (frequency of |FCM| > 0.07: EAR, 0.20 [0.16, 0.27] vs OAR, 0.32 [0.26, 0.391; p < 0.01). No intergroup differences were detected in heart rate (HR), systolic (SPAP) or diastolic pulmonary artery pressures (DPAP), or central venous pressures (CVPs). With the exception of a greater incidence of low CVP during EAR, there were no significant differences in the frequency of extremes of hemodynamic values between groups. These results show improved hemodynamic stability during EAR compared with OAR.Journal of Cardiothoracic and Vascular Anesthesia 02/1999; 13(1):42-6. DOI:10.1016/S1053-0770(99)90172-6 · 1.48 Impact Factor