Abstract
Objective. Intensive care and operating room monitors generate data that are not fully utilized. False alarms are so frequent that attending personnel tends to disconnect them. We developed an expert system that could select and validate alarms by integration of seven vital signs monitored on-line from cardiac surgical patients. Methods. The system uses fuzzy logic and is able to work under incomplete or noisy information conditions. Patient status is inferred every 2 seconds from the analysis and integration of the variables and a unified alarm message is displayed on the screen. The proposed structure was implemented on a personal computer for simultaneous automatic surveillance of up to 9 patients. The system was compared with standard monitors (SpaceLabsTM PC2), using their default alarm settings. Twenty patients undergoing cardiac surgery were studied, while we ran our system and the standard monitor simultaneously. The number of alarms triggered by each system and their accuracy and relevance were compared. Two expert observers (one physician, one engineer) ascertained each alarm reported by each system as true or false. Results. Seventy-five percent of the alarms reported by the standard monitors were false, while less than 1% of those reported by the expert system were false. Sensitivity of the standard monitors was 79% and sensitivity of the expert system was 92%. Positive predictive value was 31% for the standard monitors and 97% for the expert system. Conclusions. Integration of information from several sources improved the reliability of alarms and markedly decreased the frequency of false alarms. Fuzzy logic may become a powerful tool for integration of physiological data.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
REFERENCES
Edsall DW. Analysis and frequency of artifacts generated by anesthesia information management systems. Anes-thesiology 1990; 73–(3A): A481
Rolf N, Cote¨ CJ. Incidence of real and false positive capnography and pulse oximetry alarms during pediatric anesthesia. Anesthesiology 1991; 75–(3A): A476
Tsien CL, Fackler JC. Poor prognosis for existing mon-itors in the intensive care unit. Crit CareMed 1997; 25–(4): 614–619
Koski EM, Maäkivirta A, Sukuvaara T, Kari A. Frequency and reliability of alarms in the monitoring of cardiac postoperative patients. Int J Clin Monit Comput 1990; 7 (2): 129–133
Wiklund L, Hoäk B, Stahl K, Jordeby-Joä nsson A. Post-anesthesia monitoring revisited: Frequency of true and false alarms from di¡erent monitoring devices. J Clin Anesth 1994; 6 (3): 182–188
Lawless ST. Crying wolf: False alarms in a pediatric intensive care unit. Crit CareMed 1994; 22 (6): 981–985
O'Carroll TM. Survey of alarms in an intensive therapy unit. Anesthesia 1986; 41 (7): 742–744
Meredith C, Edworthy J. Are there too many alarms in the intensive care unit? An overview of the problems. J Adv Nurs 1995; 21 (1): 15–20
Kestin IG, Miller BR, Lockhart CH. Auditory alarms during anesthesiamonitoring. Anesthesiology 1988; 69 (1): 106–109
Mora FA, Passariallo G, Carrault G, Le Pichon JP. Intelli-gent patient monitoring and management systems: A review. IEEE Eng inMed & Biol 1993; 12 (4): 23–33
Navabi M, Watt R, Hamero¡ S, Mylrea K. Integrated monitoring can detect critical events and improve alarm accuracy. J Clin Eng 1991; 16 (4): 295–306
Watt RC, Navabi MJ, Mylrea KC, Hamero¡ SR. Inte-grated monitoring ``smart alarms''can detect critical events and reduce false alarms. Anesthesiology 1989; 71 (3A): A338
Factor M, Gelernter DH, Kolb CE, Miller PL, Sittig DF. Real-time data fusion in the intensive care unit. IEEE Computer 1991; 24 (11): 45–54
Watt R, Maslana E, Mylrea C. Alarms and anesthesia: Challenges in the design of intelligent systems for patient monitoring. IEEE Eng inMed & Biol 1993; 12 (4): 34–41
Hudson DL, Cohen ME. Fuzzy logic in medical expert systems. IEEE Eng inMed & Biol 1994; 13 (5): 693–698
Becker K, Rau G, Kaäsmacher H, Petermeyer MK al¡ G, Zimmermann HJ. Fuzzy logic approach to intelligent alarms. IEEE Eng inMed & Biol 1994; 13 (5): 710–716
Wolf M, Kee lM, von Siebenthal K, Bucher HU, Geering K, Lehareinger Y, Niederer P. Improved monitoring of preterm infants by fuzzy logic. Technol Health Care 1996; 4 (2): 193–201
Sukuvaara T, Sydaänmaa M, Nieminen H, Heikelaä A, Koski E. Object-oriented implementation of an architec-ture for patient monitoring. IEEE Eng in Med & Biol 1993; 12 (4): 69–81
Maäkivirta A, Koski E, Kari A, Sukuvaara T. The median ¢lter as a preprocessor for a patient monitor limit alarm system in intensive care. Comput Methods Programs Biomed 1991; 34 (2–3): 139-144
Dawant BM. Knowledge-based systems for intelligent patient monitoring and management in critical care envi-ronments. In: Bronzino JD, ed. The biomedical engi-neering handbook. Boca Raton: CRC Press, Inc., 1995: 2746–2756
Sukuvaara T, Koski EM, Maäkivirta A, Kari A. A knowl-edge-based alarm system for monitoring cardiac operated patients technical construction and evaluation. Int J ClinMonit Comput 1993; 10 (2): 117–126
Fukui Y, Masuzawa T. Knowledge-based approach to intelligent alarms. J ClinMon 1989; 5 (3): 211–216
Schecke T, Langen M, P10 (4): 38–44
Koski EM, Maäkivirta A, Sukuvaara T, Kari A. Clinicians' opinions on alarm limits and urgency of therapeutic responses. Int J ClinMonit Comput 1995; 12 (2): 85–88
Beneken JE, Van der Aa JJ. Alarms and their limits in monitoring. J ClinMonit 1989; 5 (3): 205–210
Van Oostrom JH, Gravenstein C, Gravenstein JS. Accept-able ranges for vital signs during general anesthesia. J Clin Monit 1993; 9: 321–325
Feldman JM, Ebrahim M. Which sensor measures heart rate best? Anesthesiology 1995; 83 (3A): A478
Maäkivirta A, Koski EM. Alarm-inducing variability in cardiac postoperative data and the e¡ects of prealarm delay. J ClinMonit 1994; 10 (3): 153–162
Pan PH, Gravenstein N. Intraoperative pulse oximetry: Frequency and distribution of discrepant data. J Clin Anesth 1994; 6 (6): 491–495
Rung GW, Bennett BA. Clinical evaluation of the MonitronTM cardio-respiratory monitor: Minimizing false alarms.Intelligent alarms reduce anesthesio-logist's response time to critical faults. Anesthesiology 1992; 77 (6): 1074–1079
Koski EM, Sukuvaara T, Maäkivirta A, Kari A. A knowl-34 Journal of ClinicalMonitoring and Computing Vol 15 No 1 January 1999 edge-based alarm system for monitoring cardiac operated patients assessment of clinical performance. Int J Clin Monit Comput 1994; 11 (2): 79–83
Block FE, Schaaf C. Auditory alarms during anesthesia monitoring with an integrated monitoring system. Int J ClinMon Comput 1996; 13 (2): 81–84
Mylrea KC, Orr JA, Westenskow DR. Integration of monitoring for intelligent alarms in antesthesia: Neural networks can they help? J Clin Monit 1993; 9 (1): 31–37
Orr JA, Westenskow DR. A breathing circuit alarm system based on neural networks. J Clin Monit 1994; 10 (2): 101–109
Thull B, Popp HJ, Rau G. Man machine interaction in critical care settings. IEEE Eng in Med & Biol 1993; 12 (4): 42–49
Block FE. Evaluation of users' abilities to recognize musical alarm tones. J Clin Monit 1992; 8 (4): 285–290
Loeb RG, Jones BR, Leonard RA, Behrman K. Recog-nition accuracy of current operating room alarms. Anesth Analg 1992; 75: 499–505
Cropp AJ, Woods LA, Raney D, Bredle DL. Name that one.The proliferation of alarms in the intensive care unit. Chest 1994; 105 (4): 1217–1220.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Oberli, C., Urzua, J., Saez, C. et al. An Expert System for Monitor Alarm Integration. J Clin Monit Comput 15, 29–35 (1999). https://doi.org/10.1023/A:1009951928395
Issue Date:
DOI: https://doi.org/10.1023/A:1009951928395