Advertisement

Artificial Intelligence and Expert Systems

  • D. M. Gaba
Conference paper

Abstract

Control and automation in anesthesia imply the intelligent manipulation of anesthetics or adjuvant drugs to provide satisfactory medical conditions for the dynamically changing patient undergoing surgery and anesthesia. Traditionally, the intelligence is supplied totally by the human anesthetist. The focus of this workshop is on new methods in which the manipulation of drugs or other interventions is handled by computers. When the computer makes these changes in response to specific measurements made on the patient, this is termed “closed-loop control”. Other forms of automation (that is, machines conducting activities formerly conducted by a person) are also possible. These range from the relatively mundane — such as the mechanical ventilator or the standard electromechanical infusion pump — to truly autonomous computer agents which could conduct diagnosis and therapy on the patient in the operating room or the intensive care unit (ICU).

Keywords

Expert System Mode Error Bayesian Belief Network Certainty Factor Cognitive Engineer 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Shortliffe EH (1992) AI meets decision science: emerging synergies for decision support. In: Evans DA, Patel VL (eds) Advanced models of cognition for medical training and practice. Springer, Berlin Heidelberg New York, pp 71–89Google Scholar
  2. 2.
    van Oostrom JH, van der Aa JJ, Nederstigt JA, Beneken JEW, Gravenstein JS (1989) Intelligent alarms in the anesthesia circle breathing system (abstract). Anesthesiology 71: A336CrossRefGoogle Scholar
  3. 3.
    Watt RC, Navabi MJ, Mylrea KC, Hammeroff SR (1989) Integrated monitoring “smart alarms” can detect critical events and reduce false alarms (abstract). Anesthesiology 71: A338CrossRefGoogle Scholar
  4. 4.
    Loeb RG, Brunner JX, Westenskow DR, Feldman B, Pace NL (1989) The Utah anesthesia workstation. Anesthesiology 70: 999–1007PubMedCrossRefGoogle Scholar
  5. 5.
    Reggia JA (1993) Neural computation in medicine. Artif Intell Med 5: 143–157PubMedCrossRefGoogle Scholar
  6. 6.
    Westenskow DR, Orr JA, Simon FH, Bender HJ, Frankenberger H (1992) Intelligent alarms reduce anesthesiologist’s response time to critical faults. Anesthesiology 77: 1074–1079PubMedCrossRefGoogle Scholar
  7. 7.
    Farrell RM, Orr JA, Kuck K, Westenskow DR (1992) Differential features for a neural network-based anesthesia alarm system. Biomed Sci Instrum 28: 99–104PubMedGoogle Scholar
  8. 8.
    Orr JA, Westenskow DR (1994) A breathing circuit alarm system based on neural networks. J Clin Monit 10: 101–109PubMedCrossRefGoogle Scholar
  9. 9.
    Pearl J (1982) Reverend Bayes on inference engines: a distributed hierarchical ap¬proach, Proc AAAI-82 National Conference on Artificial Intelligence, Pittsburgh, PA. MIT Press, Cambridge, MA, pp 133–136Google Scholar
  10. 10.
    Suermondt HJ (1992) Explanation in Bayesian belief networks. PhD thesis, Stanford UniversityGoogle Scholar
  11. 11.
    Pearl J (1988) Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan Kaufmann, San Mateo, CAGoogle Scholar
  12. 12.
    Beinlich IA, Gaba DM (1989) The ALARM monitoring system — intelligent decision making under uncertainty (abstract). Anesthesiology 71: A337CrossRefGoogle Scholar
  13. 13.
    Herskovitz E, Cooper GF (1991) Kutato: an entropy-driven system for construction of probabilistic expert systems from databases. In: Bonissone PO, Henrion M, Kanal LN, Lemmer JF (eds) Uncertainty in Artificial Intelligence. North-Holland, AmsterdamGoogle Scholar
  14. 14.
    Beinlich IA (1990) Prototypical structures for probabilistic networks. Masters thesis, Stanford UniversityGoogle Scholar
  15. 15.
    Rutledge GW (1993) Dynamic selection of models for a ventilator-management advisor. Proc Annu Symp Comput Appl Med Care (SCAMC): 344–350Google Scholar
  16. 16.
    Rutledge GW, Thomsen GE, Farr BR, Tovar MA, Polaschek JX, Beinlich IA, Sheiner LB, Fagan LM (1993) The design and implementation of a ventilator-management advisor. Artif Intell Med 5: 67–82PubMedCrossRefGoogle Scholar
  17. 17.
    Uckun S, Dawant BM (1992) Qualitative modeling as a paradigm for diagnosis and prediction in critical care environments. Art Intell Med 4: 127–144CrossRefGoogle Scholar
  18. 18.
    Uckun S, Dawant BM, Lindstrom DP (1993) Model-based diagnosis in intensive care monitoring: the YAQ approach. Art Intell Med 5: 31–48CrossRefGoogle Scholar
  19. 19.
    Hayes-Roth B (1985) A blackboard architecture for control. Art Intell 26: 251–321CrossRefGoogle Scholar
  20. 20.
    Ash D (1993) Diagnosis using action-based hierarchies for real-time performance. PhD thesis, Stanford UniversityGoogle Scholar
  21. 21.
    Larsson JE (1992) Knowledge-based methods for control systems. Department of Auto¬matic Control, Lund Institute of Technology, Lund, SwedenGoogle Scholar
  22. 22.
    Martin JF, Schneider AM, Quinn ML, Smith NT (1992) Improved safety and efficacy in adaptive control of arterial blood pressure through the use of a supervisor. IEEE Trans Biomed Eng 39: 381 - 388PubMedCrossRefGoogle Scholar
  23. 23.
    Martin JF, Smith NT, Quinn ML, Schneider AM (1992) Supervisory adaptive control of arterial pressure during cardiac surgery. IEEE Trans Biomed Eng 39: 389–393PubMedCrossRefGoogle Scholar
  24. 24.
    Isaka S, Sebald AV (1993) Control strategies for arterial blood pressure regulation. IEEE Trans Biomed Eng 40: 353–363PubMedCrossRefGoogle Scholar
  25. 25.
    Woods DD (1990) Modeling and predicting human error. In: Elkind JI, Card SK, Hochberg J, Huey BM (eds) Human performance models for computer-aided engineering. Academic, Boston, pp 248–274Google Scholar
  26. 26.
    Sarter NB, Woods DD (1995) “How in the world did I ever get into that mode?” Mode error and awareness in supervisory control. Hum Factors (in press)Google Scholar
  27. 27.
    Wiener EL (1988) Cockpit automation. In: Wiener EL, Nagel DC (eds) Human factors in aviation. Academic, San Diego, pp 433–461Google Scholar
  28. 28.
    Norman DA (1988) The psychology of everyday things. Basic Books, New YorkGoogle Scholar
  29. 29.
    Norman DA (1992) Turn signals are the facial expressions of automobiles. Addison-Wesley, Reading, MAGoogle Scholar
  30. 30.
    Norman DA (1993) Things that make us smart. Addison-Wesley, Reading, MAGoogle Scholar
  31. 31.
    Cook RI, Potter SS, Woods DD, McDonald JS (1991) Evaluating the human engineering of microprocessor-controlled operating room devices. J Clin Monit 7: 217–226PubMedCrossRefGoogle Scholar
  32. 32.
    Cook RI, Woods DD, Howie MB, Harrow JC, Gaba DM (1992) Unintentional delivery of vasoactive drugs with an electromechanical infusion device. J Cardiothoracic Anesth 6: 238–9244CrossRefGoogle Scholar
  33. 33.
    Howard SK (1993) Failure of an automated noninvasive blood pressure device: the contribution of human error and software design flaw (abstract). J Clin Monit 9: 232–233Google Scholar
  34. 34.
    Botney RI, Gaba DM (1995) Human factors issues in monitoring. In: Blitt C (ed) Monitoring in anesthesia and intensive care. Churchill Livingstone, New York, pp 23–54Google Scholar
  35. 35.
    Schwid HA, O’Donnell D (1992) Anesthesiologists’ management of simulated critical incidents. Anesthesiology 76: 495–501PubMedCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • D. M. Gaba

There are no affiliations available

Personalised recommendations