Advertisement

A Knowledge Based Alarmer for the Postoperative Care of Cardiac Patients

  • Erkki M. J. Koski
  • Tommi Sukuvaara
  • Aki Mäkivirta
  • Aarno Kari
Conference paper

Abstract

The prototype of an intelligent alarmer for the postoperative monitoring of cardiac surgery patients was tested on ten patients immediately after the operation. The alarmer had been executed on two PC/ATs and programmed to notify of four pathological states: hypovolemic state, hyperdynamic state, left ventricular failure or hypoventilatory state. Fourteen of the 32 alarms given during 37.2 hours of monitoring were considered correct. The observed sensitivity of 100% and the specificities of 67% for alarms and of 38% for alerts warrant further development of the technique.

Keywords

Pulmonary Capillary Wedge Pressure Cardiac Surgery Patient Patient Data Management System Postoperative Monitoring Hyperdynamic State 
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.
    Turnan KJ, McCarthy RJ, Spiess BD, DaValle M, Dabir R, Ivankovich AD. Does choice of anesthetic agent significantly affect outcome after coronary artery surgery? Anesthesiology 1989; 70: 189–198.CrossRefGoogle Scholar
  2. 2.
    Friedman A, Bernstein H. Hemodynamic monitoring during and after cardiac surgery. In: Gray RJ, Matloff JM, editors. Medical management of the curdiac surgical palient. Baltimore: Williams & Wilkins, 1990.Google Scholar
  3. 3.
    Stoodley KDC, Crew AD, Lu R, Naghdy F. A microcomputer implementation of status and alarm algorithms in a cardiac surgical intensive care unit. Int J Clin Mon Comp 1987; 4:115–122.CrossRefGoogle Scholar
  4. 4.
    Cohn AI, Rosenbaum S, Factor M, Miller PL DYNASCENE: an approach to computer-based intelligent cardiovascular monitoring using sequential clinical “scenes”. Meth Inf Med 1990; 29: 122–131.Google Scholar
  5. 5.
    Kari A, Ruokonen E, Takala J. Comparison of acceptance and performance of automated and manual data management systems in intensive care. Int J Clin Mon Comp 1990; 7: 157–162.CrossRefGoogle Scholar
  6. 6.
    Koski EMJ, Mäkivirta A, Sukuvara T, Kari A. Frequency and reliability of alarms in the monitoring of cardiac postoperative patients. Int J Clin Mon Comp 1990; 7: 129–133.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Tokyo 1992

Authors and Affiliations

  • Erkki M. J. Koski
    • 1
  • Tommi Sukuvaara
    • 2
  • Aki Mäkivirta
    • 2
  • Aarno Kari
    • 1
  1. 1.Department of Intensive CareKuopio University Central HospitalKuopioFinland
  2. 2.Medical Engineering LaboratoryTechnical Research Centre of FinlalndTampereFinland

Personalised recommendations