A knowledge-based alarm system for monitoring cardiac operated patients-assessment of clinical performance

An intelligent alarm system for the postoperative monitoring of cardiac surgery patients, which did not require any manual data entries, was tested in two phases. A clinician monitored at bedside the patients' recovery and verified clinically abnormal physiological states. After the first test with ten patients, the system's rulebase was upgraded and then tested with an additional 15 patients. The alarm system employed two PC/ATs and was programmed to give notive of four pathological states (hyperdynamic state, hypovolemic state, hypoventilation and left ventricular failure) at two levels of urgency (alarm and alert levels). The monitoring lasted 5.4±1.7 hours per patient (mean ±S.D.), totalling 134.7 hours. The system alarmed 27 times during the first and 73 times during the second phase of the testing. The sensitivity of the alarms was 100% in both phases, and the specificities increased from 20.0% to 73.9% and from 59.1% to 70.0% for the alarms and the alerts, respectively. This computerized decision support system based exclusively on data available in the automatically collected data base had a low false positive rate and gave early warnings about pathological states in the homogeneous group of adult postoperative cardiac patients.

[1]  R M Gardner,et al.  Physician decision-making--evaluation of data used in a computerized ICU. , 1984, International journal of clinical monitoring and computing.

[2]  A. Mäkivirta,et al.  Development of an expert system for haemodynamic monitoring: computerized symbolization of on-line monitoring data , 1991, International journal of clinical monitoring and computing.

[3]  K D Stoodley,et al.  A microcomputer implementation of status and alarm algorithms in a cardiac surgical intensive care unit , 1987, International journal of clinical monitoring and computing.

[4]  D R Westenskow,et al.  The Utah anesthesia workstation. , 1989, Anesthesiology.

[5]  Avent Rk,et al.  A critical review of trend-detection methodologies for biomedical monitoring systems. , 1990 .

[6]  D. Spiegelhalter,et al.  Evaluating medical expert systems: what to test and how? , 1990, Medical informatics = Medecine et informatique.

[7]  P L Miller,et al.  DYNASCENE: an approach to computer-based intelligent cardiovascular monitoring using sequential clinical "scenes". , 1990, Methods of information in medicine.

[8]  David S. Bree,et al.  GUUS an expert system in the intensive care unit , 1990, International journal of clinical monitoring and computing.

[9]  A. Mäkivirta,et al.  The median filter as a preprocessor for a patient monitor limit alarm system in intensive care. , 1991, Computer methods and programs in biomedicine.

[10]  L C Sheppard,et al.  Automated Treatment of Critically Ill Patients Following Operation , 1968, Annals of surgery.

[11]  A. Kari,et al.  Comparison of acceptance and performance of automated and manual data management systems in intensive care , 1990, International journal of clinical monitoring and computing.

[12]  B. Spiess,et al.  Does choice of anesthetic agent significantly affect outcome after coronary artery surgery , 1989 .

[13]  A. Mäkivirta,et al.  A knowledge-based alarm system for monitoring cardiac operated patients — technical construction and evaluation , 1993, International journal of clinical monitoring and computing.

[14]  T M O'Carroll,et al.  Survey of alarms in an intensive therapy unit * , 1986, Anaesthesia.

[15]  Aki Mäkivirta,et al.  Frequency and reliability of alarms in the monitoring of cardiac postoperative patients , 1990, International journal of clinical monitoring and computing.