Abstract
The interpretation of automatically collected data to produce intelligent alarms and identify particular conditions is nearly impossible without identifying the specific context in which the data are obtained. Shifts in clinical context occur because of changes in the patient’s physiologic state, or due to the passage of time, or due to changes imposed by therapeutic intervention such as surgery. Techniques to identify such changes in clinical context are discussed with particular attention to the application of cluster analysis, discriminant analysis, and statistical predictors. An example of these analyses applied to EEG data is presented, showing an unexpected hysteresis of EEG behavior in response to an hypoxic challenge.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Seiver A, Holtzman S. Decision analysis: a framework for critical care decision assistance. Int J Clin Monit Comput 1989; 6: 137–56.
Moorman RC, Mackenzi CF, Ho GH, Barnas GM, Wilson PD, Matjasko MJ. Automated real-time data acquisition and analysis of cardiorespiratory function. Int J Clin Monit Comput 1991; 8: 56–59.
King PH, Smith BE. Computerized monitoring at Vanderbilt University status and future directions. Int J Clin Monit Comput 1991; 8: 117–20.
Rampil IJ. Intelligent detection of artifact. In: Gravenstein JS, Newbower RS, Ream AK, Smith NT (eds) The automated anesthesia record and alarm systems. Boston: Buttersworths, 1987: 175–90.
Koski EMJ, Makivirta A, Sukuvaara T, Kari A. Frequency and reliability of alarms in the monitoring of cardiac post-operative patients. Int J Clin Monit Comput 1990; 7: 129–33.
Waterson CK, Calkins JM. Development directions for monitoring in anesthesia. Semin Anesthesia 1986; 5: 225–36.
Ream AK. Future trends in monitoring and biomedical instrumentation. In: Saidman LJ, Smith NT (eds) Monitoring in Anesthesia. 2nd ed. Boston: Butterworths, 1984: 535–50.
Coleman WP, Siegel JH, Giovannini I, DeGaetano A, Goordarzi S, Tacchino RM, et al. Probability and the patient state space. Int J Clin Monit Comput 1990; 7: 201–15.
Aventi RK, Charlton JD. A critical review of trend-detection methodologies for biomedical monitoring systems. Crit Rev Biomed Eng 1990; 17: 621–59.
Rampil IJ, Holzer JA, Quest DQ, et al. Prognostic value of computerized EEG analysis during carotid endarterectomy. Anesth Analg 1983; 62: 186–92.
Brunner JX, Westenskow DR, Zelenkov P. Prototype ventilator and alarm algorithm for the NASA space station. J Clin Monit. 1989; 5: 90–9.
Pryor TA. Development of decision support systems. Int J Clin Monit Comput 1990; 7: 137–46.
DeRoach JN. Neural networks—an artificial intelligence approach to the analysis of clinical data. Australas Phys Eng Sci Med 1989; 12: 100–6.
Orr JA, Kuck K, Farrell RM, Westenskow DR. Neural network breathing circuit alarms in an anesthesia work-station [abstract]. Anesthesiology 1991; 75: 1005A.
Henderfer MS, Blashfield RK. Cluster analysis. Beverly Hills: Sage Publications, 1984.
Predicting cure and credit: discriminant analysis [computer program]. SPSS/PC and Statistics Guide. Chicago: SPSS Inc., 1988; 1: B1–B39.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Bloom, M.J. Techniques of identify clinical contexts during automated data analysis. J Clin Monit Comput 10, 17–22 (1993). https://doi.org/10.1007/BF01133522
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF01133522