Trend Recognition in Clinical Signals using Template-Based Methods
07 February 2018 (online)
The recognition of clinically significant trends in monitored signals plays an important role in many medical diagnostic applications. A template-based system technique to identify characteristic patterns in time-series data is described, based on fuzzy logic. Fuzzy set theory allows the creation of fuzzy templates from linguistic rules. The resulting fuzzy template system can accommodate multiple time signals, relative or absolute trends, and automatically generates a normalised “goodness of fit” score. The template approach was originally developed for monitoring during anaesthesia but has the potential to be useful in other domains that require temporal pattern recognition.
- 1 Forsstrom JJ, Dalton KJ. Artificial neural networks for decision support in clinical medicine. Ann Med 1995; 27: 509-17.
- 2 Dawant BM, Manders EJ, Lindstrom DP. Adaptive signal analysis and interpretation for real-time intelligent patient monitoring. Method Inform Med 1994; 33: 60-3.
- 3 Haimowitz IJ, Kohane IS. Automated trend detection with multiple temporal hypotheses. 13th Int Joint Conf on Artif Intell; Chamberey, France: 1993. 146-51.
- 4 Vitez TS, Wada R, Macario A. Fuzzy logic: theory and medical applications. J Cardiovascular Anes 1996; 10: 800-8.
- 5 Steimann F. The interpretation of time-varying data with DiaMon-1. Artif Intell Med 1996; 8: 343-57.
- 6 Dubois D, Prade H. Fuzzy Sets and Systems: Theory and Applications . New York: Academic Press; 1980
- 7 Lowe A, Jones RW, Harrison MJ. The SENTINEL intelligent anaesthesia monitor, to be presented Int. ICSC Sympos on Soft Comp in Biomedicine; Rochester, New York: 1999
- 8 Shafer G. A Mathematical Theory of Evidence. Princeton: Princeton University Press; 1976