Framework for Biosignal Interpretation in Intensive Care and Anesthesia

Abstract:

Improved monitoring improves outcomes of care. As critical care is “critical”, everything that can be done to detect and prevent complications as early as possible benefits the patients. In spite of major efforts by the research community to develop and apply sophisticated biosignal interpretation methods (BSI), the uptake of the results by industry has been poor. Consequently, the BSI methods used in clinical routine are fairly simple. This paper postulates that the main reason for the poor uptake is the insufficient bridging between the actors (i.e., clinicians, industry and research). This makes it difficult for the BSI developers to understand what can be implemented into commercial systems and what will be accepted by clinicians as routine tools. A framework is suggested that enables improved interaction and cooperation between the actors. This framework is based on the emerging commercial patient monitoring and data management platforms which can be shared and utilized by all concerned, from research to development and finally to clinical evaluation.

Keywords:

Biosignal Interpretation - Framework for BSI - Intensive Care - Anesthesia

¹ One must bear in mind that a human being (a patient) is not a machine and therefore data derived from the patient is context sensitive in addition to possibly being erroneous and faulty.

• REFERENCES

• 1 Baselli A. et al. Cardiovascular variability signals: towards the identification of a closed-loop model of the neural control mechanisms. IEEE Trans BME 1988; 35: 1033-46.
• 2 Becker K. et al. Fuzzy logic approaches to intelligent alarms. IEEE EMB Mag 1994; 13: 710-6.
• 3 De Beer NAM. et al. Clinical evaluation of a method for automatic detection and removal of artifacts in auditory evoked potential monitoring. J Clin Mon 1995; 11: 381-91.
• 4 Bianchi AM. et al. Time-variant power spectrum analysis for the detection of transient episodes in HRV signal. IEEE Trans BME 1993; 40: 136-44.
• 5 Blom JA. The SIMPLEXYS experiment.’•fg’y real time expert systems in patient monitoring. . PhD thesis. Eindhoven: Eindhoven University of Technology; 1990
• 6 Bosnjak A. et al. An approach to intelligent ischaemia monitoring. J MBEC 1995; 33: 749-56.
• 7 Brain A, Koutlidis R. Knowledge modelization for brainstem auditory evoked potential interpretation: EPEXS. In Proc 14th Int’l C IEEE EMBS . 1992: 2479-80.
• 8 Dodd N. Neural network alarm monitor for use in intensive care - Comparative performance studies. In Proc Neural Networks and Expert Systems in Medicine and Health Care. . Rosen KG, Ifeachor E. (eds.). Plymouth: University Medical Centre; 1994: 441-5.
• 9 Fitzgerald WJ. et al. Analysis of the EEG using chaotic dynamics. BTJ Anaesth 1993; 71: 769P.
• 10 Gade I. et al. Modelling techniques and their application in high-dependency environments - learning models. Comp Meth & Progr Biomed (Accepted for publication).
• 11 van Gils MJ. Peak Identification in Auditory Evoked Potentials using Artificial Neural Networks . PhD thesis, ISBN 90-386-0036-4. Eindhoven: Eindhoven University of Technology; 1995
• 12 Held CM, Roy RJ. Multiple drug hemodynamic control by means of a supervisory-fuzzy rule-based adaptive control system: validation on a model. IEEE Trans BME 1995; 42: 371-85.
• 13 Karrakchou M. et al. Analyzing pulmonary capillary pressure: more accurate measurements using mutual wavelet packets for adaptive filtering. IEEE EMB Mag 1995; 14: 179-85.
• 14 Li C, Zheng C, Tai C. Detection of ECG characteristic points using wavelet transforms. IEEE Trans BME 1995; 42: 21-8.
• 15 Liberati D, Brandazza P. Detection of transient single-sweep somatosensory evoked potential changes via principal components analysis by inversion of simulated event related potentials. In Proc 14th Int’l C IEEE EMBS . 1992: 2454-5.
• 16 Loula P. et al. Nonlinear interpretation of respiratory sinus arrhythmia in anesthesia. ‘ Meth Inf Med 1994; 33: 52-7.
• 17 Moret-Bonillo V. et al. The PATRICA project. A semantic-based methodology for intelligent monitoring in the ICU. IEEE EMB Mag 1993; 12: 59-68.
• 18 Mäkivirta A, Koski EMJ. Alarm-inducing variability in cardiac postoperative data and the effects of prealarm delay. J Clin Mon 1994; 10: 153-62.
• 19 Orr JA, Westenskow DR. A breathing circuit alarm system based on neural networks. J Clin Mon 1994; 10: 101-9.
• 20 Piater J. et al. Fuzzy sets for feature identification in biomedical signals with self-assessment reliability: An adaptable algorithm modeling human procedure in BAEP analysis. Comp & Biomed Res 1995; 28: 335-53.
• 21 Prentza A, Wesseling KH. Catheter-manometer system damped blood pressures detected by neural nets. J MBEC 1995; 33: 589-95.
• 22 Sadasivan PK. et al. Use of finite FIR digital filter structures with improved magnitude and phase characteristics for reduction of muscle noise in EEG signals. J MBEC 1995; 33: 306-12.
• 23 Senhadji L. et al. Comparing Wavelet Transforms for recognizing cardiac patterns. IEEE EMB Mag 1995; 14: 167-73.
• 24 Shahsavar N. et al. VentEx: an on-line knowledge-based system to support ventilator management. Technology and Health Care 1994; 01: 233-43.
• 25 Sharma A, Wilson SE. EEG classification for estimating anesthetic depth during halothane anesthesia. In Proc 14th Int’l C IEEE EMBS . 1992: 2409-10.
• 26 Sigl JC, Chamoun NG. An introduction to bispectral analysis for the electroencephalogram. J Clin Mon 1994; 10: 392-404.
• 27 Signorini MG. et al. Bifurcation analysis of a physiological model of the baroreceptive control. In Proc 17th Int’l C IEEE EMBS . 1995
• 28 Summers R. et al. Ventilator Management. The role of knowledge-based technology. IEEE Trans BME 1993; 12: 89-98.
• 29 Thakor NV, Rix H. Wavelet analysis of evoked potentials. In Proc 14th Int’l C IEEE EMBS . 1992: 2446-7.
• 30 Thomson CE. et al. Assessment of anesthetic depth by clustering analysis and autoregressive modelling of electroencephalograms. Comp Meth & Progr Biomed 1991; 34: 125-38.
• 31 Watt RC. et al. Neural network classification of anesthetic levels using EEG spectral signatures. Anesthesiology 1993; 79: A456.
• 32 Watt RC. et al. EEG dimensionality and anesthetic level. Anesthesiology 1994; 81: A478.
• 33 Ying H, Shepard LC. Regulating mean arterial pressure in post-surgical cardiac patients. IEEE EMB Mag 1994; 13: 671-7.