Intelligent Signal Analysis Using Case-Based Reasoning for Decision Support in Stress Management - Computational Intelligence in Healthcare: Advanced Methodologies - page 176

Therefore we have shown that it is possible to reach near expert level performance of
a decision support system based on CBR for diagnosing stress. It is crucial to under-
stand what features an expert uses to see similarity between subjects. The develop-
ment of the approach has also lead to experts more clearly seeing what features they
use for classification which may lead to a standard procedure for diagnosis in the
future. This also provides important information to the clinician to make a decision
about individual treatment plans.
The CBR system with rather simple and intelligent analysis of sensor signals, al-
lows the use of finger temperature measurements in an autonomous system. This
enables the treatment of individuals to be carried out at home or in the work environ-
ment. This system can be valuable for decision support for non-experts or as a second
opinion for experts in stress management.
References
1. Northrop, R.B.: Signals and systems in biomedical engineering. CRC Press, New York
(2003)
2. Nilsson, M., Funk, P.: A case-based classification of respiratory sinus arrhythmia.
In: Funk, P., González Calero, P.A. (eds.) ECCBR 2004. LNCS (LNAI), vol. 3155, pp.
673-685. Springer, Heidelberg (2004)
3. Ölmeza, T., Dokur, Z.: Classification of heart sounds using an artificial neural network.
Pattern Recognition Letters 24(1-3), 617-629 (2003)
4. Sahambi, J.S., Tandon, S.N., Bhatt, R.K.P.: Using wavelet transforms for ECG characteri-
zation. An on-line digital signal processing system. Engineering in Medicine and Biology
Magazine 16(1), 77-83 (1997)
5. Kalayci, T., Ozdamar, O.: Wavelet preprocessing for automated neural network detection
of EEG spikes. Engineering in Medicine and Biology Magazine 14(2), 160-166 (1995)
6. Funk, P., Xiong, N.: Case-based reasoning and knowledge discovery in medical applica-
tions with time series. Computational Intelligence 22(3-4), 238-253 (2006)
7. Xiong, N., Funk, P.: Concise case indexing of time series in health science by means of
key sequence discovery. Applied Intelligence 28(3), 247-260 (2008)
8. Von Schéele, B.H.C., von Schéele, I.A.M.: The Measurement of Respiratory and
Metabolic Parameters of Patients and Controls Before and After Incremental Exercise on
Bicycle: Supporting the Effort Syndrome Hypothesis. Applied Psychophysiology and Bio-
feedback 24(3), 167-177 (1999)
9. Turban, E., Aronson, E.J.: Decision support systems and intelligent systems, 6th edn. Pren-
tice Hall, Englewood Cliffs (2001)
10. Bemmel, J.H.V., Musen, M.A.: Handbook of Medical informatics. Springer, Heidelberg
(1997)
11. Shortliffe, E.: Computer-based medical consultations: MYCIN. Elsevier North Holland,
New York (1976)
12. Watson, I.: Applying Case-Based Reasoning: Techniques for Enterprise Systems. Morgan
Kaufmann Publishers Inc., San Francisco (1997)
13. Aamodt, A., Plaza, E.: Case-based reasoning: Foundational issues, methodological varia-
tions, and system approaches. AI Communications 7, 39-59 (1994)
14. Hinkle, D., Toomey, C.: Applying Case-Based Reasoning to Manufacturing. AI Maga-
zine 16(1), 65-73 (1995)
15. Selye, H.: The Stress of Life. McGraw Hill, New York (1956); Rev. ed. (1976)