AUTOMATED ARRHYTHMIA ANALYSIS — AN EXPERT SYSTEM FOR AN INTENSIVE CARE UNIT

Heart failure is the most common reason of death nowadays, but if the medical help is given directly, the patient’s life may be saved in many cases. Numerous heart diseases can be detected by means of analyzing electrocardiograms (ECG). This work concentrates on extracting characteristic features from ECG’s. The features are used to detect life-threating arrhythmias. A computer system has been developed that in future may become a part of a larger system used for monitoring patients at an intensive-care unit (ICU). State-of-the-art tools have been used in creation of the computer system. It correctly performs diagnosis but more work is required before the system could be utilized at the bedside. Krzysztof Dubowik Automated Arrhythmia Analysis – 7 An Expert System for an Intensive-Care Unit Acknowledgements At this point, I would also like to thank my supervisors Jan Eric Larsson and Piotr Szczepaniak as for without their effort this work could not be possible. Many thanks to Fredrik Dahlstrand for the Fuzzy MESS tool I used in this project and all the help and ideas he provided me with. I would also like to thank Bengt Öhman for his valuable remarks on the thesis. This work is courtesy of Swedish Institute, which has been kind enough to sponsor my visit to Sweden. Krzysztof Dubowik Automated Arrhythmia Analysis – 8 An Expert System for an Intensive-Care Unit Table of

[1]  G. Moody,et al.  QRS morphology representation and noise estimation using the Karhunen-Loeve transform , 1989, [1989] Proceedings. Computers in Cardiology.

[2]  R O Morales,et al.  Evaluation of QRS morphological classifiers in the presence of noise. , 1997, Computers and biomedical research, an international journal.

[3]  James A. Brule.  Fuzzy Systems: A Tutorial , 1985 .

[4]  W.J. Tompkins,et al.  Neural-network-based adaptive matched filtering for QRS detection , 1992, IEEE Transactions on Biomedical Engineering.

[5]  H. T. Nagle,et al.  A comparison of the noise sensitivity of nine QRS detection algorithms , 1990, IEEE Transactions on Biomedical Engineering.

[6]  J. Willis Hurst,et al.  Introduction to electrocardiography , 1973 .

[7]  P.C. Voukydis,et al.  A neural network system for detection of life-threatening arrhythmias, based on Kohonen networks , 1995, Computers in Cardiology 1995.

[8]  Robert I. Levine,et al.  A Comprehensive Guide to AI and Expert Systems , 1987, IEEE Expert.

[9]  K. Akazawa,et al.  Adaptive threshold QRS detection algorithm for ambulatory ECG , 1991, [1991] Proceedings Computers in Cardiology.

[10]  Roberto Togneri,et al.  QRS detection using morphological and rhythm information , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[11]  Milan Sonka,et al.  Image Processing, Analysis and Machine Vision , 1993, Springer US.

[12]  I. G. Umbers,et al.  An analysis of human decision-making in cement kiln control and the implications for automation , 1980 .

[13]  Jan Eric Larsson,et al.  Guardian: An Intelligent Autonomous Agent for Medical Monitoring and Diagnosis , 1998, IEEE Intell. Syst..

[14]  Myoungho Lee,et al.  A simple real-time QRS detection algorithm , 1996, Proceedings of 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[15]  N.V. Thakor,et al.  Applications of adaptive filtering to ECG analysis: noise cancellation and arrhythmia detection , 1991, IEEE Transactions on Biomedical Engineering.

[16]  Yu Hen Hu,et al.  QRS detection using a fuzzy neural network , 1995, Proceedings of 17th International Conference of the Engineering in Medicine and Biology Society.

[17]  K. Mcintyre,et al.  Textbook of advanced cardiac life support , 1983 .

[18]  A. Mocholi,et al.  Previous identification of QRS onset and offset is not essential for classifying QRS complexes in a single lead , 1997, Computers in Cardiology 1997.

[19]  Jan Eric Larsson.  MESS—A Minimal Expert System Shell , 1988 .

[20]  Kang-Ping Lin,et al.  A technique for automated arrythmia detection of Holter ECG , 1995, Proceedings of 17th International Conference of the Engineering in Medicine and Biology Society.

[21]  Sanjit K. Mitra,et al.  Handbook for Digital Signal Processing , 1993 .

[22]  W. Snodgrass.  Physiology , 1897, Nature.

[23]  Morten Lind,et al.  Modeling goals and functions of complex industrial plants , 1994, Appl. Artif. Intell..

[24]  Lotfi A. Zadeh,et al.  MAKING COMPUTERS THINK LIKE PEOPLE , 1984 .

[25]  A. Ruha,et al.  A real-time microprocessor QRS detector system with a 1-ms timing accuracy for the measurement of ambulatory HRV , 1997, IEEE Transactions on Biomedical Engineering.

[26]  J. Ulrich.  [Physiology of the heart]. , 1950, Zeitschrift fur Kreislaufforschung.

[27]  E. Ifeachor,et al.  Techniques for optimal enhancement and feature extraction of fetal electrocardiogram , 1995 .

[28]  Elpida T. Keravnou,et al.  Expert systems architectures , 1988 .

[29]  Jan Eric Larsson,et al.  Goals and functions of the human body: an MFM model for fault diagnosis , 1997, IEEE Trans. Syst. Man Cybern. Part A.

[30]  R. S. Anand,et al.  Efficient and reliable detection of QRS-segment in ECG signals , 1995, Proceedings of the First Regional Conference, IEEE Engineering in Medicine and Biology Society and 14th Conference of the Biomedical Engineering Society of India. An International Meet.

[31]  Willis J. Tompkins,et al.  A Real-Time QRS Detection Algorithm , 1985, IEEE Transactions on Biomedical Engineering.

[32]  J. Baldwin.  Fuzzy logic and fuzzy reasoning , 1979, 1979 18th IEEE Conference on Decision and Control including the Symposium on Adaptive Processes.

[33]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .