Methodology of ECG Interpretation in the Padova Program

Abstract

The main lines ofthe program designed for the interpretation of ECGs, developed in Padova by LADSEB-CNR with the cooperation of the Medical School of the University of Padova are described. In particular, the strategies used for (i) morphology recognition, (ii) measurement evaluation, and (iii) linguistic decision making are illustrated. The main aspect which discerns this program in comparison with other approaches to computerized electrocardiography is its ability of managing the imprecision in both the measurements and the medical knowledge through the use of fuzzy-set methodologies. So-called possibility distributions are used to represent ill-defined parameters as well as threshold limits for diagnostic criteria. In this way, smooth conclusions are derived when the evidence does not support a crisp decision. The influence of the CSE project on the evolution of the Padova program is illustrated.

Key-Words

Decision-Making - Fuzzy Sets - Linguistic Values - ECG Interpretation

• REFERENCES

• 1 Willems JL, Arnaud P, van Bemmel JH. et al. Common Standards for quantitative Electrocardiography: CSE Project Phase One. In: Ripley KL. ed. Computers in Cardiology 1982. Long Beach Ca: IEEE Computer Society; 1982: 69-74.
• 2 Willems JL. The CSE Project: goals and achievements. In: Willems JL, van Bemmel JH, Zywietz C. eds. Computer ECG Analysis: Towards Standardization. Amsterdam: North-Holland Publ Comp; 1986: 11-21.
• 3 Degani R. Un sistema di interpretazione automatica di ECG. In: Proc Convegno su Tecniche di Elaborazione di Segnali Biologici. Pavia 1974; 474-87.
• 4 Dalla-Volta S, Degani R. An approach to computer analysis of electrocardiograms. J Clin Comp 1976; 05: 205-12.
• 5 Cooksey JD, Dunn M, Massie E. Clinical Vectorcardiography and Electrocardiography. Chicago: Year Book Medical Publ; 1977
• 6 Saffiotti A. An AI view of the treatment of uncertainty. Knowledge Engin Rev 1988; 02: 75-97.
• 7 Dubois D, Prade H. Fuzzy Sets and Systems: Theory and Applications. New York: Academic Press; 1980
• 8 Martin-Clouaire R, Prade H. SPII-1: a simple inference engine capable of accommodating imprecision and uncertainty. In: Mitra G. ed. Computer-Assisted DecisionMaking. Amsterdam: North-Holland Publ Comp; 1986: 117-31.
• 9 Farreny H, Prade H, Wyss E. Approximate reasoning in a rule-based expert system using possibility theory: A case study. In: Kugler HJ. ed. Proc Internal Conj IFIP 86. Amsterdam: North-Holland Publ Comp; 1986: 407-13.
• 10 Buisson JC, Farreny H, Prade H. Dealing with imprecision and uncertainty in the expert system DIABETO-III. In: Proc 2nd Internal Conj on Artificial Intelligence (CIIAM-86). Paris: Hermes; 1986: 705-21.
• 11 Saitta L, Torasso P. Fuzzy characterization of coronary disease. Fuzzy Sets and Systems 1981; 05: 245-58.
• 12 Sanchez E, Gouvemet J, Bartolin R, Yovan L. Linguistic approach in fuzzy logic of the WHO classification of dyslipoproteinemias. In: Yager RR. ed. Fuz zy Sets and Possibility Theory. New York: Pergamon Press; 1982: 582-88.
• 13 Adlassnig K-P, Kolarz G. Representation and semiautomatic acquisition of medical knowledge in CADIAG-1 and CADIAG2. Comp Biomed Res 1986; 19: 63-79.
• 14 Degani R. Pattern recognition of piecewise-linear approximated ECG waveforms. In: Proc EUROCON 77 on Communications. Venezia 1977; Vol. II, 345-52.
• 15 Bortolan G, Cavaggion C, Degani R, Pacini G, Bressan M, Dalla-Volta S, Zampieri F. Metodologie di logica sfumata applicate alla diagnosi assistita da elaboratore in elettrocardiografia clinica. Rendiconti LX X XI Riunione Annuale A EI. Trieste. In: 1980 I.60..
• 16 Willems JL. CSE 2nd Progress Report. Leuven: ACCO Publ; 1982
• 17 Willems JL, Zywietz C, Arnaud P. et al. Influence of noise on wave boundary recognition by ECG measurement programs. Comp Biomed Res 1987; 20: 543-62.
• 18 Bortolan G, Cavaggion C, Degani R. A comparison of ECG measurements derived from 3, 6 and 12 simultaneous leads. In: Ripley KL. ed. Computers in Cardiology 1983. Long Beach Ca: IEEE Computer Society; 1983: 269-72.
• 19 Willems JL, Arnaud P, van Bemmel JH. et al. Establishment of a reference library for evaluating computer ECG measurement programs. Comp Biomed Res 1985; 18: 439-57.
• 20 Willems JL, Arnaud P, van Bemmel JH. et al. Assessment of the performance of electrocardiographic computer programs with the use of a reference database. Circulation 1985; 71: 523-34.
• 21 Bortolan G, Golferini F, Degani R. The CSE database in the development of a new algorithm for P wave recognition. In: Ripley KL. ed. Computers in Cardiology 1985. Long Beach Ca: IEEE Computer Society; 1985: 435-38.
• 22 Willems JL, Arnaud P, van Bemmel JH. et al. A reference data base for multilead electrocardiographic computer measurement programs. J Amer Coll Cardiol 1987; 10: 1313-21.
• 23 Degani R, Bortolan G. Computerized electrocardiography and fuzzy sets. In: Jones A, Kaufmann A, Zimmermann H-J. eds. Fuzzy Sets, Theory and Applications. Dordrecht: Reidel Publ; 1986: 317-29.
• 24 Degani R, Bortolan G. Fuzzy numbers in computerized electrocardiography. Fuzzy Sets and Systems 1987; 24: 345-62.
• 25 Degani R, Bortolan G. Combining measurement precision and fuzzy diagnostic criteria. In: Willems JL, van Bemmel JH, Zywietz C. eds. Computer ECG Analysis: Ibwards Standardization. Amsterdam: North-Holland Publ Comp; 1986: 177-82.
• 26 Degani R, Bortolan G. The problem of linguistic approximation in clinical decision-making. Intemat J Approx Reasoning 1988; 02: 143-62.
• 27 Degani R, Bortolan G. Fuzzy decisionmaking in electrocardiography. Artif Intell Med 1989; I: 87-91.
• 28 Bortolan G, Degani R. Linguistic approximation of fuzzy certainty factors in computerized electrocardiography. In: Gupta MM, Yamakawa T. eds. Fuz zy Computing. Amsterdam: North-Holland Publ Comp; 1988: 243-61.
• 29 Drazen E. Automated Electrocardiography in the United States. Cambridge Ma: Arthur D. Little Inc; 1976