Development and Evaluation of Fuzzy Criteria for the Diagnosis of Rheumatoid Arthritis

H. Leitich; K.-P. Adlassnig; G. Kolarz

doi:10.1055/s-0038-1634678

Methods of Information in Medicine, Table of Contents

Methods Inf Med 1996; 35(04/05): 334-342
DOI: 10.1055/s-0038-1634678

Original Article

Schattauer GmbH

Development and Evaluation of Fuzzy Criteria for the Diagnosis of Rheumatoid Arthritis

Authors

H. Leitich

¹Department of Medical Computer Sciences, University of Vienna, Baden, Austria
K.-P. Adlassnig

¹Department of Medical Computer Sciences, University of Vienna, Baden, Austria
G. Kolarz

²Clinic for Rheumatic Diseases of the Social Insurance Company for Trade and Industry, Baden, Austria

³Institute for Rheumatology in Baden, Austria

Abstract

Abstract:

In 1987, the American Rheumatism Association issued a set of criteria for the classification of rheumatoid arthritis (RA) to provide a uniform definition of RA patients. Fuzzy set theory and fuzzy logic were used to transform this set of criteria into a diagnostic tool that offers diagnoses at different levels of confidence: a definite level, which was consistent with the original criteria definition, as well as several possible and superdefinite levels. Two fuzzy models and a reference model which provided results at a definite level only were applied to 292 clinical cases from a hospital for rheumatic diseases. At the definite level, all models yielded a sensitivity rate of 72.6% and a specificity rate of 87.0%. Sensitivity and specificity rates at the possible levels ranged from 73.3% to 85.6% and from 83.6% to 87.0%. At the superdefinite levels, sensitivity rates ranged from 39.0% to 63.7% and specificity rates from 90.4% to 95.2%. Fuzzy techniques were helpful to add flexibility to preexisting diagnostic criteria in order to obtain diagnoses at the desired level of confidence.

Keywords:

Fuzzy Set Theory - Expert Systems - Diagnosis - Rheumatoid Arthritis - CADIAG-2

Full Text

References

References
1 Adlassnig K-P. A fuzzy logical model of computer-assisted medical diagnosis. Meth Inform Med 1980; 19: 141-8.
2 Adlassnig K-P. Fuzzy set theory in medical diagnosis. IEEE T Syst Man Cyb 1986; 16: 260-5.
3 Adlassnig K-P. Uniform representation of vagueness and imprecision in patient’s medical findings using fuzzy sets. In: Trappl R. (ed). Proceedings of Cybernetics and Systems ’88. Dordrecht: Kluwer Academic Publishers; 1988: 685-92.
4 Adlassnig K-P, Kolarz G. Representation and semiautomatic acquisition of medical knowledge in CADIAG-1 and CADIAG-2. Comput Biomed Res 1986; 19: 63-79.
5 Adlassnig K-P, Kolarz G, Scheithauer W, Effenberger H, Grabner G. CADIAG: Approaches to computer-assisted medical diagnosis. Comput Biol Med 1985; 15: 315-35.
6 Adlassnig K-P, Scheithauer W. Performance evaluation of medical expert systems using ROC curves. Comput Biomed Res 1989; 22: 297-313.
7 Bernelot Moens HJ, Van der Korst JK. Development and validation of a computer program using Bayes’ theorem to support diagnosis of rheumatic diseases. Ann Rheum Dis 1992; 51: 266-71.
8 Horn W. MESICAR – A medical expert system integrating causal and associative reasoning. Appl Artif Intell 1989; 3: 305-56.
9 Kingsland III LC, Lindberg DAB. The criteria form of knowledge representation in medical artificial intelligence. In: Salamon R, Blum B, Jorgensen M. eds. Proceedings of MEDINFO ’86. Elsevier Science Publ; 1986: 12-16.
10 Kingsland III LC, Lindberg DAB, Sharp GC. Anatomy of a knowledge-based consultant system: AI/RHEUM. MD Comput 1986; 3: 18-26.
11 Kolarz G, Adlassnig K-P. Problems in establishing the medical expert systems CADIAG-1 and CADIAG-2 in rheumatology. J Med Syst 1986; 10: 395-405.
12 Mathew B, Norris D, Hendry D, Waddell G. Artificial intelligence in the diagnosis of low back pain and sciatica. Spine 1988; 13: 168-72.
13 McCrea JD, McCredie MR, McSherry DM, Brooks PM. A controlled evaluation of diagnostic criteria in the development of a rheumatology expert system. Brit J Rheumatol 1989; 28: 13-7.
14 Schewe S, Herzer P, Krüger K. Prospective application of an expert system for the medical history of joint pain. Klin Wochenschr 1990; 68: 466-71.
15 Schewe S, Scherrmann W, Gierl L. Evaluation and measuring of benefit of an expert system for differential diagnosis in rheumatology. In: Rienhoff O, Piccolo U, Schneider B. eds. Expert Systems and Decision Support in Medicine. Berlin: Springer-Verlag; 1988: 351-4.
16 Adlassnig K-P, Leitich H, Kolarz G. On the applicability of diagnostic criteria for the diagnosis of rheumatoid arthritis in an expert system. Expert Syst Appl 1993; 6: 441-8.
17 Arnett FC, Edworthy SM, Bloch DA. et al. The American Rheumatism Association 1987 revised criteria for the classification of rheumatoid arthritis. Arthritis Rheum 1988; 33: 315-24.
18 Ropes MW, Bennett GA, Cobb S, Jacox R, Jassar RA. Revision of diagnostic criteria for rheumatoid arthritis. B Rheum Dis 1958; 9: 175-7.
19 Leitich H, Adlassnig K-P, Schuh C, Kolarz G. Improving diagnostic performance with fuzzy logic: A demonstration with the medical expert system CADIAG-2. In: Trappl R. ed. Proceedings of Cybernetics and Systems ’94. Singapore: World Scientific Publishing; 1994: 263-70.
20 Bolc L, Borowik P. Many-Valued Logics 1 – Theoretical Foundations. New York: Springer-Verlag; 1992
21 Steinbrocker O, Traeger CH, Batterman RC. Therapeutic criteria in rheumatoid arthritis. JAMA 1949; 140: 659-62.