Evaluating Four Diagnostic Methods with Acute Abdominal Pain Cases

Abstract:

Contemporary work in medical decision support is characterized by a multitude of methods. To investigate their relative strengths and weaknesses, we built four diagnostic expert systems based on different methods (Bayes, case-based classification, heuristic classification) for analysis of the same set of 1254 cases of acute abdominal pain previously documented in a prospective multicenter study. The results of the comparative evaluation indicate that differences in overall performance are relatively small (statistically not significant). The performance depends more on the quality of the knowledge base and the case data than on the inference methods of the expert systems. Methods relying exclusively on empirical knowledge (Bayes, case-based classification) tend to have slightly higher overall performance scores due to a diagnostic bias toward ordinary and common diseases. By contrast, methods operating with expert knowledge (e. g., heuristic classification) perform slightly worse overall, but are more sensitive toward uncommon (serious) diseases.

Keywords:

Decision Support Systems - Evaluation - Problem Solving - Case-Based Reasoning - Acute Abdominal Pain

• References

• 1 De Dombal FT, Leaper DJ. et al. Computeraided diagnosis of acute abdominal pain. BMJ 1972; 2: 9-13.
• 2 Adams ID, Chan M. et al. Computer aided diagnosis of acute abdominal pain: a multi-centre study. BMJ 1986; 293: 800-4.
• 3 McAdam WAF, Davenport P. et al. Twelve years’ experience of computer-aided diagnosis in a district general hospital. Ann Royal Coll Surgeons of England 1990; 72: 140-6.
• 4 Ohmann C, Kraemer M. Evaluierung von Entscheidungsunterstützungssystemen bei der Diagnose von akuten Bauchschmerzen. Biometrie und Informatik in Medizin und Biologie 1992; 23: 107-11.
• 5 Berner E, Webster G, Shugerman A. Performance of four computer-based diagnostic systems. N Engl J Med 1994; 330: 1792-6.
• 6 Wellwood J, Johannessen S, Spiegelhalter DJ. How does computer-aided diagnosis improve the management of acute abdominal pain?. Ann Royal Coll Surgeons of England 1992; 74: 40-6.
• 7 De Dombal FT, de Baere H. et al. Objective medical decision making in acute abdominal pain. In: Beneken JW, Thevenin V. eds. Advances in Biomedical Engineering. Amsterdam: IOS Press; 1993: 65-87.
• 8 Ohmann C, Kraemer M, Jäger S. et al. Akuter Bauchschmerz – standardisierte Befundung als Diagnoseunterstützung. Chirg 1992; 63: 113-23.
• 9 Ohmann C, Heicappell R. Personalcomputer im Krankenhaus (Personal Computer in the Hospital). Stuttgart/New York: Georg Thieme Verlag; 1990
• 10 Puppe F. Systematic Introduction to Expert Systems. Berlin: Springer Verlag; 1993
• 11 Puppe F, Goos K. Improving case based classification with expert knowledge. GWAI 91, 15. Fachtag für Künstliche Intelligenz 1991; 196-205.
• 12 Goos K. Fallbasiertes Klassifizieren – Methoden, Integration und Evaluation (Case-based Classification – Methods, Integration and Evaluation). (PhD Thesis in Computer Science) Department of Computer Science, University of Würzburg; Germany: 1995
• 13 Mootz O. Adaptives Verbessern von fallvergleichendem Zusatzwissen (Adaptive Improvement of Knowledge for Case-based Classification). (Masters’ thesis in Computer Science) Department of Computer Science, University of Würzburg; Germany: 1994
• 14 Puppe F, Pöck K. et al. Wiederverwendbare Bausteine für eine konfigurierbare Diagnostik-Shell (Reusable Components of a Configurable Diagnostic Shell). Künstliche Intelligenz 1994; 2: 13-8.
• 15 Aurc ARC. Aide au diagnostic et à la décision devant un syndrome douloureux abdominal aigu. Rev Epidem et Santé Publ 1984; 32: 40-4.
• 16 Fathi-Torbaghan M, Meyer D. MEDUSA: A fuzzy expert system for medical diagnosis of acute abdominal pain. Meth Inform Med 1994; 33: 522-9.