Download PDF
Methods Inf Med 1998; 37(01): 59-63
DOI: 10.1055/s-0038-1634497
Original Article
Schattauer GmbH

Diagnosis of Acute Appendicitis in Two Databases. Evaluation of Different Neighborhoods with an LVQ Neural Network

E. Pesonen
1   Department of Computer Science and Applied Mathematics, University of Kuopio, Finland
,
C. Ohmann
2   Theoretical Surgery Unit, Department of General and Trauma Surgery, Heinrich-Heine-University, Germany
,
M. Eskelinen
3   Department of Surgery, University of Kuopio, Finland
,
M. Juhola
1   Department of Computer Science and Applied Mathematics, University of Kuopio, Finland
› Author Affiliations
Further Information

Publication History

Publication Date:
07 February 2018 (online)

    Permissions and Reprints

Abstract:

The use of an artificial neural network system was studied in the diagnosis of acute abdominal pain, especially acute appendicitis, with patients from Finland and Germany. Separate Learning Vector Quantization (LVQ) neural networks were trained with a training set from each database and also with a combined database. Each neural network was evaluated separately with a test set of cases from each database. With the combined database different neighborhood methods were compared to find the optimal choice for this decision-making problem. The acute appendicitis cases of the Finnish test data set were classified well with all the networks, but the cases of the German test set were difficult to classify for the Finnish network. The use of larger neighborhoods increased the sensitivity of the classification by nearly 10%. The differences in the results of the Finnish and German databases suggest that there are differences in the data collection or patient populations between centers. Therefore, care must be taken when using decision-support systems which have been developed in other centers. Neural networks offer a method to evaluate differences between databases. With the use of larger neighborhoods, the effects of the differences on the accuracy of the classification can be partly diminished.

Keywords

Database - Acute Appendicitis - Diagnosis - Learning Vector Quantization - Neural Network - Neighborhood
 

  • REFERENCES

  • 1 de Dombal FT, Leaper DJ, Horrocks JC, Staniland JR, McCann AP. Computer-aided diagnosis of abdominal pain. BMJ 1972; 2: 9-13.
    PubMedGoogle Scholar
  • 2 Adams ID, Chan M, Clifford PC. et al. Computer-aided diagnosis of acute abdominal pain: a multicentre study. BMJ 1986; 293: 800-4.
    CrossrefPubMedGoogle Scholar
  • 3 Arnbjomsson E. Scoring system for computer-aided diagnosis of acute appendicitis. The value of prospective versus retrospective studies. Ann Chir Gynaecol 1985; 74: 159-66.
    PubMedGoogle Scholar
  • 4 Eberhart RC, Dobbins R, Hutton L. Neural network paradigm comparisons for appendicitis diagnoses. In: Computer-based Medical Systems. Proceedings of the Fourth Annual IEEE Symposium. Los Alamitos, California: IEEE Computer Society Press; 1991: 298-304.
    Google Scholar
  • 5 Eskelinen M, Ikonen J, Lipponen P. A computer-based diagnostic score to aid in diagnosis of acute appendicitis. Theor Surg 1992; 7: 86-90.
    PubMedGoogle Scholar
  • 6 Fathi-Torbaghan M, Meyer D. MEDUSA: A fuzzy expert system for medical diagnosis of acute abdominal pain. Meth Inform Med 1994; 33: 522-9.
    PubMedGoogle Scholar
  • 7 Fenyo G. Routine use of a scoring system for decision-making in suspected acute appendicitis in adults. Acta Chir Scand 1987; 153: 545-51.
    PubMedGoogle Scholar
  • 8 Forsstrom JJ, Gronroos JM, Eklund P, Irjala K. Using neuro-fuzzy tool to support medical decision making. A case study on the diagnosis of acute appendicitis. In: Proc Int Conf Neural Network. Plymouth, UK: University of Plymouth; 1994: 527-34.
    Google Scholar
  • 9 Ohmann C, Moustakis V, Yang Q, Lang K. Evaluation of automatic knowledge acquisition techniques in the diagnosis of acute abdominal pain. Artif Intell Med 1996; 8: 23-36.
    CrossrefPubMedGoogle Scholar
  • 10 Phillips S, Wiles J, Schwartz S. A comparison of three classification algorithms on the diagnosis of abdominal pains. In: Proceedings of the Second Australian Conference of Neural Networks (ACNN 91). Sydney: Sydney University Press; 1991: 283-7.
    Google Scholar
  • 11 Puppe B, Ohmann C, Goos K, Puppe F, Mootz O. Evaluating four diagnostic methods with acute abdominal pain cases. Meth Inform Med 1995; 34: 361-8.
    PubMedGoogle Scholar
  • 12 Van Way III CV, Murphy JR, Dunn EL, Elerding SC. A feasibility study of computer-aided diagnosis in appendicitis. Surg Gynaec Obstet 1982; 155: 685-8.
    PubMedGoogle Scholar
  • 13 Pesonen E, Juhola M, Ikonen J, Eskelinen M. A tentative automatic diagnosis of acute abdomen using neural networks. In: Multiple Paradigms for Artificial Intelligence. Proceedings of STeP94 Conference on Artificial Intelligence Research in Finland, Helsinki, Finland: Finnish Artificial Intelligence Society; 1994: 59-66.
    Google Scholar
  • 14 Pesonen E, Eskelinen M, Juhola M. Comparison of different neural network algorithms in the diagnosis of acute appendicitis. Int J BioMed Comp 1996; 40: 227-33.
    CrossrefPubMedGoogle Scholar
  • 15 Kohonen T. Self-Organizing Maps. Berlin, Heidelberg: Springer-Verlag; 1995
    Google Scholar
  • 16 de Dombal FT. Acute abdominal pain – an OMGE survey. Scand J Gastroenterol 1979; 14 [Suppl 56] 29-43.
    PubMedGoogle Scholar
  • 17 de Dombal FT. The OMGE acute abdominal pain survey. Progress report 1986. Scand J Gastroenterol 1988; 23 [Suppl 56] 35-42.
    PubMedGoogle Scholar
  • 18 Pesonen E, Ikonen J, Juhola M, Eskelinen M. Parameters for a knowledge base for acute appendicitis. Meth Inform Med 1994; 33: 220-6.
    PubMedGoogle Scholar
  • 19 de Dombal FT, de Baere H, van Elk PJ. et al. Objective medical decision making in acute abdominal pain. In: Beneken JEW, Thevenin V. eds. Advances in Biomedical Engineering. Amsterdam: IOS Press; 1993: 65-87.
    Google Scholar
  • 20 Sammon JW. A nonlinear mapping for data structure analysis. IEEE Trans Comput 1969; 5: 401-9.
    PubMedGoogle Scholar