Advertisement

Knowledge-based systems for lymph node pathology: A comparison of two approaches

  • Nguyen D. T. 
  • Park I. A. 
  • Cherubino P. 
  • Tamino P. B. 
  • Diamond L. W. 
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 934)

Abstract

A formal evaluation was performed between two knowledge-based systems for lymph node pathology: 1) Intellipath, Kiel edition, a Bayesian system; and, 2) “Professor Amadeus”, which uses categorical reasoning and defined diagnostic patterns. The evaluation, involving three pathologists, was based on 57 lymph node biopsies. Intellipath demonstrated satisfactory performance, with from 63.2% to 71.9% correct answers, depending on the experience level of the pathologist. “Professor Amadeus” achieved better results, with accuracy rates ranging from 93% to 96.5%. In this study, the better performance of “Professor Amadeus” could be attributed to a more effective multiparameter approach, fewer errors in the knowledge base, and better handling of input parameters.

Keywords

Mycosis Fungoides Lymph Node Module Categorical Reasoning Diagnostic Pattern Follicular Dendritic Cell Sarcoma 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Deber RB, Baumann AO. Clinical reasoning in medicine and nursing: Decision making versus problem solving. Teach Learn Med. 1992;4:140–6.Google Scholar
  2. [2]
    Szolovits P, Pauker SG. Categorical and probabilistic reasoning in medical diagnosis. Artif Intell. 1978;11:115–44.CrossRefGoogle Scholar
  3. [3]
    Diamond LW, Mishka VG, Seal AH, Nguyen DT. Are normative expert systems appropriate for diagnostic pathology? J Am Med Informatics Assoc. 1995; (in press).Google Scholar
  4. [4]
    Feinstein AR. An analysis of diagnostic reasoning I. The domains and disorders of clinical macrobiology. Yale J Bio Med. 1973;46:212–32.Google Scholar
  5. [5]
    Feinstein AR. An analysis of diagnostic reasoning II. The strategy of intermediate decisions. Yale J Bio Med. 1973;46:264–83.Google Scholar
  6. [6]
    Elstein AS. Paradigms for research on clinical reasoning: A researcher's commentary. Teach Learn Med. 1992;4:147–9.Google Scholar
  7. [7]
    Sultan C, Imbert M, Priolet G. Decision-making system (DMS) applied to hematology. Diagnosis of 180 cases of anemia secondary to a variety of hematologic disorders. Hematol Pathol. 1988;2:221–8.PubMedGoogle Scholar
  8. [8]
    Heckerman DE, Horvitz, EJ, Nathwani BN. Toward normative expert systems: Part I The pathfinder project. Meth Inf Med. 1992;31:90–105.Google Scholar
  9. [9]
    Heckerman DE, Nathwani BN. Toward normative expert systems: Part II Probability-Based Representations for efficient knowledge acquisition and inference. Meth Inf Med. 1992;31:106–16.Google Scholar
  10. [10]
    Nathwani BN, Heckerman DE, Horvitz EK, Lincoln TL. Integrated expert systems and videodisc in surgical pathology: An overview. Hum Path. 1990;21:11–27.PubMedGoogle Scholar
  11. [11]
    Nguyen DT, Diamond LW, Priolet G, Sultan C. A decision support system for diagnostic consultation in laboratory hematology. In: Lun KC, Degoulet P, Piemme TE, Rienhoff O, eds. MEDINFO 92, Amsterdam: North Holland, 1992;591–95.Google Scholar
  12. [12]
    Diamond LW, Nguyen DT, Sheridan BL, Strul M, Bailey K, Bak A. An automated hematology laboratory with computer-controlled robotics. In: Greenes RA et al. MEDINFO 95 (in press).Google Scholar
  13. [13]
    Diamond LW, Nguyen DT, Jouault H, Imbert M. Evaluation of a knowledge-based system for interpreting flow cytometric immunophenotyping data. In: Reichert A, Sadan BA, Bengtsson S, Bryant J, Piccolo U (eds). Proceedings of MIE 93 London: Freund Publishing House, 1993,124–8.Google Scholar
  14. [14]
    Diamond LW, Nguyen DT, Andreeff M, Maiese RL, Braylan RC. A knowledgebased system for the interpretation of flow cytometry data in leukemias and lymphomas. Cytometry. 1994; 17:266–73.PubMedGoogle Scholar
  15. [15]
    Nguyen DT, Cherubino P, Tamino PB, Diamond LW. Computer-assisted bone marrow interpretation: a pattern approach. In: Reichert A, Sadan BA, Bengtsson S, Bryant J, Piccolo U (eds). Proceedings of MIE 93. London: Freund Publishing House, 1993;119–23.Google Scholar
  16. [16]
    Nguyen DT, Diamond LW, Cherubino P, Koala WBJ, Imbert M, Andreeff M. A diagnostic workstation for neoplastic bone marrow diseases: Evaluation on 526 cases. In: Greenes RA et al. MEDINFO 95 (in press).Google Scholar
  17. [17]
    Nguyen DT, Mishka VG, Moskowitz FB, Diamond LW. A multiparameter decision support system for lymph node pathology. In: Barahona P, Veloso M, Bryant J (eds). Proceedings of MIE 94. Lisbon: 1994; 162–7.Google Scholar
  18. [18]
    Diamond LW, Nguyen DT. Communication between expert systems in haematology. In: Richards B (ed). Healthcare Computing 1993 — Current Perspectives in Healthcare Computing, Weybridge, UK: BJHC Books, 1993;111–19.Google Scholar
  19. [19]
    Middleton B, Shwe MA, Heckerman DE, Henrion M, Horvitz EJ, Lehmann HP, Cooper GF. Probabilistic diagnosis using a reformulation of the INTERNIST-1/QMR knowledge base II. Evaluation of diagnostic performance. Meth Inform Med 1991;30:256–67.PubMedGoogle Scholar
  20. [20]
    Li Y-C, Haug PJ. Evaluating the quality of a probabilistic diagnostic system using different inferencing strategies. In: Safran C, ed. Proceedings of the Seventeenth Annual Symposium on Computer Applications in Medical Care. New York: McGraw-Hill, 1993;471–7.Google Scholar
  21. [21]
    Berner ES, Webster GD, Shugerman AA, Jackson JR, Algina J, Baker AL, Ball EV, Cobbs G, Dennis VW, Frenkel EP, Hudson LD, Mangall EL, Rackley CE, Taunton OD. Performance of four computer-based diagnostic systems. N Engl J Med 1994;330:1792–6.PubMedGoogle Scholar
  22. [22]
    Lennert K. Malignant Lymphomas other than Hodgkin's Disease. New York: Springer-Verlag, 1978.Google Scholar
  23. [23]
    Clancey WJ. Heuristic classification. Artif Intell 1985; 27: 289–350.CrossRefGoogle Scholar
  24. [24]
    Nathwani BN. Diagnostic significance of morphologic patterns in lymph node proliferations. In: Knowles DM, ed. Neoplastic Hematopathology. Baltimore: Williams & Wilkins, 1992;407–25.Google Scholar
  25. [25]
    Heckerman DE, Nathwani BN. An evaluation of the diagnostic accuracy of pathfinder. Comput Biomed Res. 1992;25:56–74.PubMedGoogle Scholar
  26. [26]
    Nathwani BN, Brynes RK, Lincoln T, Hansmann ML. Classifications of Non-Hodgkin's lymphomas. In: Knowles DM, ed. Neoplastic Hematopathology. Baltimore: Williams & Wilkins, 1992:555–601.Google Scholar
  27. [27]
    van Ginneken, van der Lei J. Understanding differential diagnostic disagreement in pathology. In: Proceedings of the Fifteenth Annual Symposium on Computer Applications in Medical Care. New York: McGraw-Hill, 1991:99–103.Google Scholar
  28. [28]
    Li Y-C, Haug PJ. Evaluating the quality of a probabilistic diagnostic system using difference inference strategies. In: Proceedings of the Seventeenth Annual Symposium on Computer Applications in Medical Care. New York: McGraw-Hill, 1993:471–477.Google Scholar
  29. [29]
    Vonderheid EC, Diamond LW, Lai SM, Au F, Dellavechia MA. Lymph node histopathologic findings in cutaneous T-cell lymphoma. A prognostic classification based on morphologic assessment. Am J Clin Pathol 1992;97:121–9.PubMedGoogle Scholar
  30. [30]
    Kim H, Zelma RJ, Fox M, Bennett JM, Berard CW, Butler JJ, Byrne GE Jr., Dorfman RF, Hartsock RJ, Mann RB, Neiman RS, Rebuck JW, Sheehan WW, Variakojis D, Wilson JF, Rappaport H. Pathology panel for lymphoma clinical studies: a comprehensive analysis of cases accumulated since its inception. J Nat Cancer Inst 1982;68:43–67.PubMedGoogle Scholar
  31. [31]
    Velez-Garcia E, Durant J, Guams R, Bartolucci A. Results of a uniform histopathologic review system of lymphoma cases. Cancer 1983;52:675–9.PubMedGoogle Scholar
  32. [32]
    Browman GP, Neame PB, Soamboonsrup P. The contribution of cytochemistry and immunophenotyping to the reproducibility of the FAB classification in acute leukemia. Blood 1986;68:900–5.PubMedGoogle Scholar
  33. [33]
    Harris NL, Jaffe ES, Stein H, Banks PM, Chan JKC, Cleary ML, Delsol G, Wolf-Peeters CD, Falini B, Gatter KC, Grogan TM, Isaacson PG, Knowles DM, Mason DY, Muller-Hermelink HK, Pileri SA, Piris MA, Ralfkiaer E, Warnke RA. A revised European-American classification of lymphoid neoplasms: A proposal from the international lymphoma study group. Blood 1994;84:1326–92.Google Scholar
  34. [34]
    Diamond LW, Nguyen DT. Linking an electronic textbook to expert systems in haematology. In: Richards B, ed. Healthcare Computing 1994-Current Perspectives in Healthcare Computing, Weybridge, UK:BJHC Books, 1993,269–79.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Nguyen D. T. 
    • 1
  • Park I. A. 
    • 1
  • Cherubino P. 
    • 1
  • Tamino P. B. 
    • 1
  • Diamond L. W. 
    • 1
  1. 1.Pathology InstituteUniversity of CologneGermany

Personalised recommendations