Computer-based Decision Support in the Management of Primary Gastric non-Hodgkin Lymphoma

Abstract

Primary non-Hodgkin lymphoma of the stomach is a rare disorder for which clinical management has not yet been settled completely. Faced with the many uncertainties associated with the selection of a treatment for a patient with this disorder, it is difficult to determine the treatment that is optimal for the patient, as well as the prognosis to be expected. The development of a decision-theoretic model of non-Hodgkin lymphoma of the stomach is described. The model aims to assist the clinician in exploring various clinical questions, among others questions concerning prognosis and optimal treatment. Central to the model is a probabilistic network that offers an explicit representation of the uncertainties underlying the decision-making process. The model has been incorporated in a decisionsupport system. Preliminary evaluation results indicate that the performance ofthe model in its present form matches the performance of experienced clinicians.

Keywords

Medical Decision Making - Medical Expert Systems - Probabilistic Networks - Influence Diagrams - Gastric Lymphoma

• REFERENCES

• 1 Eidt S, Stolte M, Fischer R. Helicobacter pylori gastritis and primary gastric non-Hodgkin's lymphoma. J Clin Pathol 1994; 47: 436-9.
• 2 Wortherspoon AC, Doglioni C, Diss TC, Pan L, Moschini A, de Boni M, Isaacson PG. Regression of primary low-grade B-cell gastric lymphoma of mucosa-associated lymphoid tissue type after eradication of Helicobacter pylori. Lancet 1991; 342: 575-7.
• 3 Wyatt JI, Rathbone BJ. Immune response of the gastric mucosa to Campylobacter pylori Scan J Gastroenterol. 1988; 23 (Suppl 142) 44-9.
• 4 Hussell T, Isaacson PG, Crabtree JE, Spenser J. The response of cells from low-grade B-cell gastric lymphomas of mucosa-associated lyphoid tissue to Helicobacter pylori. Lancet 1993; 342: 571-4.
• 5 Bayerdorffer E, Neubauer A, Rudolph B. et al. Regression of primary gastric lymphoma of mucosa-associated lymphoid tissue type after cure of Helicobacter pylori infection. Lancet 1995; 345: 1591-4.
• 6 Azab MB, Henry-Amar M, Rougier P, Bognel C. et al. Prognostic factors in primary gastrointestinal non-Hodgkin's lymphoma. Cancer 1989; 64: 1208-17.
• 7 Shipp MA. Prognostic factors in aggressive non-Hodgkin's lymphoma: who has “high-risk disease”?. Blood 1994; 83 (5) 1165-73.
• 8 Valicenti RK, Wasserman TH, Kucik NA. Analysis of prognostic factors in localized gastric lymphoma: the importance of bulk of disease. Int J Radiation Oncology Biol Phys 1992; 27: 591-8.
• 9 Radaszkiewicz T, Dragosics B, Bauer P. Gastrointestinal malignant lymphomas of the mucosa-associated lymphoid tissue: factors relevant for prognosis. Gastroenterology 1992; 102: 1628-38.
• 10 Taal BG, Boot H, Van Heerde P, De Jong D, Hart GAM. Primary non-Hodgkin of the stomach: endoscopic pattern and prognosis in low versus high grade malignancy in relation to the MALT concept. Gut 1996; 39: 556-61.
• 11 Shipp MA, Harrington DP, Anderson JR, Armitage JO, Bonadonna G, Brittinger G, Cabanillas F, Canellos GP, Coiffier B, Connors JM, Cowan RA, Crowther D, Dahlberg S, Engelhard M, Fisher RI, Gisselbrecht C, Horning SJ, Lepage E, Lister A, Meerwaldt JH, Montserrat E, Nissen NI, Oken MM, Perterson BA, Tondini C, Velasquez WS, Yeap BY. A predictive model for aggressive NHL: The International Non-Hodgkin's Lymphoma Prognostic Factors Project. N Engl J Med 1993; 329: 987.
• 12 Hermans J, Krol AD, van Groningen K. et al. International Prognostic Index for aggressive non-Hodgkin's lymphoma is valid for all malignancy grades. Blood 1995; 86: 1460-3.
• 13 Gaag LC, van der. Bayesian belief networks: odds and ends. The Computer Journal 1996; 39: 79-113.
• 14 Jensen FV. An Introduction to Bayesian Networks. London: UCL Press; 1996
• 15 Pearl J. Probabilistic Reasoning in Intelligent Systems. San Mateo, California: Morgan Kaufman; 1988
• 16 Lauritzen SL, Spiegelhalter DJ. Local computations with probabilities on graphical structures and their application to expert systems. Journal of the Royal Statistical Society (Series B) 1987; 50: 157-224.
• 17 Sox HC, Blatt MA, Higgins MC, Marton KI. Medical Decision Making. Boston: Butterworths; 1988
• 18 Shachter RD. Evaluating influence diagrams. Operation Research 1986; 34 (6) 871-82.
• 19 Cooper GF. A method for using belief networks as influence diagrams. In: Proceedings of the 4th Workshop on Uncertainty in Artificial Intelligence. 1988; 55-63.
• 20 Andreassen S, Woldbye M, Falck B, Andersen SK. MUNIN – A causal probabilistic network for interpretation of electromyographic findings. In: McDermott J. ed. Proceedings of the 10th International Joint Conference on Artificial Intelligence. Los Altos, CA: Morgan Kaufmann; 1987: 366-72.
• 21 Heckerman DE, Nathwani BN. Towards normative expert systems: part II – probability-based representations for efficient knowledge acquisition and inference. Methods Inf Med 1992; 31: 106-16.
• 22 Spiegelhalter DJ, Franklin RCG, Bull K. Assessment, criticism and improvement of imprecise subjective probabilities for a medical expert system. In: Henrion M, Shachter RD, Kanal LN, Lemmer JF. eds. Uncertainty in Artificial Intelligence 5. Amsterdam: North-Holland; 1990: 285-94.
• 23 Lucas PJF, van der Gaag LC. Principles of Expert Systems. Wokingham: Addison-Wesley; 1991
• 24 Heckerman DE, Horvitz EJ, Nathwani BN. Towards normative expert systems: part I – The Pathfinder project. Methods Inf Med 1992; 31: 90-105.
• 25 Korver M, Lucas PJF. Converting a rule-based expert system into a belief network. Med Inf 1993; 18 (3) 219-41.
• 26 Lucas PJF. Knowledge acquisition for decision-theoretic expert systems. AISB Quaterly 1996; 94: 23-33.
• 27 Musshoff K. Klinische Stadieneinteilung der Nicht-Hodgkin-Lymphome. Strahlentherapie 1977; 153: 218-21.
• 28 Isaacson PG. Gastrointestinal lymphoma. Hum Pathol 1994; 25: 1020-164.
• 29 Olesen KG, Kjaerulff U, Jensen F, Jensen FV, Falck B, Andreassen S, Andersen SK. A MUNIN network for the median nerve – A case study on loops. Applied Artificial Intelligence 1989; 3: 301-19.
• 30 Wellman MP. Fundamental concepts of qualitative probabilistic networks. Artif Intell 1990; 33 (3) 257-303.
• 31 Pradhan M, Henrion M, Provan G, Del Favero B, Huang K. The Sensitivity of Belief Networks to Imprecise Probabilities: an Experimental Investigation. Report SMI-95-0595. Stanford, CA: Stanford University; 1995
• 32 Srinivas S, Breese J. IDEAL: Influence Diagram Evaluation and Analysis in Lisp Documentation and Users Guide. Palo Alto: Rockwell International Science Center; 1993
• 33 Hilden J, Habbema JDF. Evaluation of clinical decision aids – more to think about. Med Inf 1990; 15: 275-84.
• 34 Miller PL. The evaluation of artificial intelligence systems in medicine. Comput Programs Biomed 1986; 22: 5-11.
• 35 Wyatt JC, Spiegelhalter DJ. Evaluating medical expert systems: what to test for and how?. Med Inf 1990; 15 (3) 205-17.
• 36 Wyatt JC, Altman DG. Commentary: prognostic models: clinically useful or quickly forgotten. BMJ 1995; 311: 1539-41.
• 37 De Dombal FT, Dallos V, McAdam WA. Can computer-aided teaching packages improve clinical care in patients with acute abdominal pain?. BMJ 1991; 302: 1495-7.