Accuracy in the Diagnostic Prediction of Acute Appendicitis Based on the Bayesian Network Model

S. Sakai; K. Kobayashi; J. Nakamura; S. Toyabe; K. Akazawa

doi:10.3414/ME9066

Methods of Information in Medicine, Table of Contents

Methods Inf Med 2007; 46(06): 723-726
DOI: 10.3414/ME9066

Original Article

Schattauer GmbH

Accuracy in the Diagnostic Prediction of Acute Appendicitis Based on the Bayesian Network Model

S. Sakai

¹Division of Information Science and Biostatistics, Niigata University Graduate School of Medical and Dental Sciences, Niigata, Japan

,

K. Kobayashi

¹Division of Information Science and Biostatistics, Niigata University Graduate School of Medical and Dental Sciences, Niigata, Japan

,

J. Nakamura

¹Division of Information Science and Biostatistics, Niigata University Graduate School of Medical and Dental Sciences, Niigata, Japan

,

S. Toyabe

²Department of Medical Informatics, Niigata University Medical and Dental Hospital, Niigata, Japan

,

K. Akazawa

²Department of Medical Informatics, Niigata University Medical and Dental Hospital, Niigata, Japan

› Author Affiliations

Abstract

Summary

Objectives : The diagnosis of acute appendicitis is difficult, and a diagnostic error will often lead to either a perforation or the removal of a normal appendix. In this study, we constructed a Bayesian network model for the diagnosis of acute appendicitis and compared the diagnostic accuracy with other diagnostic models, such as the naive Bayes model, an artificial neural network model, and a logistic regression model.

Methods : The data from 169 patients, who suffered from acute abdominal pain and who were suspected of having an acute appendicitis, were analyzed in this study. Nine variables were used for the evaluation of the accuracy of the four models for the diagnosis of an acute appendicitis. The naive Bayes model, the Bayesian network model, an artificial neural network model, and a logistic regression model were used i this study for the diagnosis of acute appendicitis. These four models were validated by using the “632 + bootstrap method” for resampling. The levels of accuracy of the four models for diagnosis were compared by the error rates and by the areas under the receiver operating characteristic curves.

Results : Through the course of illness, 50.9% (86 of 169) of the patients were diagnosed as having an acute appendicitis. The error rate was the lowest in the Bayesian network model, as compared with the other diagnostic models. The area under the receiver operating characteristic curve analysis also showed that the Bayesian network model provided the most reliable results.

Conclusion : The Bayesian network model provided the most accurate results in comparison to other models for the diagnosis of acute appendicitis.

Keywords

Artificial neural network - Bayesian network - diagnostic prediction - logistic regression analysis

Full Text

References

References
1. Andersson RE. Meta-analysis of the clinical and laboratory diagnosis of appendicitis. Br J Surg 2004; 91 (28) 37.
2. Eldar S, Nash E, Sabo E, Matter I, Kunin J, Mogilner JG, Abrahamson J. Delay of surgery in acute appendicitis. Am J Surg 1997; 173: 194-198.
3. Arnbjornsson E. Scoring system for computer-aided diagnosis ofacute appendicitis. The value of prospective versus retrospective studies. Ann Chir Gynaecol 1985; 74: 159-166.
4. Eskelinen M, Ikonen J, Lipponen P. A computer-based diagnostic score to aid in diagnosis of acute appendicitis. A prospective study of 1333 patients with acute abdominal pain. Theor Surg 1992; 7 (86) 90.
5. Alvarado A. A practical score for the early diagnosis of acute appendicitis. Ann Emerg Med 1986; 15 (557) 564.
6. Ohmann C, Franke C, Yang Q. Clinical benefit of a diagnostic score for appendicitis: results of a prospective interventional study. German Study Group of Acute Abdominal Pain. Arch Surg 1999; 134 (993) 996.
7. Tzanakis NE, Efstathiou SP, Danulidis K. et al. A new approach to accurate diagnosis of acute appendicitis. World J Surg 2005; 29: 1151-1156.
8. Kharbanda AB, Taylor GA, Fishman SJ, Bachur RG. A clinical decision rule to identify children at low risk for appendicitis. Pediatrics 2005; 116: 709-716.
9. Burnside ES, Rubin DL, Fine JP, Shachter RD, Sisney GA, Leung WK. Bayesian network to predict breast cancer risk of mammographic microcalcifications and reduce number of benign biopsy results: initial experience. Radiology 2006; 240 (03) 666-673.
10. Herskovits EH, Cooper GH. Algorithms for Bayesian belief-network precomputation. Methods Inf Med 1991; 30 (02) 81-89.
11. Alvarez SM, Poelstra BA, Burd RS. Evaluation of a Bayesian decision network for diagnosing pyloric stenosis. J Pediatr Surg 2006; 41 (01) 155-161.
12. Wang XH, Zheng B, Good WF, King JL, Chang YH. Computer-assisted diagnosis of breast cancer using a data-driven Bayesian belief network. Int J Med Inform 1999; 54 (02) 115-126.
13. Kline JA, Novobilski AJ, Kabrhel C, Richman PB, Courtney DM. Derivation and validation of a Bayesian network to predict pretest probability of venous thromboembolism. Ann Emerg Med 2005; 45 (03) 282-290.
14. Aronsky D, Haug PJ. Diagnosing community-acquired pneumonia with a Bayesian network. Proc AMIA Symp 1998; 632-636.
15. Gevaert O, De Smet F, Timmerman D, Moreau Y, De Moor B. Predicting the prognosis of breast cancer by integrating clinical and microarray data with Bayesian networks. Bioinformatics 2006; 22 (14) e184-190.
16. Sakellaropoulos GC, Nikiforidis GC. Development of a Bayesian network for the prognosis of head injuries using graphical model selection techniques. Methods Inf Med 1999; 38 (01) 37-42.
17. Rodin AS, Boerwinkle E. Mining genetic epidemiology data with Bayesian networks I: Bayesian networks and example application (plasma apoE levels). Bioinformatics 2005; 21 (15) 3273-3278.
18. Murphy K. The Bayes Net Toolbox for MATLAB. Computing science and statistics 2001; 33: 1786-1789.
19. Friedman N, Koller D. Being Bayesian about network structure. In: Uncertainty in Artificial Intelligence: Proceedings ofthe Sixteenth Conference (UAI-2000) 2000: 201-210.
20. Angelopoulos N, Cussens J. Markov chain Monte Carlo using tree-based priors on model structure. Proceedings of the Sventeenth Conference (UAI-2001) 2001: 16-23.
21. Schurink CA, Lucas PJ, Hoepelman IM, Bonten MJ. Computer-assisted decision support for the diagnosis and treatment of infectious diseases in intensive care units. Lancet Infect Dis 2005, 5: 305-212 (Review)
22. Efron B, Tibshirani R. Improvement on cross-validation: The .632+ bootstrap method. J Am Stat Assoc 1997; 92: 548-560.
23. Wehberg S, Schumacher M. A comparison of non-parametric error rate estimation methods in classification problems. Biom J 2004; 46: 35-47.
24. Hanley JA, McNeil BJ. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 1982; 143 (29) 36.
25. http://www.cs.berkeley.edu/~murphyk/Bayes/bnt.html
26. Yen AM, Liou HH, Lin HL, Chen TH. Bayesian random-effect model for predicting outcome fraught with heterogeneity. Methods Inf Med 2006; 45 (06) 631-637.
27. Metzler D, Nebel ME. Predicting RNA secondary structures with pseudoknots by MCMC sampling. J Math Biol. (in press)
28. Ma J, Amos CI, Daw EW. Ascertainment correction for Markov chain Monte Carlo segregation and linkage analysis of a quantitative trait. Genet Epidemiol 2007; 31 (06) 594-604.
29. Li L., Yu M, Chin R, Lucksiri A, Flockhart DA, Hall SD. Drug-drug interaction prediction: Bayesian meta-analysis approach. Stat Med 2007; 26 (20) 3700-3721.
30. Liu J, Zhang Y, Zhang Q, Wang L, Zhang J. Study on mapping quantitative trait loci for animal complex binary traits using Bayesian-Markov chain Monte Carlo approach. Sci China C Life Sci 2006; 49 (06) 552-529.
31. Toft N, Innocent GT, Gettinby G, Reid SWJ. Assesing the convergence of Markov chain Monte Carlo methods: An example from evaluation of diagnostic tests in absence of a gold standard. Prev Vet Med 2007; 79 (02) 4 244-256.
32. Hua J, Lowey J, Xiong Z, Dougherty ER. Noise-injected neural networks show promise for use on small-sample expression data. BMC Bioinformatics 2006; 7: 274.