Prospective validation of an artificial neural network as a computer-aided diagnosis of acute abdominal pain in a emergency room

Carlos M Cardozo Zepeda; Francisco Guadarrama Quijada; Jesús Reyes Corona; Rosamelia Fernández Capistrán; Dora M  Becerra; Manuel Adolfo Hernández; Miguel Lázaro León; Jesús Martínez Sánchez

2000, Number 5

Next >>

Med Crit 2000; 14 (5)

Prospective validation of an artificial neural network as a computer-aided diagnosis of acute abdominal pain in a emergency room

Cardozo ZCM, Guadarrama QF, Reyes CJ, Fernández CR, Becerra DM, Adolfo HM, Lázaro LM, Martínez SJ

Full text

How to cite this article

Language: Spanish
References: 24
Page: 159-164
PDF size: 169.90 Kb.

ABSTRACT

Objective: To investigate the value of an artificial neural network (ANN) to predicting the need of surgical treatment in patients with acute abdominal pain.
Design: Case series report.
Setting: Emergency room of a private medical center, Mexico City.
Patients: A total of 130 patients with acute abdominal pain.
Interventions: None.
Methods: An ANN was constructed with 14 input parameters, 13 hidden layers and a single output parameter.The 14 input parameters included clinical and laboratory data collected by emergency room physicians. The ANN was trained in 65 patients and tested in other 65.
Results: The ANN predicted correctly the diagnosis in 100% (18/18) of surgical patients and in 95% (45/47) of medical patients of the ANN tested.
Conclusion: These results suggest that an ANN can be a useful tool to predicting surgical treatment in patients with acute abdominal pain.

REFERENCES

Gill BD, Jenkins JR. Cost-effective evaluation and management of the acute abdomen. Surg Clin North Am 1996;76(1): 71-82.
Szolovits P, Patil RS, Schwartz WB. Artificial intelligence in medical diagnosis. Ann Intern Med 1988; 108: 80-87.
Baxt WG, Skora J. Prospective validation of artificial neural network trained to identify acute myocardial infarction.Lancet 1996; 6(347): 12-14.
Scott JA, Fisher RE, Palmer EL. Neural networks in ventilation-perfusion imaging. Part II. Effects of interpretive variability. Radiology 1996;198(3): 707-713.
Cross SS, Harrison RF, Kennedy L. Introduction to neural networks. Lancet 1997;346(12):1075-1079.
Gurriere MR, Detsky AS. Neural networks: What are they. Ann Intern Med 1991;115(11): 906-907.
Baxt WG. Use of an artificial neural network for the diagnosis of myocardial infarction. Ann Intern Med 1991; 115(11): 843-848.
Principe JC, Lefebvre WC, Euliano NR. Data fitting with linear models. In: Neural Systems: Fundamentals through simulation. Principe, 1996.
Reggia JA, Tuhrim S (eds). Computer assisted medical decision making. In: Computers and medicine. New York: Springer-Verlag, 1985.
De-Dombal FT. Computer-aided decision support-glittering prospects, practical problems, and Pandora’s box. Baillieres Clin Obstet Gynaecol 1990;4(4): 841-849.
Baxt WG. Application of neural networks to clinical medicine. Lancet 1995;346:1135-1138.
Baxt WG, Skora J. Prospective validation of artificial neural network trained to identify acute myocardial infarction. Lancet 1996;6(347):12-14.
McAdam WA, Brock BM, Armitage T, Davenport P, Chan M, de-Dombal FT. Twelve years’ experience of computeraided diagnosis in a district general hospital. Ann R Coll Surg Engl 1980; 72(2):140-146.
Anatol TI, Holder Y. A scoring system for use in the diagnosis of acute abdominal pain in childhood. West Indian Med J 1995;44(2):67-69.
Eberhart RC, Dobbins RW, Hutton LV. Neural network paradigm comparisons for appendicitis diagnosis. In: Proceedings of the Fourth Anual IEEE Symposium on Computer-Based Medical Systems 1991;298:304.
Somoza E, Somoza JR. A neural-network approach to predicting admission decisions in a psychiatric emergency room. Med Desis Making 1993;13:273-280.
Skabo Z, Kao PF, Mathews WB, Ravert HT, Musachio JL, Scheffel U, Dannals RF. Positron emission tomography of 5-HT reuptake sites in the human brain with C-11 McN5652 extraction of characteristic images by artificial neural network analysis. Behav Brain Res 1996;73(1-2):221-224.
Edenbrant L, Heden B, Pahlm O. Neural networks for analysis of ECG complexes. J Electrocardiol 1993;26:74.
Klopel B. Aplication of neural networks for EEG analysis considerations and first results. Neuropsychobiology 1994;29:39-46.
Doig GS et al. Modeling mortality in the intensive care unit. Comparing the performance of a back-propagation associative-learning neural network with multivariate logistic regression. In: Proceedings of the Fifth Annual Symposiumon Computers applied to Medical Care 1993;361:65.
Ebell MH. Artificial neural networks for predicting failure to survive following in-hospital cardiopulmonary resuscitation. J Fam Pract 1993;36:297-303.
De Dombal FT, Leaper DJ, Staniland JR et al. Computeraided diagnosis of acute abdominal pain. Br Med J 1972;2:9-13.
Horrocks JC, McCann AP, Staniland JR et al. Computeraided diagnosis: Description of an adaptable system and operation experience with 2,043 cases. Br Med J 1972;2:5-9.
Kazmierczak SC, Catrou PG, Van Lente F. Diagnostic accuracy of pancreatic enzymes evaluated by use of multivariate data analysis. Clin Chem 1993;39(9):1960-1965.