(2015) Comparing the accuracy of neural network models and conventional tests in diagnosis of suspected acute appendicitis. Journal of Mazandaran University of Medical Sciences. pp. 58-65. ISSN 17359279 (ISSN)
Text
Comparing the accuracy of neural network models and conventional tests in diagnosis of suspected acute appendicitis.pdf Download (304kB) |
Abstract
Background and purpose: Diagnosis of acute appendicitis can be difficult due to similarity of symptoms to many abdominal diseases. Delayed diagnosis could expose the patient to serious conditions. In this study we compared the Artificial Neural Network (ANN) models and conventional laboratory tests in diagnosis of appendicitis. Materials and methods: The study population included 100 patients with suspected appendicitis. White Blood Cells (WBC), Procalcitonin (PCT), C-reactive protein (CRP) and PMN were measured as conventional diagnostic tests and ANN was applied as a combinational test. Definite diagnosis of appendicitis was made based on pathology results. For each test, Receiver Operating Characteristic (ROC) curve and sensitivity and specificity tables were used. Results: The mean age of patients was 28.01±12.68 years and 71 (71) were male. The sensitivity of ANN model was 97.59 and the sensitivities of CRP and WBC were 92.77 and 85.54, respectively. The highest accuracy in diagnosis of acute appendicitis was achieved by ANN (88). Conclusion: This study showed that combinational test using ANN could be more beneficial in diagnosis of acute appendicitis. © 2015, Mazandaran University of Medical Sciences. All rights reserved.
Item Type: | Article |
---|---|
Keywords: | Appendicitis C-reactive protein Leukocytes count Neural network model Procalcitonin C reactive protein acute appendicitis adult Article artificial neural network comparative study diagnostic accuracy diagnostic test accuracy study female human laboratory test leukocyte count major clinical study male polymorphonuclear cell receiver operating characteristic sensitivity and specificity |
Divisions: | |
Page Range: | pp. 58-65 |
Journal or Publication Title: | Journal of Mazandaran University of Medical Sciences |
Journal Index: | Scopus |
Volume: | 25 |
Number: | 128 |
ISSN: | 17359279 (ISSN) |
Depositing User: | مهندس مهدی شریفی |
URI: | http://eprints.bmsu.ac.ir/id/eprint/417 |
Actions (login required)
View Item |