Comparison of the Levels of Accuracy of an Artificial Neural Network Model and a Logistic Regression Model for the Diagnosis of Acute Appendicitis

An accurate diagnosis of acute appendicitis in the early stage is often difficult, and decision support tools to improve such a diagnosis might be required. This study compared the levels of accuracy of artificial neural network models and logistic regression models for the diagnosis of acute appendicitis. Data from 169 patients presenting with acute abdomen were used for the analyses. Nine variables were used for the evaluation of the accuracy of the two models. The constructed models were validated by the “.632+ bootstrap method”. The levels of accuracy of the two models for diagnosis were compared by error rate and areas under receiver operating characteristic curves. The artificial neural network models provided more accurate results than did the logistic regression models for both indices, especially when categorical variables or normalized variables were used. The most accurate diagnosis was obtained by the artificial neural network model using normalized variables.

[1]  M. Schumacher,et al.  A Comparison of Nonparametric Error Rate Estimation Methods in Classification Problems , 2004 .

[2]  A. Sanabria,et al.  Randomized controlled trial. , 2005, World journal of surgery.

[3]  Howard Levinson,et al.  Routine versus selective abdominal computed tomography scan in the evaluation of right lower quadrant pain: a randomized controlled trial. , 2007, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[4]  Kenneth J Ottenbacher,et al.  Comparison of logistic regression and neural network analysis applied to predicting living setting after hip fracture. , 2004, Annals of epidemiology.

[5]  K Irjala,et al.  Phospholipase A2, C-reactive protein, and white blood cell count in the diagnosis of acute appendicitis. , 1994, Clinical chemistry.

[6]  E. Sabo,et al.  Delay of surgery in acute appendicitis. , 1997, American journal of surgery.

[7]  N. Tzanakis,et al.  A New Approach to Accurate Diagnosis of Acute Appendicitis , 2005, World Journal of Surgery.

[8]  H Gholam Hosseini,et al.  The comparison of different feed forward neural network architectures for ECG signal diagnosis. , 2006, Medical engineering & physics.

[9]  Anupam B Kharbanda,et al.  A Clinical Decision Rule to Identify Children at Low Risk for Appendicitis , 2005, Pediatrics.

[10]  Alfredo Alvarado,et al.  A Practical Score for the Early Diagnosis of Acute Appendicitis , 1986 .

[11]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

[12]  R. Galen,et al.  The Assessment of Laboratory Tests in the Diagnosis of Acute Appendicitis , 1984 .

[13]  R. Tibshirani,et al.  Improvements on Cross-Validation: The 632+ Bootstrap Method , 1997 .

[14]  R. Andersson,et al.  Meta‐analysis of the clinical and laboratory diagnosis of appendicitis , 2004, The British journal of surgery.

[15]  A. Gautier,et al.  C-reactive protein , 2005 .

[16]  M Juhola,et al.  Comparison of different neural network algorithms in the diagnosis of acute appendicitis. , 1996, International journal of bio-medical computing.

[17]  J L Pater,et al.  Comparing the predictive value of neural network models to logistic regression models on the risk of death for small-cell lung cancer patients. , 2006, European journal of cancer care.

[18]  C. Ohmann,et al.  Clinical benefit of a diagnostic score for appendicitis: results of a prospective interventional study. German Study Group of Acute Abdominal Pain. , 1999, Archives of surgery.

[19]  K E Applegate,et al.  When appendicitis is suspected in children. , 2001, Radiographics : a review publication of the Radiological Society of North America, Inc.

[20]  E. Arnbjörnsson,et al.  Scoring system for computer-aided diagnosis of acute appendicitis. The value of prospective versus retrospective studies. , 1985, Annales chirurgiae et gynaecologiae.

[21]  M. Zweig,et al.  Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. , 1993, Clinical chemistry.

[22]  Zixiang Xiong,et al.  Noise-injected neural networks show promise for use on small-sample expression data , 2006, BMC Bioinformatics.

[23]  Peter C Austin,et al.  Inflation of the type I error rate when a continuous confounding variable is categorized in logistic regression analyses , 2004, Statistics in medicine.

[24]  W. Sauerbrei,et al.  Dangers of using "optimal" cutpoints in the evaluation of prognostic factors. , 1994, Journal of the National Cancer Institute.

[25]  W. Baxt,et al.  A neural computational aid to the diagnosis of acute myocardial infarction. , 2002, Annals of emergency medicine.

[26]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.