Comparison of Logistic Regression and Artificial Neural Network in Low Back Pain Prediction: Second National Health Survey

Background: The purpose of this investigation was to compare empirically predictive ability of an artificial neural network with a logistic regression in prediction of low back pain. Methods: Data from the second national health survey were considered in this investigation. This data includes the information of low back pain and its associated risk factors among Iranian people aged 15 years and older. Artificial neural network and logistic regression models were developed using a set of 17294 data and they were validated in a test set of 17295 data. Hosmer and Lemeshow recommendation for model selection was used in fitting the logistic regression. A three-layer perceptron with 9 inputs, 3 hidden and 1 output neurons was employed. The efficiency of two models was compared by receiver operating characteristic analysis, root mean square and -2 Loglikelihood criteria. Results: The area under the ROC curve (SE), root mean square and -2Loglikelihood of the logistic regression was 0.752 (0.004), 0.3832 and 14769.2, respectively. The area under the ROC curve (SE), root mean square and -2Loglikelihood of the artificial neural network was 0.754 (0.004), 0.3770 and 14757.6, respectively. Conclusions: Based on these three criteria, artificial neural network would give better performance than logistic regression. Although, the difference is statistically significant, it does not seem to be clinically significant.

[1]  R. Hinman,et al.  Specific treatment of problems of the spine (STOPS): design of a randomised controlled trial comparing specific physiotherapy versus advice for people with subacute low back disorders , 2011, BMC musculoskeletal disorders.

[2]  E. M. Hagen.  Light mobilization treatment of subacute, non-spesific low back pain , 2006 .

[3]  Michael D. Clemes,et al.  Consumer choice prediction : artificial neural networks versus logistic models , 2005 .

[4]  R. Dybowski,et al.  Comprar Clinical Applications of Artificial Neural Networks | Richard Dybowski | 9780521001335 | Cambridge University Press , 2007 .

[5]  S. Anitha,et al.  Application of a radial basis function neural network for diagnosis of diabetes mellitus , 2006 .

[6]  Kenji Suzuki,et al.  Artificial Neural Networks - Methodological Advances and Biomedical Applications , 2011 .

[7]  Muhammad Mukhlisin,et al.  Performance of artificial neural network and regression techniques for rainfall-runoff prediction , 2011 .

[8]  Michael J Gibney,et al.  Analysis of meal patterns with the use of supervised data mining techniques--artificial neural networks and decision trees. , 2008, The American journal of clinical nutrition.

[9]  D. Hosmer,et al.  Applied Logistic Regression , 1991 .

[10]  Monique Frize,et al.  Medical Outcome Prediction for Intensive Care Unit Patients , 2010, Int. J. Comput. Model. Algorithms Medicine.

[11]  Glucosamine and the ongoing enigma of chronic low back pain. , 2010, JAMA.

[12]  K. Mohammad,et al.  Mental disorder assessed by General Health Questionnaire and back pain among postmenopausal Iranian women. , 2008, Pakistan journal of biological sciences : PJBS.

[13]  C. Sehgal,et al.  Comparative analysis of logistic regression and artificial neural network for computer-aided diagnosis of breast masses. , 2005, Academic radiology.

[14]  Mohammad Ghodsi,et al.  Comparison of artificial neural network and logistic regression models for prediction of mortality in head trauma based on initial clinical data , 2005, BMC Medical Informatics Decis. Mak..

[15]  Jeremy Wyatt,et al.  Clinical applications of artificial neural networks: Artificial neural networks: practical considerations for clinical application , 2001 .

[16]  Diego A. Alvarez,et al.  Comparison between logistic regression and neural networks to predict death in patients with suspected sepsis in the emergency room , 2005, Critical care.

[17]  Richard Dybowski,et al.  Clinical applications of artificial neural networks: Theory , 2001 .

[18]  Caro Lucas,et al.  Predicting the type of pregnancy using artificial neural networks and multinomial logistic regression: a comparison study , 2005, Neural Computing & Applications.

[19]  Ugur Bilge,et al.  Artificial neural network, genetic algorithm, and logistic regression applications for predicting renal colic in emergency settings , 2009, International Journal of Emergency Medicine.

[20]  J. Wilbur,et al.  American Family Physician , 2008 .

[21]  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.

[22]  K. Mohammad,et al.  Sociodemographic and smoking associated with obesity in adult women in Iran: results from the National Health Survey. , 2008, Journal of public health.

[23]  N. Foster.  Barriers and progress in the treatment of low back pain , 2011, BMC medicine.