Predictive Models for Pre-Operative Diagnosis of Rotator Cuff Tear: A Comparison Study of Two Methods between Logistic Regression and Artificial Neural Network

Abstract:

Rotator cuff tears are the most common disorder of the shoulders.agnetic resonance Image (MRI) is the diagnostic gold standard of rotator cuff tears. However, there are some dilemmas in the rotator cuff tears treatment. Clinically, surgical results of rotator cuff tears are sometimes different from MRI results of rotator cuff tears. The main purpose of this study is to build up predicative models for pre-operative diagnosis of rotator cuff tears There are two models of this study are proposed: logistic regression model and artificial neural network model. Patients are divided into two sets: Set1 is patients with full thickness rotators cuff tears. Set 2 is patients with partial thickness rotators cuff tears. The charts of 158 patients are completely reviewed and the collected data were analyzed. The results showed that the predictive accuracy of artificial neural networks model is higher than the predictive accuracy of logistic model. The application of this study can assist doctors to increase the accuracy rate of pre-operative diagnosis and to decrease the legal problems.

• Periodical: Applied Mechanics and Materials (Volume 595)
• Pages: 263-268
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.595.263
• Online since: July 2014
• Authors: Chen Chiang Lin, Hsin Hui Chan, Chen Yuan Huang, Nang Shu Yang*
• Keywords: Artificial Neural Network (ANN), Logistic Regression, Predictive Mode, Rotator Cuff Tear

References

[1] Norwood LA. Barrack R. Jacobson KE. Clinical presentation of complete tears of the rotator cuff. J Bone Joint Surg [Am] Vol. 71-A (1989), pp.499-505.

DOI: 10.2106/00004623-198971040-00004

[2] Murrell GA, Walton JR . Diagnosis of rotator cuff tears. Lancet Vol 357 ( 2001), pp.769-70.

DOI: 10.1016/s0140-6736(00)04161-1

[3] Beaudreuil J. et al., Contribution of clinical examinations to the diagnosis of rotator cuff disease: A systematic literature review. Joint Bone Spine. Vol 76(1) (2009), pp.15-9.

DOI: 10.1016/j.jbspin.2009.05.010

[4] Evancho AM, et al., MR image diagnosis of rotator cuff tears. AJR AmJ Roentgenol. Vol 150(4) (1988) pp.751-4.

[5] Smith TO, et al., The diagnostic accuracy of MRI for the detection of partial- and full-thickness rotator cuff tears in adults. Magnetic Resonance Imaging. Vol 30 (2012), pp.336-346.

DOI: 10.1016/j.mri.2011.12.008

[6] Han J, Kamber M, Pei J. Data Mining, Concepts and Techniques ", Elsevier, 3rd Edition, (2012).

[7] Baxt WG. Use of an artificial neural network for data analysis in clinical decision-making: the diagnosis of acute coronary occlusion. Neural Computation. Vol 2(4) (1990), pp.480-9.

DOI: 10.1162/neco.1990.2.4.480

[8] Baxt WG. Use of an artificial neural network for the diagnosis of myocardial infarction. Annals of Internal Medicine . Vol 115(11) (1991), pp.843-8.

DOI: 10.7326/0003-4819-115-11-843

[9] Lin CC, Ou YK, Chen SH, Liu YC, Lin J. Comparison of artificial neural network and logistic regression models for predicting mortality in elderly patients with hip fracture. Injury, Int. J. Care Injured. Vol 41 (2010), pp.869-73.

DOI: 10.1016/j.injury.2010.04.023

[10] Bagley SC. White H. Golomb BA. Logistic regression in the medical literature: Standards for use and reporting, with particular attention to one medical domain. Journal of Clinical Epidemiology. Vol 54 (2001), pp.979-85.

DOI: 10.1016/s0895-4356(01)00372-9

[11] Steve Lawrence and C. Lee Giles. Overfitting and Neural Networks: Conjugate Gradient and Backpropagation, International Joint Conference on Neural Networks, Como, Italy, July 24–27, IEEE Computer Society, Los Alamitos, CA (2000), p.114–119.

DOI: 10.1109/ijcnn.2000.857823