Application of Artificial Neural Networks for Diagnosing Acute Appendicitis

Abstract:

The purpose of this study is to develop an appendicitis diagnosis system, by using artificial neural networks (ANNs). Acute appendicitis is one of the most common surgical emergencies of the abdomen. Various methods have been developed to diagnose appendicitis, but these methods have not shown good performance in the Middle East and Asia, or even in the West. We used the structures of ANNs with 801 patients. These various structures are a multilayer neural network structure (MLNN), a radial basis function neural network structure (RBF), and a probabilistic neural network structure (PNN). The Alvarado clinical scoring system was used for comparison with the ANNs. The accuracy of MLNN, RBF, PNN, and Alvarado was 97.84%, 99.80%, 99.41% and 72.19%, respectively. The AUC of MLNN, RBF, PNN, and Alvarado was 0.985, 0.998, 0.993, and 0.633, respectively. The performance of ANNs was significantly better than the Alvarado clinical scoring system (P<0.001). The models developed to diagnose appendicitis using ANNs showed good performance. We consider that the developed models can help junior clinical surgeons diagnose appendicitis.

• Periodical: Applied Mechanics and Materials (Volumes 479-480)
• Pages: 445-450
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.479-480.445
• Online since: December 2013
• Authors: Sung Yun Park, Sangjoon Lee, Jae Hoon Jeong, Sung Min Kim
• Keywords: Abdomen, Appendicitis, Area under the ROC Curve, Artificial Neural Network (ANN), Clinical Scoring System

References

[1] C. Chong, M. Adi, A. Thien, A. Suyoi, A. Mackie, A. Tin, S. Tripathi, N. Jaman, K. Tan, K. Kok, V. Mathew, O. Paw, H. Chua, and S. Yapp: Singapore Med J. Vol. 51 (2010), p.220.

[2] H. Lintula, H. Kokki, R. Kettunen, and M. Eskelinen: Langenbecks Arch. Surg. Vol. 394 (2009), p.999.

DOI: 10.1007/s00423-008-0425-0

[3] H. Lintula, H. Kokki, J. Pulkkinen, R. Kettunen, O. Gröhn, and M. Eskelinen: Langenbecks Arch. Surg. Vol. 395 (2010), p.495.

DOI: 10.1007/s00423-010-0627-0

[4] D. Flum, and T. Koepsell: Arch. Surg. Vol. 137 (2002), p.799.

[5] A. Alvarado: Ann. Emerg. Med. Vol. 15 (1986), p.557.

[6] E. Paulson, and C. Coursey: Am. J. Roentgenol. Vol. 193 (2009), p.1268.

[7] P. Poortman, P. N. Lohle, C. M. Schoemaker, M. A. Cuesta, H. J. Oostvogel, E. S. de Lange-de Klerk, and J. F. Hamming: Eur. J. Radiol. Vol. 74 (2010), p.67.

DOI: 10.1016/j.ejrad.2008.12.012

[8] G. M. Israel, N. Malguria, S. McCarthy, J. Copel, and J. Weinreb: J. Magn. Reson. Imaging Vol. 28 (2008), p.428.

DOI: 10.1002/jmri.21456

[9] J. Hawkins, and R. Thirlby: Adv. Surg. Vol. 43 (2009), p.13.

[10] M. Kalan, D. Talbot, W. Cunliffe, and A. Rich: Ann. R. Coll. Surg. Engl. Vol. 76 (1994), p.418.

[11] C. H. Hsieh, R. H. Lu, N. H. Lee, W. T. Chiu, M. H. Hsu, and Y. C. Li: Surgery Vol. 149 (2011), p.87.

[12] A. Konan, M. Hayran, and Y. A. Kilic: Ulus. Travma. Acil. Cerrahi. Derg. Vol. 17 (2011), p.396.

DOI: 10.5505/tjtes.2011.03780

[13] H. John, U. Neff, and M. Kelemen: World J. Surg. Vol. 17 (1993), p.243.

[14] Z. H. Zhou, Y. Jiang, Y. B. Yang, and S. F. Chen: Artif. Intell. Med. Vol. 24 (2002), p.25.

[15] F. Temurtas: Expert Syst. Appl. Vol. 36 (2009), p.944.

[16] D. Delen, G. Walker, and A. Kadam: Artif Intell Med Vol. 34 (2005), p.113.

[17] D. Wu, K. Warwick, Z. Ma, M. Gasson, J. Burgess, S. Pan, and T. Aziz: Int. J. Neural Syst. Vol. 20 (2010), p.109.

[18] D. E. Rumelhart, and J. L. McClelland, in: Learning internal representations by error propagation, edited by J.A. Feldman, P.J. Hayes, and D.E. Rumelhart Publications/MIT Press, Cambridge (1988).

[19] S. Sakai, K. Kobayashi, J. Nakamura, S. Toyabe, and K. Akazawa: Methods Inf. Med. Vol. 46 (2007), p.723.

[20] S. Prabhudesai, S. Gould, S. Rekhraj, P. Tekkis, G. Glazer, and P. Ziprin: World J. Surg. Vol. 32 (2008), p.305.

DOI: 10.1007/s00268-007-9298-6