Journal of Veterinary Clinics (한국임상수의학회지)

The Korean Society of Veterinary Clinics (한국임상수의학회)
권호 표지

Development an Artificial Neural Network to Predict Infectious Bronchitis Virus Infection in Laying Hen Flocks

산란계의 전염성 기관지염을 예측하기 위한 인공신경망 모형의 개발

  • Pak Son-Il (Department of Veterinary Medicine and Institute of Veterinary Science, Kangwon National University) ;
  • Kwon Hyuk-Moo (Department of Veterinary Medicine and Institute of Veterinary Science, Kangwon National University)
  • 박선일 (강원대학교 수의학과 동물의학종합연구소) ;
  • 권혁무 (강원대학교 수의학과 동물의학종합연구소)
  • Published : 2006.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

A three-layer, feed-forward artificial neural network (ANN) with sixteen input neurons, three hidden neurons, and one output neuron was developed to identify the presence of infectious bronchitis (IB) infection as early as possible in laying hen flocks. Retrospective data from flocks that enrolled IB surveillance program between May 2003 and November 2005 were used to build the ANN. Data set of 86 flocks was divided randomly into two sets: 77 cases for training set and 9 cases for testing set. Input factors were 16 epidemiological findings including characteristics of the layer house, management practice, flock size, and the output was either presence or absence of IB. ANN was trained using training set with a back-propagation algorithm and test set was used to determine the network's capability to predict outcomes that it has never seen. Diagnostic performance of the trained network was evaluated by constructing receiver operating characteristic (ROC) curve with the area under the curve (AUC), which were also used to determine the best positivity criterion for the model. Several different ANNs with different structures were created. The best-fitted trained network, IBV_D1, was able to predict IB in 73 cases out of 77 (diagnostic accuracy 94.8%) in the training set. Sensitivity and specificity of the trained neural network was 95.5% (42/44, 95% CI, 84.5-99.4) and 93.9% (31/33, 95% CI, 79.8-99.3), respectively. For testing set, AVC of the ROC curve for the IBV_D1 network was 0.948 (SE=0.086, 95% CI 0.592-0.961) in recognizing IB infection status accurately. At a criterion of 0.7149, the diagnostic accuracy was the highest with a 88.9% with the highest sensitivity of 100%. With this value of sensitivity and specificity together with assumed 44% of IB prevalence, IBV_D1 network showed a PPV of 80% and an NPV of 100%. Based on these findings, the authors conclude that neural network can be successfully applied to the development of a screening model for identifying IB infection in laying hen flocks.

2003년 5월부터 2005년 11월까지 산란계의 전염성기관지염(IB) 예찰 프로그램에 등록한 농장에 대한 역학조사에서 얻은 자료에 근거하여 IB 감염을 확인할 수 있는 모형을 구축하기 위하여 16개의 입력 뉴런, 3 개의 은닉 뉴런, 1개의 출력 뉴런으로 구성된 3층 인공신경망 모형을 개발하였다. 총 86개의 계군 중 77개는 훈련자료에 할당하고 나머지 9개는 검정자료로 무작위로 할당하여 back-propagation algorithm으로 신경망 훈련을 수행하였다. 입력 뉴런은 산란계군의 특성, 사양관리, 계군의 크기 등 16개의 역학조사 항목을 사용하였으며 출력 뉴런은 IB 감염의 유무로 투입하였다. 훈련된 신경망을 검정자료에 적용하여 민감도와 특이도를 산출하였으며 진단의 정확도는 receiver operating characteristic (ROC) 곡선을 사용하여 곡선 밑의 면적(AUC)을 계산하여 평가하였다. 입력 뉴런의 특성과 훈련모수를 변경하면서 다양한 신경망을 구성하였으며 최적의 신경망으로 확인된 IBV_D1 신경망의 경우 훈련자료에 대하여 77건 중 73건을 올바르게 판단하여 94.8%의 정확도를 보였다. 민감도와 특이도는 각각 95.5% (42/44, 95% CI, 84.5-99.4)와 93.9% (31/33, 95% CI, 79.8-99.3)로 나타났다. 훈련된 신경망을 검정자료에 적용하여 ROC 곡선을 작성한 결과 AUC는 전체의 94.8% (SE=0.086, 95% CI 0.592-0.961)를 차지하는 우수한 모형으로 나타났다. ROC 곡선에서 기준을 0.7149 이상으로 판단할 때 진단의 정확도가 88.9%로 가장 높았으며 100%의 민감도를 달성하였다. 이러한 민감도와 특이도에서 44%의 IB 유병률을 가정할 때 IBV_D1 모형은 80%의 양성예측도와 100%의 음성예측도를 보였다. 이러한 소견에 근거할 때 본 연구에서 구축한 신경망 모형은 산란계군에서 IB의 존재를 확인하기 위한 목적에 성공적으로 응용될 수 있을 것으로 판단되었다.

Keywords

References

  1. Astion ML, Wilding P. The application of backpropagation neural networks to problems in pathology and laboratory medicine. Arch Pathol Lab Med 1992; 116: 995-1001
  2. Baxt WG Improving the accuracy of an artificial neural network using multiple differently trained networks. Neural Comp 1992; 4: 772-780 https://doi.org/10.1162/neco.1992.4.5.772
  3. Beck JR, Shultz EK. The use of relative operating characteristic (ROC) curves in test performance evaluation. Arch Pathol Lab Med 1986; 110: 13-20
  4. Cicchetti DV. Neural networks and diagnosis in the clinical laboratory: state of the art. Clin Chem 1992; 38: 9-10
  5. Cunningham CH. Avian infectious bronchitis: characteristics of the virus and antigenic types. Am J Vet Res 1975; 36: 522-523
  6. Dhinakar Raj G, Jones RC. Infectious bronchitis virus: immunopathogenesis of infection in the chicken. Avian Pathol 1997; 26: 677-706 https://doi.org/10.1080/03079459708419246
  7. Eidson CS, Page RK, Fletcher OJ, Kleven SH. Vaccination of broiler breeders with teno-synovitis vaccine. Poult Sci 1979; 58: 1490-1497 https://doi.org/10.3382/ps.0581490
  8. Feinstein AR. Multiple logistic regression. In: Feinstein AR (ed). Multivariable analysis. 1st ed. New Haven: Yale University Press, 1996: 297-300
  9. Furlong JW, Dupuy ME, Heinsimer JA. Neural network analysis of serial cardiac enzyme data. Am J Clin Pathol 1991; 96: 134-141 https://doi.org/10.1093/ajcp/96.1.134
  10. Hanley JA, McNeil BJ. The meaning and use of the area under the receiver operating characteristic (ROC) curve. Radiology 1982; 143: 29-36 https://doi.org/10.1148/radiology.143.1.7063747
  11. Heald CW, Kim T, Sischo WM, Cooper JB, Wolfgang DR. A computerized mastitis decision aid using farm-based records: an artificial neural network approach. J Dairy Sci 2000; 83: 711-720 https://doi.org/10.3168/jds.S0022-0302(00)74933-2
  12. Kim JH, Song CS, Mo IP, Kim SH, Sung HW, Yoon HS. An outbreak of nephropathogenic infectious bronchitis in commercial pullets. Res Reports Rural Develop Admin 1992; 34: 28-33
  13. Kusters JG, Niesters HGM, Bleumink-Pyuym NMC, Davelaar FG, Horzinek MC, van der Zeijst BAM. Molecular epidemiology of infectious bronchitis virus in the Netherlands. J Gen Viral 1987; 68: 343-352 https://doi.org/10.1099/0022-1317-68-2-343
  14. Lawrence J. Introduction to neural networks: design, theory, and applications. 6th ed, Luedeking S (Ed). Nevada City, CA, California Scientific Software Press, 1994: 154-155
  15. Meistrell ML. Evaluation of neural network performance by receiver operating characteristic (ROC) analysis: examples from the biotechnology domain. Comput Methods Programs Biomed 1990: 32; 73-80 https://doi.org/10.1016/0169-2607(90)90087-P
  16. Pak SI, Kwon HM, Yoon HJ, Song CS, Son YH, Mo IP, Song CY. Risk factors for infectious bronchitis virus (IBV) infection in laying flocks in three provinces of Korea: preliminary results. Korean J Vet Res 2005; 45: 405-410
  17. Parsons D, Ellis MM, Cavanagh D, Cook JKA. Characterization of an infectious bronchitis virus isolated from vaccinated broiler breeder flocks. Vet Rec 1992; 131: 408-411 https://doi.org/10.1136/vr.131.18.408
  18. Roush WB, Kirby YK, Cravener TL, Wideman RF. Artificial neural network prediction of ascites in broilers. Poult Sci 1996; 75: 1479-1487 https://doi.org/10.3382/ps.0751479
  19. Schwartz MH, Ward RE, MacWilliam C, Verner JJ. Using neural networks to identify patients unlikely to achieve a reduction in bodily pain after total hip replacement surgery. Med Care 1997; 35; 1020-1030 https://doi.org/10.1097/00005650-199710000-00004
  20. Shang JS, Lin YE, Goetz AM. Diagnosis of MRSA with neural networks and logistic regression approach. Health Care Manag Sci 2000; 3: 287-297 https://doi.org/10.1023/A:1019018129822
  21. Song CS, Lee YJ, Kim JH, Sung CW, Lee Y, Izumiya T, Miyazawa T, Jang HK, Mikami T. Epidemiological classification of infectious bronchitis virus isolated in Korea between 1986 and 1997. Avian Pathol 1998; 27: 409-416 https://doi.org/10.1080/03079459808419360
  22. Swets JA. Measuring the accuracy of diagnostic systems. Science 1988; 240: 1285-1293 https://doi.org/10.1126/science.3287615
  23. Thayer SG, Eidson CS, Page RK, Kleven SH. Multivalent inactivated virus oil emulsion vaccines in broiler breeder chickens. I. Newcastle disease virus and infectious bursal disease virus bivalent vaccines. Poult Sci 1983; 62: 1978-1983 https://doi.org/10.3382/ps.0621978
  24. Tourassi GD, Markey MK, Lo JY, Floyd CE Jr. A neural network approach to breast cancer diagnosis as a constraint satisfaction problem. Med Phys 2001; 28: 804-811 https://doi.org/10.1118/1.1367861
  25. Yu L, Jiang Y, Low S, Wang Z, Nam SJ, Liu W, Kwangac J. Characterization of three infectious bronchitis virus isolates from China associated with proventriculus in vaccinated chickens. Avian Dis 2001; 45: 416-424 https://doi.org/10.2307/1592981