On the misuses of artificial neural networks for prognostic and diagnostic classification in oncology

Statistics in Medicine

Volumn 19, Issue 4, 2000, Pages 541-561

  Schwarzer, Guido ^a   Vach, Werner ^b   Schumacher, Martin ^a  

^a UNIVERSITY OF FREIBURG   (Germany)

^b UNIVERSITY OF SOUTHERN DENMARK   (Denmark)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL NEURAL NETWORK; BREAST CANCER; CANCER DIAGNOSIS; CANCER SURVIVAL; CONFERENCE PAPER; HUMAN; MAJOR CLINICAL STUDY; ONCOLOGY; OVARY CANCER; PROBABILITY; PROGNOSIS; RECEIVER OPERATING CHARACTERISTIC; REGRESSION ANALYSIS; STATISTICAL MODEL; STATISTICAL PARAMETERS; UTERINE CERVIX CANCER;

DECISION SUPPORT TECHNIQUES; DIAGNOSTIC TECHNIQUES AND PROCEDURES; HUMANS; LOGISTIC MODELS; MODELS, STATISTICAL; NEOPLASMS; NEURAL NETWORKS (COMPUTER); PROBABILITY; PROGNOSIS; SURVIVAL ANALYSIS;

EID: 0034728368     PISSN: 02776715     EISSN: None     Source Type: Journal    
DOI: 10.1002/(SICI)1097-0258(20000229)19:4<541::AID-SIM355>3.0.CO;2-V     Document Type: Conference Paper

References (102)

1. Baxt WG. Application of artifical neural networks to clinical medicine. Lancet 1995; 346:1135-1138.
2. Cross SS, Harrison RF, Kennedy RL. Introduction to neural networks. Lancet 1995; 346:1075-1079.
3. Dybowski R, Gant V. Artificial neural networks in pathology and medical laboratories. Lancet 1995; 346:1203-1207.
4. Wyatt J. Nervous about artificial neural networks? Lancet 1995; 346:1175-1177.
5. Penny W, Frost D. Neural networks in clinical medicine. Medical Decision Making 1996; 16:386-398.
6. Cheng B, Titterington DM. Neural networks: a review from a statistical perspective (with discussion). Statistical Science 1994; 9:2-54.
7. Ripley BD. Statistical aspects of neural networks. In Networks and Chaos - Statistical and Probabilistic Aspects, Barndorff-Nielsen OE, Jensen JL (eds). Chapman and Hall: London, 1993.
8. Schumacher M, Roßner, R, Vach W. Neural networks and logistic regression: Part I. Computational Statistics and Data Analysis 1996; 21:661-682.
9. Stern HS. Neural networks in applied statistics (with discussion). Technometrics 1996; 38:205-220.
10. Warner B, Misra M. Understanding neural networks at statistical tools. American Statistician 1996; 50:284-293.
11. Cox DR, Snell EJ. Analysis of Binary Data, 2nd edn. Chapman and Hall: London, 1992.
12. Hastie TJ, Tibshirani RJ. Generalized Additive Models. Chapman and Hall: London, 1990.
13. Royston P, Altman DG. Regression using fractional polynomials of continuous covariates: parsimonious parametric modelling (with discussion). Applied Statistics 1994; 43:429-467.
14. Bridle JS. Probabilistic interpretation of feedforward classification network outputs with relationships to statistical pattern recognition. In Neuro-Computing: Algorithms, Architectures and Applications, Fugleman SF, Hérault J (eds), Springer-Verlag: New York, 1990.
15. Bridle JS. Training stochastic model recognition algorithms as networks can leads to maximum mutual information estimation of parameters. In Advances in Neural Information Processing Systems 2, Touretzky DS (ed.), Morgan Kaufmann: San Mateo, CA, 1990.
16. Engel J. Polytomous logistic regression. Statistica Neerlandica 1988; 42:233-252.
17. McCullagh P, Nelder JA. Generalized Linear Models, 2nd edn. Chapman and Hall: London, 1989.
18. Kullback S, Leibler RA. On information and sufficiency. Annals of Mathematical Statistics 1995; 22:79-86.
19. Barron AR, Barron RL. Statistical learning networks: a unifying view. In Computing Science and Statistics: Proceedings 20th Symposium Interface, Wegman E (ed.) American Statistical Association: Washington, 1988.
20. Hinton GE. Connectionist learning procedures. Artificial Intelligence 1989; 40:185-234.
21. Mood AM, Graybill FA, Boes DC. Introduction to the Theory of Statistics, 3rd edn. McGraw-Hill: Singapore, 1974.
22. Ripley BD. Pattern Recognition and Neural Networks. University Press: Cambridge, 1996.
23. Sarle WS. Neural networks and statistical models. In Proceedings of the 19th Annual SAS Users Group International Conference, 1994.
24. Cybenko G. Approximation by superpositions of a sigmoidal function. Mathematics of Controls, Signals, and Systems 1989; 2:303-314.
25. Funahashi K. On the approximate realization of continuous mappings by neural networks. Neural Networks 1989; 2:183-192.
26. Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators Neural Networks 1989; 2:359-366.
27. Finney DJ. The estimation from individual records of the relationship between dose and quantal response. Biometrika 1947; 34:320-334.
28. Fahrmeir L, Tutz G. Multivariate Statistical Modelling Based on Generalized Linear Models. Springer-Verlag: New York, 1994.
29. Morgenthaler S. Least-absolute-deviations fits for generalized linear models. Biometrika 1992; 79:747-754.
30. Pregibon D. Resistant fits for some commonly used logistic models with medical applications. Biometrics 1982; 38:485-498.
31. SAS-Institute Inc. SAS/STAT User's Guide, Version 6, 4th edn. SAS-Institute Inc: Cary NC, 1990.
32. Zell A, Mamier G, Vogt M, Mache N, Hübner R, Döring S, Herrmann KU, Soyez T, Schmalzl M, Sommer T, Hatzigeorgiou A, Posselt D, Schreiner T, Kett B, Clemente G, Wieland J. Stuttgart Neural Network Simulator, User Manual, Version 4.1, Report no 6/95. Institute for Parallel and Distributed High Performance Systems, 1995.
33. Burke HB. Artificial neural networks for cancer research: outcome prediction. Seminars in Surgical Oncology 1994; 10:73-79.
34. De Laurentiis M, Ravdin PM. Survival analysis of censored data: neural network analysis detection of complex interactions between variables. Breast Cancer Research and Treatment 1994; 32:113-118.
35. Faraggi D, Simon R. A neural network model for survival data. Statistics in Medicine 1995; 14:73-82.
36. Kappen HJ, Neijt JP. Neural network analysis to predict treatment outcome. Annals of Oncology 1993; 4:Supplement S31-34.
37. Liestøl K, Andersen PK, Andersen U. Survival analysis and neural nets. Statistics in Medicine 1994; 13: 1189-1200.
38. Ravdin PM, Clark GM. A practical application of neural network analysis for predicting outcome of individual breast cancer patients. Breast Cancer Research and Treatement 1992; 22:285-293.
39. Ravdin PM, Clark GM, Hilsenbeck SG, Owens MA, Vendely P, Pandian MR, McGuire WL. A demonstration that breast cancer recurrence can be predicted by neural network analysis. Breast Cancer Research and Treatment 1992; 21:47-53.
40. Cox DR. Regression models and life tables (with discussion). Journal of the Royal Statistical Society, Series B 1972; 34:187-220.
41. Doksum KA, Gasko M. On a correspondence between models in binary regression analysis and in survival analysis. International Statistical Review 1990; 58:243-252.
42. Prentice RL, Gloeckler LA. Regression analysis of grouped survival data with application to breast cancer data. Biometrics 1978; 34:57-67.
43. Kalbfleisch JD, Prentice RL. The Statistical Analysis of Failure Time Data. Wiley: New York, 1980
44. Andersen PK, Borgan Ø, Gill RD, Keiding N. Statistical Models Based on Counting Processes. Springer-Verlag: New York, 1993.
45. McGuire WL, Tandon AK, Allred DC, Chamness GC, Ravdin PM, Clark GM. Treatment decisions in axillary node-negative breast cancer patients. Monographs - National Cancer Institute 1992; 11:173-180.
46. Van Houwelingen JC, ten Bokkel Huinink WW, van der Burg ME, van Oosterom AT. Neijt JP. Predictability of the survival of patients with advanced ovarian cancer. Journal of Clinical Oncology 1989; 7:769-773.
47. Biganzoli E, Boracchi P, Mariani L, Marubini E. Feed forward neural networks for the analysis of censored survival data: a partial logistic regression approach. Statistics in Medicine 1998; 17:1169-1186.
48. Andrews DF, Herzberg AM. Data - a Collection of Problems from manv Fields for the Student and Research Worker. Springer-Verlag: New York, 1985.
49. Akaike H. Fitting autoregressive models for prediction. Annals of the Institute of Statistical Mathematics 1969; 21:243-247.
50. Murata N, Yoshizawa S, Amari SI. Network information criterion - determining the number of hidden units for artificial neural network models. IEEE Transactions on Neural Networks, 1994; 5:865-872.
51. De Leo JM, Campbell G. Receiver operating characteristic (ROC) methodology in artificial neural networks with biomedical applications. In Proceedings of the World Congress on Neural Networks, 1995.
52. Livingstone DJ, Manallack DT. Statistics using neural networks: chance effects. Journal of Medicinal Chemistry 1993; 36:1295-1297.
53. Dawson AE, Austin RE, Weinberg DS. Nuclear grading of breast carcinoma by image analysis classification by multivariate and neural network analysis. American Journal of Clinical Pathology 1991; 95:Supplement S29-37.
54. Maclin PS, Dempsey J, Brooks J, Rand J. Using neural networks to diagnose cancer. Journal of Medical Systems 1991; 15:11-19.
55. Ostrem JS, Valdes AD, Edmonds PD. Application of neural nets to ultrasound tissue characterization. Ultrasonic Imaging 1991; 13:298-299.
56. Piraino DW, Amartur SC, Richmond BJ, Schils JP, Thome JM, Belhobek GH, Schlucter MD. Application of an artifical neural network in radiographic diagnosis. Journal of Digital Imaging 1991; 4:226-232.
57. Astion ML, Wilding P. Application of neural networks to the interpretation of laboratory data in cancer diagnosis. Clinical Chemistry 1992; 38:34-38.
58. Cicchetti DV. Neural networks and diagnosis in the clinical laboratory: state of the art. Clinical Chemistry 1991; 38:9-10.
59. Goldberg V, Manduca A, Ewert DL, Gisvold JJ, Greenleaf JF. Improvement in specificity of ultrasonography for diagnosis of breast tumors by means of artificial intelligence. Medical Physics 1992; 19:1475-1481.
60. Nafe R, Chortiz H. Introduction of a neuronal network as a tool for diagnostic analysis and classification based on experimental pathologic data. Experimental and Toxicologic Pathology 1992; 44:17-24.
61. O'Leary TJ, Mikel UV, Becker RL. Computer-assisted image interpretation: use of a neural network to differentiate tubular carcinoma from sclerosing adenosis. Modern Pathology 1992; 5:402-405.
62. Schweiger CR, Soeregi G, Spitzauer S, Maenner G, Pohl AL. Evaluation of laboratory data by conventional statistics and by three types of neural networks. Clinical Chemistry 1993; 39:1966-1971.
63. Becker RL. Computer-assisted image classification: use of neural networks in anatomic pathology. Cancer Letters 1994; 77:111-117.
64. Bugliosi R, Tribalto M, Avvisati G, Boccadoro M, De Martinis C, Friera R, Mandelli F, Pileri A, Papa G. Classification of patients affected by multiple myeloma using a neural network software. European Journal of Haematobgy 1994; 52:182-183.
65. Burke HB. Increasing the power of surrogate endpoint biomarkers: the aggregation of predictive factors. Journal of Cellular Biochemistry 1994; 19 Supplement 278-282.
66. Clark GM, Hilsenbeck SG, Ravdin PM, De Laurentiis M, Osborne CK. Prognostic factors: rationale and methods of analysis and integration. Breast Cancer Research and Treatement 1994; 32:105-112.
67. Ercal F, Chawla A, Stoecker WV, Lee H, Moss RH. Neural network diagnosis of malignant melanoma from color images. IEEE Transations on Biomedical Engineering 1994; 41:837-845.
68. Erler BS, Hsu L, Truong HM, Petrovic LM, Kim SS, Huh MH, Ferrell LD, Thung SN, Geller SA, Marchevsky AM. Image analysis and diagnostic classification of hepatocellular carcinoma using neural networks and multivariate discriminant functions. Laboratory Investigation 1994; 71:446-451.
69. Floyd Jr CE, JYL, Yun AJ, Sullivan DC, Kornguth PJ. Prediction of breast cancer malignancy using an artificial neural network. Cancer 1994; 74:2944-2948.
70. Giger ML, Vyborny CJ, Schmidt RA. Computerized characterization of mammorgraphic masses: analysis of spiculation. Cancer Letters 1994; 77:201-211.
71. Kolles H, von Wangenheim A, Niedermayer I, Vince GH, Feiden W. Computer assisted grading of astrocytoma. Verhandlungen der Deutschen Gesellschaft für Pathologie 1994; 78:427-431.
72. Maclin PS, Dempsey J. How to improve a neural network for early detection of hepatic cancer. Cancer Letters 1994; 77:95-101.
73. Reinus WR, Wilson AJ, Kaiman B, Kwasny S. Diagnosis of focal bone lesions using neural networks. Investigative Radiology 1994; 29:606-611.
74. Rogers SK, Ruck DW, Kabrisky M. Artificial neural networks for early detection and diagnosis of cancer. Cancer Letters 1994; 77:79-83.
75. Snow PB, Smith DS, Catalona WJ. Artificial neural networks in the diagnosis and prognosis of prostate cancer: a pilot study. Journal of Urology 1994; 152:1923-1926.
76. Wilding P, Morgan MA, Grygotis AE, Shoffner MA, Rosato EF. Application of backpropagation neural networks to diagnosis of breast and ovarian cancer. Cancer Letters 1994; 77:145-153.
77. Wu YC, Doi K, Giger ML, Metz CE, Zhang W. Reduction of false positives in computerized detection of lung nodules in chest radiographs using artificial neural networks, discriminant analysis, and a rule-based scheme. Journal of Digital Imaging 1994; 7:196-207.
78. Attikiouzel Y, de Silva CJ. Applications of neural networks in medicine. Australasian Physical & Engineering Sciences in Medicine 1995; 18:158-164.
79. Baker JA, Kornguth PJ, Lo JY, Williford ME, Floyd CE. Breast cancer: prediction with artificial neural network based on bi-rads standardized lexicon. Radiology 1995; 196:817-822.
80. Christy PS, Tervonen O, Scheithauer BW, Forbes GS. Use of a neural network and a multiple regression model to predict histologic grade of astrocytoma from mri appearances. Neuroradiology 1995; 37:89-93.
81. Doyle HR, Parmanto B, Munro PW, Marino IR, Aldrighetti L, Doria C, McMichael J, Fung JJ. Building clinical classifiers using incomplete observations - a neural network ensemble for hepatoma detection in patients with cirrhosis. Methods of Information in Medicine 1995; 34:253-258.
82. Fogel DB, Wasson 3rd EC, Boughton EM. Evolving neural networks for detecting breast cancer. Cancer Letters 1995; 96:49-53.
83. Gurney JW, Swensen ST. Solitary pulmonary nodules: determining the likelihood of malignancy with neural network analysis. Radiology 1995: 196: 823-829.
84. Hamamoto I, Okada S, Hashimoto T, Wakabayashi H, Maeba T, Maeta H. Prediction of the early prognosis of the hepatectomized patient with hepatocellular carcinoma with a neural network. Computers in Biology and Medicine 1995; 25:49-59.
85. Kolles H, von Wangenheim A, Vince GH, Niedermayer I, Feiden W. Automated grading of astrocytomas based on histomorphometric analysis of Ki-67 and Feulgen stained paraffin sections, classification results of neuronal networks and discriminant analysis. Annals Cellular Pathology 1995; 8:101-116.
86. Moul JW, Snow PB, Fernandez EB, Maher PD, Sesterhenn IA. Neural network analysis of quantitative histological factors to predict pathological stage in clinical stage i nonseminomatous testicular cancer. Journal of Urology 1995; 153:1674-1677.
87. Niederberger CS. Commentary on the use of neural networks in clinical urology. Journal of Urology 1995; 153:1362.
88. Simpson HW, McArdle C, Pauson AW, Hume P, Turkes A, Griffiths K. A non-invasive test for the pre-cancerous breast. European Journal of Cancer 1995; 31 A: 1768-1772.
89. Strotzer M, Krös P, Held P, Feuerbach S. Die Treffsicherheit künstlicher neuronaler Netze in der radiologischen Differentialdiagnose solitärer Knochenläsionen. Fortschritte auf dem Gebiete der Röntgenstrahlen und der Neuen Büdgebenden Verfahren 1995; 163:245-249.
90. Truong H, Morimoto R, Walts AE, Erler B, Marchevsky A. Neural networks as an aid in the diagnosis of lymphocyte-rich effusions. Analytical and Quantitative Cytology and Histology 1995; 17:48-54.
91. Hand DJ. Discrimination and Classification. Wiley: New York, 1981.
92. Breiman L, Friedman JH. Olshen RA, Stone CJ. Classification and Regression Trees. Wadsworth and Brooks: Monterey, California, 1984.
93. Vach W, Roßner R, Schumacher M. Neural networks and logistic regression: Part II. Computational Statistics and Data Analysis 1996; 21:683-701.
94. Hecht-Nielsen R. Neurocomputing. Addison-Wesley: New York, 1990.
95. Bottaci L, Drew PJ, Hartley JE, Hadfield MB, Farouk R, Lee PWR, Macintyre IMC, Duthie GS, Monson JRT. Artificial neural networks applied to outcome prediction for colorectal cancer patients in separate institutions. Lancet 1997; 350:469-472.
96. Burke HB, Goodman PH, Rosen DB, Henson DE, Weinstein JN, Harrell FE, Marks JR, Winchester DP, Bostwick DG. Artificial neural networks improve the accuracy of cancer survival prediction. Cancer 1997; 79:857-862.
97. Lachenbruch PA. Some misuses of discriminant analysis. Methods of Information in Medicine 1977; 16:255-258.
98. Ennis M, Hinton G, Naylor D, Revow M, Tibshirani R. A comparison of statistical learning methods on the GUSTO database. Statistics in Medicine 1998; 17:2501-2508.
99. Lee KL, Woodlief LH, Topol EJ, Weaver WD, Betriu A, Col J, Simoons M, Aylward P, Van de Werf F, Califf RM. Predictors of 30-day mortality in the era of reperfusion for acute myocardial infarction, results from an international trial of 41021 patients. Circulation 1995; 91:1659-1668.
100. GUSTO-1 Investigators. An international randomized trial comparing four thrombolytic strategies for acute myocardial infarction. New England Journal of Medicine 1993; 329:673-682.
101. Tu JV. Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. Journal of Clinical Epidemiology, 1996; 49:1225-1231.
102. Tu JV, Weinstein MC, McNeill BJ, Naylor CD and the Steering Committee of the Cardiac Care Network of Ontario. Predicting mortality after coronary artery bypass surgery: what do artifical neural networks learn? Medical Decision Making 1998; 18:229-235.