Performance of Multi-Layer Feedforward Neural Networks to Predict Liver Transplantation Outcome

Abstract

A novel multisolutional clustering and quantization (MCO) algorithm has been developed that provides a flexible way to preprocess data. It was tested whether it would impact the neural network’s performance favorably and whether the employment of the proposed algorithm would enable neural networks to handle missing data. This was assessed by comparing the performance of neural networks using a well-documented data set to predict outcome following liver transplantation. This new approach to data preprocessing leads to a statistically significant improvement in network performance when compared to simple linear scaling. The obtained results also showed that coding missing data as zeroes in combination with the MCO algorithm, leads to a significant improvement in neural network performance on a data set containing missing values in 59.4% of cases when compared to replacement of missing values with either series means or medians.

Keywords

Neural Network - Algorithms - Cluster Analysis - Missing Data - Liver Transplantation

• REFERENCES

• 1 Akay M. Noninvasive diagnosis of coronary artery disease using a neural network algorithm. Bioi Cybern 1992; 67: 361-7.
• 2 Baxt WG. Use of an artificial neural network for the diagnosis of myocardial infarction. Ann Intern Med 1991; 115: 843-8.
• 3 Tourassi GD, Floyd CE, Sostman HD, Coleman RE. Acute pulmonary embolism: artificial neural network approach for diagnosis. Radiology 1993; 189: 555-8.
• 4 Doyle HR, Dvorchik I, Mitchell SH. et al Predicting outcome after liver transplantation: A connectionist approach. Ann Surg 1994; 219: 408-15.
• 5 Kappen HJ, Neijt JP. Advanced ovarian cancer: Neural network analysis to predict treatment outcome. Ann Oncol 1993; 4 (Suppl. 04) S31-4.
• 6 Buchman TG, Kubos KL, Seidler AJ, Siegforth MJ. A comparison of statistical and connectionist models for the prediction of chronicity in a surgical intensive care unit. Crit Care Med 1994; 22: 750-62.
• 7 Jensen EW, Demant L, Sanchez R. A model for estimation of the pulmonary capillary pressure. Meth Inform Med 1994; 33: 139-42.
• 8 Edenbrandt L, Devine B, Macfarlane PW. Classification of electrocardiographic ST-T segments – human expert vs artificial neural network. Eur Heart J 1993; 14: 464-8.
• 9 Rinast E, Linder R, Weiss HD. Neural network approach for computer-assisted interpretation of ultrasound images of the gallbladder. Eur J Radial 1993; 17: 175-8.
• 10 Kosugi Y, Sase M, Kuwatani H. et al Neural network mapping for nonlinear stereotactic normalization of brain MR images. J Comput Assist Tomogr 1993; 17: 455-60.
• 11 Vertosick FT, Rehn T. Predicting behavior of an enzyme-linked immunoassay model by using commercially available neural network software. Clin Chern 1992; 39: 2478-82.
• 12 Rabow AA, Scheraga HA. Lattice neural network minimization. Application of neural network optimization for locating the global-minimum conformations of proteins. J Mol Bioi 1993; 232: 1157-68.
• 13 Uberbacher EC, Mural RJ. Locating protein-coding regions in human DNA sequences by a multiple sensor – neural network approach. Proc Natl Acad Sci USA 1991; 88: 11261-5.
• 14 Little RJA, Rubin DB. Statistical Analysis with Missing Data. New York: John Wiley & Sons; 1987
• 15 Parmanto B, Munro PW, Doyee HR. et al Neural network classifier for hepatoma detection. In: Proceedings of the World Congress on Neural Networks. 1994. San Diego, CA: 1285-1290.
• 16 Dvorchik I, Doyle HR. Improvement of backpropagation network’s learning potentials by employment of alternative clustering and quantization data algorithm. In: Proceedings of the World Congress on Neural Networks. 1994. San Diego, CA: 3: 686-90.
• 17 Hertz J, Krogh A, Palmer RG. Introduction to the Theory of Neural Computation. Redwood City: Addison-Wesley Publishing Company; 1993
• 18 Hestenes MR, Stiefel E. Methods of conjugate gradients for solving linear systems. Nat Bur Standards J Res 1952; 49: 409-36.
• 19 Lippmann RP. An introduction to computing with neural nets. IEEE ASSP Magazine 1987; 4: 4-22.
• 20 Nilsson NJ. Learning Machines: Foundations of Trainable Pattern Classifying Systems. New York: McGraw-Hill; 1965
• 21 Bailar BA, Bailar JC. Comparison of the biases of the “hot deck” imputation procedure with an “equal weights” imputation procedure. In: Madow WG, Olkin I. eds Incomplete Data in Sample Surveys, Vol. III: Symposium on Incomplete Data, Proceedings. New York: Academic Press; 1983
• 22 Bailar BA, Bailey L, Corsby C. A comparison of some adjustment and weighting procedures for survey data. In: American Statistical Association, Proceedings of the Survey Research Methods Section. 1978: 175-200.
• 23 Dempster AP, Laird NM, Rubin DB. Maximum likelihood estimation from incomplete data via the EM algorithm (with discussion). J Roy Statist Soc 1977; B39: 1-38.