Some Examples for Solving Clinical Problems Using Neural Networks
In this paper neural networks are presented for solving some pharmaceutical problems. We have predicted and prevented patients with potential risk of post-Chemotherapy Emesis and potentially intoxicated patients treated with Digoxin. Neural networks have been also used for predicting Cyclosporine A concentration and Erythropoietin concentrations. Several neural networks (multilayer perceptron for classification tasks and Elman and FIR networks for prediction) and classical methods have been used. Results show how neural networks are very suitable tools for classification and prediction tasks, outperforming the classical methods1. In a neural approach it is not strictly necessary to assume a specific relationship between variables and no previous knowledge of the problem is either necessary. These features allow the user better generalization performance than using classical methods. Several software applications have been developed in order to improve clinical outcomes and reduce costs to the Health Care System.
KeywordsNeural Network Root Mean Square Error Multilayer Perceptron Narrow Therapeutical Range Elman Network
Unable to display preview. Download preview PDF.
- 1.Jiménez, N.V, Albert, A., Soria, E., Camps, G, Serrano, A.J: Prediction of Digoxin Plasma Potentially Toxic Levels by Using a Neural Network Model, ASHP Midyear Clinical Meeting. Orlando, Florida U.S.A (2000)Google Scholar
- 2.Haykin, S: Neural Networks. Ed. Macmillan, (1994) 1–44Google Scholar
- 3.Camps, G., Soria, E., Jiménez, N.V.: Artificial Neural Networks for the Classification of Potentially Intoxicated Patients Treated with Digoxin, World Congress on Medical Physics and Biomedical Engineering, (2000)Google Scholar
- 4.Visual Basic 5. Edición Especial. Prentice-Hall. (1997).Google Scholar
- 5.Aapro, MS: Treatment of cancer therapy related emesis. Handbook of chemotherapy in clinical oncology. Jersey: Scientific Communication (1993) 488–92.Google Scholar
- 6.Catalán, J.L.: “FrProgramas de emesis y sistemas informáticos para su predicción. XX Curso de terapia intravenosa y nutrición artificial. Valencia (1998)Google Scholar
- 7.Balhman, J.: Schoter KH, Scigalla P, et al. “Morbidity and mortality in hemodialysis patiens with and without erythropoietin treatment: A controled study”. Contrib Nephrol, Vol. 76, (1984) 250–256.Google Scholar
- 9.Martín, J.D., Soria, E., Jiménez, N.V., Camps, G., Serrano, A.J., Pérez-Ruixo, J.: Nonlinear prediction of rhEPO by using Neural Networks. World Congress on Medical Physics and Biomedical Engineering, Chicago, (2000).Google Scholar
- 10.Belitsky: Neoral used in the renal transplant recipient, Transplantation Proceedings, Suppl. Review., Vol. 32,no. 30, (2000) S10–S19Google Scholar
- 12.Wan, E.A: Finite Impulse Response Neural Networks with Applications in Time Series Prediction, Master’s Thesis”. Department of Electrical Engineering. Standford University, (1993)Google Scholar