類分子神經系統在新生兒之全靜脈營養的應用

A Study on the Total Parenteral Nutrition of Premature Birth Babies with the Artificial NeuroMolecular System

廖國勛(Guo-Xun Liao)；蔣志雄(Zih-Xiong Jiang)；陳重臣(Jong-Chen Chen)

演化式學習 ； 全靜脈營養 ； 統計分析 ； 類神經網路 ； Evolutionary Learning ； Total Parenteral Nutrition ； Statistical Analysis ； Artificial Neural Networks

管理與系統

15卷1期（2008 / 01 / 01）

161 - 176

繁體中文

全靜脈營養療法(total parenteral nutrition, T.P.N.)主要是針對營養不足的病人，以靜脈營養的注射方式，嘗試改善患者的健康情形。早產兒由於多數身體功能尚未齊全，其營養攝取一直是很大問題。本研究嘗試利用一套具有自主性學習功能之資料區別系統－類分子神經系統（Artificial NeuroMolecular System, ANM系統），以建立早產兒身體健康狀況與醫生之全靜脈營養處方之間的關係，並進一步探討與倒傳遞網路、統計方法、及人工判別作比較分析。實驗結果顯示，ANM系統不僅比統計方法及倒傳遞網路具有相對較佳的資料區別能力。出乎意料之外，ANM系統的結果甚至比人工判別的表現更佳。最後，本研究並探討各項屬性對早產兒體重增減的影響。

The objective of total parenteral nutrition (T.P.N.) is to improve nutritional deficiency of patients with nutritional liquids by intravenous injection. A premature baby usually has the problem of nutritional deficiency as most of its body functions have not developed completely. The objective of this study is to investigate the relationship between the health conditions of premature birth babies and the nutritional prescription filled by physicians using the Artificial NeuroMolecular System, a self-organizing system. The experimental results of the system were compared to those of the backpropagation neural networks, statistical tool, and human judgment. The results showed that the performance of the system was better than that of the backpropagation neural networks and statistical tools. Contrary to our expectation, our result was even better than that of human judgment. Lastly, we investigated the degrees of influence of each parameter.

1. Chen, J. C.,Conrad, M.(1997).Pattern Categorization and Generalization with a Virtual Neuromolecular Architecture.Neural Networks,10,111-123.
2. Chen, J. C.,Conrad, M.(1997).Evolutionary Learning with a Neuromolecular Architecture: A Biologically Motivated Approach to Computational Adaptability.Soft Computing,1,19-34.
3. Chen, J. C.,Conrad, M.(1994).A Multilevel Neuromolecular Architecture that Uses the Extradimensional Bypass Principle to Facilitate Evolutionary Learning.Physica D,75,417-437.
4. Chen, S. C.(1998).Problem Solving with a Perpetual Evolutionary Learning Architecture.Applied Intelligence,8(1),53-71.
5. Fogel, D.(1995).Evolutionary Computation: Towards a New Philosophy of Machine Intelligence.Piscatawy, NJ:IEEE Press.
6. Fogel, L. I.,Owens, A. S.,Walsh, M. J.(1996).Artificial Intelligence Through Simulated Evolution.New York, NY:John Wiley & Sons.
7. Hameroff S. R.,Watt, R. C.(1982).Information Processing in Microtubules.Journal of Theoretical Biology,549-561.
8. Hameroff, S. R.(1987).Ultimate Computing.Amsterdam:North-Holland.
9. Holland, J. H.(1975).Adaption in Natural and Artificial Systems.Ann Arbor, MI:University of Michigan Press.
10. Liberman, E. A.,Minina, S. V.,Golubtsov, K. V.(1975).The Study of the Metabolic Synapse II: Comparison of Cyclic 3`,5`-AMP and Cyclic 3`,5`-GMP Effects.Biophysics,22,75-81.
11. Liberman, E. A.,Minina, S. V.,Shklovsky-Kordy, N. E.,Conrad, M.(1982).Change of Mechanical Parameters as a Possible Means for Information Processing by the Neuron (in Russian).Biophysics,27,863-870.
12. Liberman, E. A.,Minina, S. V.,Shklovsky-Kordy, N. E.,Conrad, M.(1982).Microinjection of Cyclic Nucleotides Provides Evidence for a Diffusional Mechanism of Intraneuronal Control.BioSystems,15,127-132.
13. Matsumoto, G.,Tsukita, S.,Arai, T.,F.D. Warner,J.R. Mcintosh (ads)(1989).Organization of the Axonal Cytoskeleton: Differentiation of the Microtubule and Actin Filament Arrays.Cell Movement: Kinesin, Dynein, and Microtubule Dynamics,2,335-356.
14. Werbos, P.(1992).The Cytoskeleton: Why It May Be Crucial to Human Learning and to Neurocontrol.Nanobiology,1,75-95.
15. 方國定、陳重臣(1999)。以科技循環週期模式探討跨組織資訊系統之採用：自主性學習之類分子神經系統應用。交大管理學報，19(2)，55-83。
16. 方國定、陳重臣(1999)。以產品面探討跨組織資訊系統之採用：自主性學習之類分子神經系統應用。資管學報，6(1)，63-83。
17. 教育園地：靜脈營養
18. 陳重臣、方國定(1999)。以類分子神經系統對B型肝炎臨床資料作診斷預測、分析、交叉驗證。管理與系統，6(4)，433-458。