臺灣博碩士論文加值系統

心血管疾病漸漸成為已開國家主要死亡原因，且長期接受治療的病患通常忽略了疾病的進行性。因此，評估用藥與生化檢驗數據來發掘原始資料中所潛藏且可以被萃取的知識，即變得很重要且必要。本篇採用了無監督式神經網路與粗集理論來發掘用藥的知識。所提出的SOM-SOM-RST 程序，其效果優於決策樹和區別分析。且在交叉驗證比對中，本程序能成功並有效地檢測出疾病趨勢有變化之病患，並且獲得約98%的準確率。粗集理論則是用來增進符號式規則的概化，以便能方便導入支援系統。因此，本篇的主要貢獻有：（1）以提出的程序來分析篩檢個別病患長期，但被忽略的疾病變化趨勢，並藉以協助醫師重新評估病患與調整治療。（2）符號式規則的概化以便於專家使用與系統發展。

Cardiovascular disease is becoming the major cause of death in many industrialized countries. People who receive long-term treatments usually ignore the progress of the disease states. Therefore, it is critical and necessary to evaluate drug utilization and laboratory test in order to discover the knowledge that is beneath and can be extracted from those raw data. This paper utilizes techniques of unsupervised networks and rough set theory to discover drug utilization knowledge. The result of the proposed SOM-SOM-RST process shows more advantages than that of decision tree and discriminate analysis. With 10-fold cross verification, the proposed process successfully and effectively detect patients whose diagnosis codes have been changed during the period of investigation and attain an accuracy of approximate 98%. Rough set theory here, hence, can be easily adapted and implemented in support systems.
The contributions of this paper are: (1) With the proposed process, individual disease state trends can be identified that remind physicians to re-evaluate the long-term, but ignored disease tends. (2) Generalization of symbolic rules for system development.

摘 要, i
ABSTRACT, ii
Content, iii
Table, iv
Figure, v
1. Introduction, 1
1.1 BACKGROUND AND MOTIVATION, 1
1.2 RESEARCH OBJECTIVES, 2
1.3 RESEARCH LIMITATIONS, 2
1.4 ORGANIZATION OF THE STUDY, 4
2. Literature review 5
2.1 SOFT COMPUTING, 6
2.1.1 Self-Organizing Map (SOM), 7
2.1.2 Rough Set Theory (RST), 9
2.2 CARDIOVASCULAR DISEASE REVIEW, 12
2.3 SOFT COMPUTING IN MEDICINE, 16
3. Soft computing for knowledge discovery, 17
3.1 RESEARCH FRAMEWORK, 17
3.2 DISCOVERY WITH SOM, 23
3.3 THE PROCESS OF SOM-SOM-RST, 26
4. Results of knowledge presentation, 28
4.1 RESULT OF 1ST AND 2ND SOM, 32
4.2 VERIFICATION, 39
5. Conclusion and future work, 41
Reference, 4

[1] Barbara Hammera et al., A general framework for unsupervised processing of structured data, Neurocomputing 57 pp.3 – 35, 2004
[2] Chappell G., Taylor J., The temporal Kohonen map, Neural Networks 6 p.441–445, 1993
[3] Coppini, Giuseppe et al., Matching of medical images by self-organizing neural networks, Pattern Recognition Letters 25, Issue: 3, 2004
[4] D. Josefson, Computers beat doctors in interpreting ECGs, Br. Med. J. 315 p.764–765, 1997
[5] David West et al., Model selection for a medical diagnostic decision support system: a breast cancer detection case, Artificial Intelligence in Medicine 20, p. 183-204, 2000
[6] Department of Health, Taiwan, “Health and National Health Insurance Annual Statistics Information Service”, http://www.doh.gov.tw
[7] Elisabeth N. Bui, Soil survey as a knowledge system, Geoderma 120 p.17–26, 2004
[8] Ermini F., Marchesi C., Intelligent data retrieval from multidimensional clinical archives, in: E. Ifeachor, A. Sperduti, A. Starita (Eds.), Neural Networks and Expert Systems in Medicine and Healthcare, World Scienti2c, Singapore, New Jersey, London, Hong Kong, pp. 295–303, 1998
[9] Fayyad, Usama et al., From Data Mining to Knowledge Discovery in Databases, American Association for Artificial Intelligence, p.37, Fall 1996
[10] Foster Provost et al., The case against accuracy estimation for comparing induction algorithms, Fifteenth International Conference on Machine Learning, Madison, WI, 1998.
[11] Frith C, Dolan RJ., Philos Trans R Soc Lond B Biol Sci.,352 (1358):1221-30, 1997 Aug 29
[12] G.H. von Wright, Explanation and Understanding, Cornell University Press, 1971
[13] Gregory, Richard L, Knowledge in perception and illusion, Phil. Trans. R. Soc. Lond. B 352, p.1121–1128 Department of Psychology, University of Bristol, 8 Woodland Road, Bristol BS8 1TA UK, 1997
[14] Hagenbuchner M., Sperduti A., Tsoi A.C., A self-organizing map for adaptive processing of structured data, IEEE Trans. Neural Networks 14 (3) p.491–505, 2003
[15] Huang, Yu-Len et al., Watershed segmentation for breast tumor in 2-D sonography, Ultrasound in Medicine and Biology (30), Issue: 5, 2004
[16] Jin, Yaochu, http://www.soft-computing.de, Honda Research Institute Europe
[17] K. Kiviluoto and P. Bergius, Two-level self-organizing maps for analysis of financial statements, IEEE International Joint Conference on Neural Networks (IJCNN''98), vol. 1, p. 189-192, 1998.
[18] Kannel WB., Hazards, risks, and threats of heart disease from the early stages to symptomatic coronary heart disease and cardiac failure. Cardiovasc Drugs, 1997
[19] Kannel WB., Office assessment of coronary candidates and risk factor insights from the Framingham study. J Hypertens Suppl, 1991
[20] Kemal Kilic et al., Fuzzy system modeling in pharmacology: an improved algorithm, Fuzzy Set and System 130, 253-264, 2002
[21] Kinosian B et al., Cholesterol and coronary heart disease: predicting risks by levels and ratios, Ann Intern Med, 1994
[22] Kohonen T., Learning vector quantization, in: M. Arbib (Ed.), The Handbook of Brain Theory and Neural Networks, MIT Press, Cambridge, MA, pp. 537–540, 1995
[23] L. Salchenberger, E.R. Venta, L.A. Venta, Using neural networks to aid the diagnosis of breast implant rupture, Comput. Operations Res. 24 (5) pp. 435–444, 1997
[24] Luo, Kuo-Hsu, Applying Two Level Self-Organizing Map to Analyze Underwriting and Claim Behavior Model, Master thesis, 2004
[25] Matthews, P.C. et al., The introduction of a design heuristics extraction method, Advanced Engineering Informatics 16 p.3-19, 2002
[26] Rich, E., Artificial intelligence. In: Shapiro, S. (Ed.), Encyclopedia of Artificial Intelligence, vol. 1. Wiley, New York, pp. 9 – 16, 1987
[27] Ritter H., Martinetz T., Schulten K., Neural Computation and Self-Organizing Maps, An Introduction, Addison-Wesley, Reading, MA, 1992.
[28] Th. Villmann, Neural maps for faithful data modelling in medicine, Neurocomputing 48 p.229–250, 2002
[29] Tommy W.S. Chow, Sitao Wu, Cell-splitting grid: a self-creating and self-organizing neural network , Neurocomputing 57 p.373 – 387, 2004
[30] Voegtlin T., Dominey P.F., Recursive self-organizing maps, in: N. Allison, H. Yin, L. Allinson, J. Slack (Eds.), Advances in Self-Organizing Maps, Springer, Berlin, 2001, pp. 210–215.
[31] Voegtlin T., Recursive self-organizing maps, Neural Networks 15 (8–9) p.979–992, 2002
[32] W.G. Baxt, Use of an artificial neural network for data analysis in clinical decision-making: the diagnosis of acute coronary occlusion, Neural Comput. 2, p. 480–489, 1990
[33] Wg Cdr Narinder Taneja, Douglas A Wiegmann, The role of perception in Medication Errors: Implications for Non-Technological Interventions, MJAFI 60: 172-176, 2004