跳到主要內容

臺灣博碩士論文加值系統

(3.236.84.188) 您好!臺灣時間:2021/08/05 00:28
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:沈智敏
研究生(外文):Shen Chih-Min
論文名稱:應用緣集合論於延遲性診斷關鍵屬性之研究
論文名稱(外文):Using Affinity Set on the Key Attributes of Delayed Diagnosis Problem
指導教授:陳郁文陳郁文引用關係
指導教授(外文):Chen Yuh-Wen
學位類別:碩士
校院名稱:大葉大學
系所名稱:工業工程與科技管理學系
學門:工程學門
學類:工業工程學類
論文種類:學術論文
論文出版年:2007
畢業學年度:95
語文別:英文
論文頁數:66
中文關鍵詞:延遲性診斷緣集合資料探勘拓樸學
外文關鍵詞:delayed diagnosisaffinity setdata miningtopology
相關次數:
  • 被引用被引用:3
  • 點閱點閱:207
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:1
根據美國醫學研究機構(Institute of Medicine,簡稱IOM)所發表之報告指出,每年因可避免的醫療錯誤,至少造成四萬四千人死亡,且高居全美十大死因第八位。此報告突顯出關於醫療錯誤的嚴重性,消費者應該了解醫療錯誤的發生機率比我們原先所想的要高出許多,所謂的醫療錯誤在本研究中之定義為延遲性診斷,表示當病人的病徵在急診室未被發現,但被加護病房的醫師發現,即稱為延遲性診斷。
 本研究應用緣集合論的概念進行資料探勘的步驟,再利用拓樸學的方法分析資料之間的關連性,進而探討哪些屬性易造成延遲性診斷,以期降低延遲性診斷的機率,增進醫療品質。
 研究結果發現,病人於血壓與脈搏不正常之緊急狀態下,易造成醫師延遲性診斷,其機率高達六成。而其原因乃因醫師在緊急的情況下,沒有多餘的時間對病患作詳盡的診斷;而且醫師易以第一印象來判斷病人之病況,因此當病人處於意識清醒且呼吸正常時,易導致醫師延遲性診斷。此外;根據結果顯示,超時工作容易造成醫師工作失焦,但是醫師的年齡大小及專科證照的多寡並不會影響延遲性診斷的機率。
 本研究亦透過粗略集合之應用軟體ROSETTA產生規則與緣集合比較,發現前者的規則庫龐大且雜亂,無法清楚地解釋資料之間的關連性,且判中率最高的規則只有四成。
According to “Institute of Medicine investigation report”, there are at least 44,000 people die in hospitals each year as a result of medical errors, and these deaths due to medical errors is becoming the 8th-leading cause of death in the United States. These results point out a serious problem of medical errors, and consumers should realize that there is no absolutely safe in the health care system.
In this research, medical errors are defined as delayed diagnosis, which means patients’ injuries are ignored at Emergency Room (ER), but are identified by doctors in Intensive Care Unit (ICU). This study is using Affinity Set by topology concept as the tool of data mining to classify and analyze the relations within medical data, and to discuss which key attributes would cause delayed diagnosis. Furthermore, to help medical providers to reduce the probability of delayed diagnosis and to improve the quality of health care.
Studying results indicate when the patient’s triage is resuscitative, and the blood pressure and the pulse are abnormal, which lead to high probability (59%) to cause delayed diagnosis, it may because doctors at ER don’t have time to appropriately diagnose the patients, and doctors usually diagnose a patient’s symptoms by his first impression; therefore, they really ignore when the patient is consciously and breathes normally. In addition, when doctors are overworked, it is likely cause to delayed diagnosis, but doctors’ age and specialists don’t influence the probability of delayed diagnosis.
The rules of Affinity with the highest hit rate is 72.6%; however, the first rule of ROSETTA only gets 40% hit rate, and the database is disorderly and can’t describe the observation’s behavior clearly.
封面內頁
簽名頁
博碩士論文暨電子檔案上網授權書 iii
Abstract iv
中文摘要 v
誌謝 vi
Contents vii
Figure List x
Table List xi

Chapter 1 Introduction 1
1.1 Background and Motivation 1
1.2 Research Objectives 3
1.3 Assumptions and Limitations 3
1.4 Research Procedure 4
Chapter 2 Literature Review 5
2.1 Data Mining 5
2.1.1 The process of Knowledge Discovery in Database 5
2.1.2 The Techniques of Data Mining 6
2.1.3 Related Studies in Medical Data Mining 7
2.2 Set Review 8
2.2.1 Fuzzy Set 8
2.2.2 Rough Set 10
2.2.3 The Concept of Affinity Set 11
2.2.4 The Definition of Affinity 12
2.2.5 Comparison with Fuzzy Sets and Rough Sets 17
2.3 Summary 18
Chapter 3 Model Construction and Resolution 19
3.1 Research Procedure 19
3.2 Processing the Data 20
3.3 Generate the Rules 21
3.4 Computing Hit Rate 21
3.5 Find out the Rule Base 23
Chapter 4 Case Study 25
4.1 Data Collection 25
4.2 Data Coordination 25
4.3 Conclusions and Discussions 27
4.3.1 The Discussion of one Attribute 28
4.3.2 The Discussion of the Combination with two Attributes 29
4.3.3 The Discussion of the Combination with three Attributes 30
4.3.4 The Discussion of the Combination with four Attributes 31
4.3.5 The Discussion of the Combination with five Attributes 33
4.3.6 The Discussion of the Combination with six Attributes 34
4.3.7 The Discussion of the Combination with seven Attributes 35
4.3.8 The Discussion of the Combination with eight Attributes 36
4.3.9 The Discussion of the Combination with nine Attributes 37
4.3.10 Summary 37
4.4 The Conclusions while Patient’s Consciousness is clear 40
4.4.1 The Discussion of the Combination with two Attributes 40
4.4.2 The Discussion of the Combination with three Attributes 41
4.4.3 The Discussion of the Combination with four Attributes 42
4.4.4 Summary 43
4.5 The conclusions while patient is clear and breath is normal 45
4.5.1 The Discussion of the Combination with two Attributes 46
4.5.2 The Discussion of the Combination with three Attributes 47
4.5.3 Summary 48
4.6 Compare the results of Affinity with ROSETTA 50
Chapter 5 Conclusions and Recommendations 52
5.1 Conclusions 52
5.2 Recommendations 53
References 55
Appendix 58

Figure List
Figure 1 Data mining as a step in the process of knowledge discovery 6
Figure 2 Bivalent Sets to Characterize the Temp. of a room 9
Figure 3 Fuzzy Sets to Characterize the Temp. of a room 10
Figure 4 Illustration of the affinity between an element e and an affinity set over an observation period P 15
Figure 5 Research procedure 20
Figure 6 Topology Chart 23
Figure 7 Classify the data with having delayed diagnosis or not 26
Figure 8 Delayed diagnosis data 28
Figure 9 The highest hit rate of each attributes 39
Figure 10 The highest hit rate of each attributes 45
Figure 11 The highest hit rate of each attributes 49

Table List
Table 1 Comparison of Affinity Set, Rough Set and Fuzzy Set 17
Table 2 The patients database 22
Table 3 List of classification of attributes 27
Table 4 The core rules of 1 attribute 29
Table 5 The core rules of 2 attributes 30
Table 6 The core rules of 3 attributes 31
Table 7 The core rules of 4 attributes 32
Table 8 The core rules of 5 attributes 33
Table 9 The core rules of 6 attributes 34
Table 10The core rules of 7 attributes 35
Table 11The core rules of 8 attributes 36
Table 12The core rules of 9 attributes 37
Table 13The coordination of each combination with different attributes 38
Table 14The core rules of 1 attribute 40
Table 15The core rules of 2 attributes 41
Table 16The core rules of 3 attributes 42
Table 17The core rules of 4 attributes 43
Table 18The coordination of each combination with different attributes 44
Table 19The core rules of 1 attribute 46
Table 20The core rules of 2 attributes 46
Table 21The core rules of 3 attributes 47
Table 22The coordination of each combination with different attributes 49
Table 23The core rules of ROSETTA with 10 attributes 50
Table 24The core rules of ROSETTA with 4 attributes 51
[1]Bellman, R. E. and Zadeh, L. A., “Decision making in a fuzzy environment,” Management Science 17B, 141-164, 1970.
[2]Dubois, D. and Prade, H., Fuzzy Sets and Systems, Theory and Applications, Academic Press, New York, 1980.
[3]Ham, J. W. and Kamber, M., Data mining: concept and techniques, QA76.9.D343 H36, 2001.
[4]Klir, G. J. and Yuan, B., Fuzzy Sets and Fuzzy Logic: Theory and Applications, 3rd, Taiwan, 2003.
[5]Kohn, L. T., Corrigan, J. M. and Donaldson, M. S. Editors, To Err is Human: Building a Safer Health System, Washington D. C., 1999.
[6]Leape, L. L., Brennan, T. A., Laird, N., Lawthers, A. G., Localio, A. R., Barnes, B. A., Hebert, L., Newhouse, J. P., Weiler, P. C. and Hiatt, H., “Incidence of adverse events and negligence in hospitalized patients. Results of the Harvard Medical Practice Study I,” THE NEW ENGLAND JOURNAL of MEDICINE, vol. 324, 370-376, 1991.
[7]Moussa, L. and Chen, Y. W., A fuzzy Set Based Framework for the Concept of Affinity.
[8]Moussa, L. and Chen, Y. W., Developing the Affinity Set (or Guanxi Set) Theory and Its Applications.
[9]Pawlak, Z., “Rough Set,” International Journal of Computer and Information Science, Vol. 11, pp. 341-356, 1982.
[10]Pawlak, Z., Rough Sets. Theoretical Aspects of Reasoning about Data, Kluwer Academic Publishers, 1991.
[11]Viveros, M. S., Nearhos, J. P. and Rothman, M. J., “Applying Data Mining Techniques to a Health Insurance Information System,” Very Large Data Bases Conference, 22nd, 1996.
[12]Wilson, R. McL., Runciman, W. B., Gibberd, R. W., Harrison, B. T., Newby, L. and Hamilton, J. D., “The Quality in Australian Health Care Study,” THE MEDICAL JOURNAL OF AUSTRALIA, vol. 163, 458-471, 1995.
[13]Zadeh, L. A., Fuzzy sets, Information and Control, 8, 338-353, 1965.
[14]Department of Health, Executive Yuan, R.O.C.(Taiwan):
http://www.doh.gov.tw/CHT2006/index_populace.aspx.
[15]IBM: http://www.ibm.com/us/
[16]Medicare Australia: http://www.hic.gov.au/
[17]Patient Safety Net: http://www.patientsafety.tw/big5/default.asp.
[18]ROSETTA software: http://www.idi.ntnu.no/~aleks/thesis/
[19]World Health Organization: http://www.who.int/patientsafety/en/.
[20]古裕彥,統計資料採礦,東海大學統計學系研究所碩士論文,2002。
[21]周建河,急診醫師人力調整前後之醫療品質相關性探討-以南部三家醫院為例,國立中山大學人力資源管理研究所碩士論文,2003。
[22]郭萃華,醫療錯誤相關因素探討-以外科醫療為例,國立台灣大學醫療機構管理研究所碩士論文,2005。
[23]陳麗琴,中文版五級急診檢傷分類電腦化系統之建構與臨床應用評估,台北醫學大學護理學研究所碩士論文,2005。
[24]楊哲彥,楊秀儀,台灣地區中醫與西醫醫療糾紛的差異,長庚大學醫務管理學系及研究所碩士論文,J Chin Med, 15(1), 1-15, 2004。
[25]雷賀君,前十字韌帶傷害快速診斷系統-以粗略集合、基因演算法與倒傳遞網路為工具,大葉大學工業工程學系研究所碩士論文,2004。
[26]趙文敏,拓樸學導論,九章出版社,台北,1992。
[27]蘇步青,拓樸學初步,亞東書局,台北,1992。
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊