資料載入中.....
|
請使用永久網址來引用或連結此文件:
https://ir.cnu.edu.tw/handle/310902800/10473
|
| 標題: | 癌症臨終病患選擇安寧療護之特性探討一利用決策樹於健保研究資料庫
Characteristics of terminal cancer patients in hospice care units：a decision tree analysis of insurance data |
| 作者: | 郭育廷
Yu-Ting Kuo |
| 貢獻者: | 楊美雪
嘉南藥理科技大學：醫療資訊管理研究所 |
| 關鍵字: | 決策樹
癌症
安寧療護
Hospice
Decision tree
Cancer |
| 日期: | 2008 |
| 上傳時間: | 2010-06-01 09:21:32 (UTC+8) |
| 摘要: | 目標:從文獻探討，安寧療護之住院醫療費用比非安寧療護節省，又可有效地減輕癌症病患身、心、靈痛苦，是值得推展的照護型態。本研究以資料探勘決策樹技術分析健保資料庫癌症末期選擇安寧之病患的有意義資訊，作為提升安寧療護使用率之政策制定的參考。方法:擷取2005年健保研究資料庫住院癌症死亡病患為研究樣本，與醫事機構基本資料檔連結獲取病患醫院權屬別、評鑑等級及分局別資料。依Charlson comorbidity index , CCI計算病患診斷共存疾病指標分數，並將年齡與CCI資料轉換為類別變數，統計分析包括描述性與卡方統計檢定，以SPSS Clementine 7.2建構決策樹模型，目標變數(輸出變數)為照護型態類別(安寧/非安寧);輸入變數包括人口學、臨床及醫院特性。評估決策樹C5.0及CART演算法建模預測正確績效，選擇較佳的演算法建模，萃取安寧療護分類規則。結果:臨終癌症病患安寧住院療護的平均每人次費用35,385，63元比傳統住院安寧療護的平均費用145,478低(p<0.001)。病患性別、年齡、癌症別、CCI別、醫院權屬別、評鑑等級別、分局別等變數，分別與照護型態有統計上顯著關聯(p<0.0001)。本研究資料C5.0演算法之正確率大於CART演算法。決策樹C5.0演算法資訊增益三大變數依序為醫院權屬別、分局別、等級別，以醫院權屬別為最重要之照護型態分類預測變數。性別變數並沒有被選取為樹之內部節點，顯示在其他變數存在下，性別並不是影響臨終病患選擇安寧之因素，即使性別在女性使用率27.62%顯著高於男性23.01%。本研究萃取安寧療護分類規則7條，其中較有意義的資訊，依信心度大小有宗教財團法人醫院(0.893) 、財團法人北區地區醫院(0.872) 、私立中區地區醫院(0.857)及財團法人東區醫學中心(0.837)。結論:安寧療護的費用比非安寧節省，宗教財團法人醫院是為癌症末期臨終病患或家屬之最佳善終醫療場所。本研究建議宗教財團法人醫院可為非宗教醫院之標竿學習對象。至於宗教與安寧療護之相關，有待後續的研究進一步深入探討。
Objectives: From literature review, inpatient medicare expenditure of hospice saving than non-hospice, and effectively reduce cancer patients physical and mental and spiritual pain, worthwhile to promote type of care. The aim of this study was use Data Mining Decision tree analyze the Bureau of National Health Insurance database that the terminal cancer patient which chose hospice, to find out the meaning information, to promote hospice’s using provide a policy for government referable.
Method: Data from National Health Insurance Research Database of the inpatient cancer patients who had death in 2005 were studied, connect with HOSP obtains patient’s data of ownership, ranking level, Branch Bureau. Count Charlson comorbidity index of patient diagnosis(Charlson comorbidity index, CCI), age and CCI transform category variable, statistical analysis including descriptive statistics and Chi test, Utilization SPSS Clementine 7.2 to establish decision tree model, Output variables for the type of care patterns(hospice/nonhospice); input variable including demographic, clinical and hospital characteristics. Assessment decision tree C5.0 and CART algorithm modeling of correctly predicted performance, choose better algorithm modeling to extraction classification rule of hospice.
Results: Variables of patient gender, age, type of cancer, ownership, ranking level, Branch Bureau has significant difference in statistical with type of care, respectively (p<0.001). The study data of C5.0 algorithms correct rate is greater than the CART algorithm. Decision tree algorithms of C5.0 gain information were the three major variables for the hospital ownership, Branch Bureau, ranking level, hospital ownership is most important classification predict variable of care type. All of characteristics in hospice and nonhospice of relatively has significant difference, The other hand, the result shows while other variables exist, gender was not impact factor of patient who choose hospice, even female in the utilization rate of 27.62% was significantly higher than male of 23.01%.The study extraction 7 rule from hospice classification, all of rule choose meaningful information, in accordance with the size of confidence in a Religious Foundation Hospital (0.893), Foundation North Region Branch AREA Hospital(0.872), Private Center Region Branch AREA Hospitals(0.857), Foundation Eastern Medical Centers(0.837).
Conclusions: The study found that patients with terminal cancer, medicare expenditure of hospice has significant lower than nonhospice, analysis result of decision tree, information gain for the largest hospital ownership, Religious Foundation Hospital predicted accuracy rate of 0.893, Religion Foundation hospitals show that is dying for terminal cancer patients or their families for the best hospice medical establishments. Finally, the study suggest that Religion Foundation hospitals can be learning objects to non- Religion Foundation hospitals. In the case of correlation between religion and hospice, waiting for follow-up researchers to further study. |
| 關聯: | 中文文獻
1.丁一賢、陳牧言：資料探勘，初版。台中市：滄海 2005；132-141。
2.中央健康保險局：安寧療護整合性照護納入全民健康保險給付試辦計畫 2000。
3.台灣安寧基金會網站。http://www.hospice.org.tw/chinese/index.php.
4.行政院衛生署：國家癌症防治五年計畫 2004。
5.行政院衛生署：衛生統計資訊網2008。
6.周歆凱、蘇喜、黃興進、蔡明足、翁林仲：運用決策樹技術探討急診病患醫療費用之消耗。臺灣公共衛生雜誌 2006，25(6)，430-439。
7.林維娟：跨區醫療利用及其影響因素分析。陽明大學醫務管理研究所碩士論文 2003。
8.邱宗傑。末期癌症病人的臨終照顧。臨床醫學 1996；37(6)：378-383。
9.柏木哲夫：用最好的方式向生命揮別------臨終照護與安寧療護(曹玉人譯)。台北：方智出版社股份有限公司 2000。
10.財團法人中華民國(台灣)安寧照顧基金會。http://www.hospice.org.tw/chinese/hospital.php。引用1/28/2008.
11.黃宇達：死亡焦慮：性別、年齡與死亡焦慮歸因之角色的探討。中原大學心理學系碩士論文 1997。
12.黃鳳英、宗惇法師、陳慶餘、惠敏法師：台灣安寧病房臨床佛教宗教師需求調查。安寧療護雜誌 2001；6(3)：16-26。
13.楊克平：論緩和療護之意義及其變化史。榮總護理 1999；16（4）：357-363。
14.鄒平儀：臨終病患安寧照顧模式之建構分析。中華醫務社會工作學刊 1996；6：101-112。
15.趙可式：安寧療護的起源與發展 1999。厚生 1999；8。
16.潘美惠、胡蓮芬：護理之家的靈性與宗教關顧－馬偕紀念醫院的經驗。長期照護雜誌 2004；8(2)：145-163。
17.鄭百評：資料採礦讓企業深耕客戶價值。數位時代雜誌 2001，專刊2 號，48-51。
18.羅健銘、陳素秋、賴允亮、林家瑾、陳建仁：住院癌末病患照護型態對住院醫療費用與住院天數之影響。台灣衛誌 2007；26(4)：270-282。
19.鐘昌宏編著：「癌病末期」安寧照顧──簡要理論與實踐。財團法人中華民國安寧照顧基金會發行 1997。
英文文獻
1.Ardelt M., Koenig CS. The Role of Religion for Hospice Patients and Relatively Healthy Older Adults 2006. Research on Agin；28(2):184-215.
2.Bacon LD.“Marketing,” Handbook of Data Mining and Knowledge Discovery, edited by Willi Klösgen & Jan M. Żytkow, OXFORD University Press 2002；715-725.
3.Balboni TA, Vanderwerker LC, Block SD, Paulk ME, Lathan CS, Peteet JR, Prigerson HG. Religiousness and spiritual support among advanced cancer patients and associations with end-of-life treatment preferences and quality of life. J Clin Oncol 2007；25(5):555-60.
4.Berry M J, Linoff G. Data Mining Techniques for Marketing. Sales and Customer Support 1997. Wiley.
5.Breiman, Friedman, Olshen, and Stone. Classication and Regression Trees. Wadsworth International Group 1984.
6.Cabena, P, Hadjinaian, PO, Stadler, D.R.J., Verhees, J. and Zanasi, A., Discovering Data Mining from Concept to Implementation, Prentice Hall 1997.
7.Campbell DE, Lynn J, Louis TA, Shugarman LR. Medicare program expenditures associated with hospice use. Ann Intern Med 2004；140(4):269-77.
8.Carlson MD, Gallo WT, Bradley EH. Ownership Status and Patterns of Care in Hospice: Results from the National Home and Hospice Care Survey. Medical Care 2004；42(5):432-8.
9.Chang LY, Wang HW. Analysis of traffic injury severity: an application of non-parametric classification tree techniques. Accid Anal Prev 2006；38(5):1019-27.
10.Charlson ME, Pompei P, Ales KL, MacKenzie CR. A new method of classifying prognostic comorbidity in longitudinal studies: development and validation. J Chronic Dis 1987；40(5):373-83.
11.Emanuel EJ, Ash A, Yu W, Gazelle G, Levinsky NG, Saynina O, McClellan M, Moskowitz M. Managed care, hospice use, site of death, and medical expenditures in the last year of life. Arch Intern Med. 2002;162(15):1722-8.
12.Fayyad U, Shapiro GP, Smyth P. The KDD process for extracting useful knowledge from volumes of data. Communications of the ACM 1996；39(11):27-34.
13.Fisher ES, Wennberg JE, Stukel TA, Skinner JS, Sharp SM, Freeman JL, Gittelsohn AM. Associations among hospital capacity, utilization, and mortality of US Medicare beneficiaries, controlling for sociodemographic factors. Health Serv Res 2000；34(6):1351-62.
14.Frawley WJ, Paitetsky SG, Matheus CJ, Knowledge Discovery in Databases: An Overview. Communications of the ACM 1996, 39:1-34.
15.Grupe FH, Owrang MM. Database Mining Discovering New Knowledge and Cooperative Advantage, Information Systems Management 1995；12(4):26-31.
16.Ham J, Kamber M. Data Mining: Concepts and Techniques. San Diego: Academic Press 2001.
17.Hanson LC, Usher B, Spragens L, Bernard S. Clinical and economic impact of palliative care consultation. J Pain Symptom Manage 2008;35(4):340-6.
18.Hermann CP. Spiritual needs of dying patients: a qualitative study. Oncol Nurs Forum 2001；28(1):67-72.
19.Hermann CP. The degree to which spiritual needs of patients near the end of life are met. Oncol Nurs Forum 2007；34(1):70-8.
20.Hospice care in Medicare: Recent trends and a review of the issues. www.medpac.gov/publications/congressional_reports/June04_ch6.pdf。引用1/18/2008.
21.Kutner JS, Bryant LL, Beaty BL, Fairclough DL. Time course and characteristics of symptom distress and quality of life at the end of life. J Pain Symptom Manage 2007；34(3):227-36.
22.Lewin SN, Buttin BM, Powell MA, Gibb RK, Rader JS, Mutch DG, Herzog TJ. Resource utilization for ovarian cancer patients at the end of life: How much is too much? Gynecologic Oncology 2005；99(2):261-266.
23.Lo J. C. The impact of hospices on health care expenditures-the case of Taiwan. Social Science & Medicine 2002；54(6):981-991.
24.McClain CS, Rosenfeld B, Breitbart W. Effect of spiritual well-being on end-of-life despair in terminally-ill cancer patients. Lancet 2003；361(9369):1603-7.
25.McClain-Jacobson C, Rosenfeld B, Kosinski A, Pessin H, Cimino JE, Breitbart W. Belief in an afterlife, spiritual well-being and end-of-life despair in patients with advanced cancer. Gen Hosp Psychiatry 2004；26(6):484-6.
26.Mor V, Kidder D. Cost savings in hospice: final results of the National Hospice Study. Health Serv Res 1985；20(4):407-22.
27.National Hospice Organization 1993.
28.Neimeyer, RA, Moore MA.Validity and reliability of the multidimensioal fear of death scale. In Nemeyer,R.A.(Ed.), Death anxiety handbook: Reasearch,instrumentation, and application (103-119).Washington: Taylor & Francis 1994.
29.Pavlopoulos SA, Stasis AC, Loukis EN. A decision tree--based method for the differential diagnosis of Aortic Stenosis from Mitral Regurgitation using heart sounds. Biomed Eng Online 2004；3(1):21.
30.Perron V, Schonwetter R. Hospice and palliative care programs. Prim Care: Clinics in Office Practice 2001, 28(2)：427-440.
31.Quinlan JR. C4.5: Programs for Machine Learning, Morgan Kaufmann 1993；USA.
32.Razavi AR, Gill H, Ahlfeldt H, Shahsavar N. Predicting metastasis in breast cancer: comparing a decision tree with domain experts. J Med Syst 2007； 31(4):263-73.
33.S.C. Hui, and G. Jha. Data mining for customer service support. Information and Management 2000；38(1):1-13.
34.Shugarman LR, Bird CE, Schuster CR, Lynn J. Age and gender differences in Medicare expenditures at the end of life for colorectal cancer decedents. J Womens Health (Larchmt) 2007；16(2):214-27.
35.Taylor EJ, Mamier I. Spiritual care nursing: what cancer patients and family caregivers want. J Adv Nurs 2005；49(3):260-7.
36.Tjortjis C, Saraee M, Theodoulidis B, Keane JA. Using T3, an improved decision tree classifier, for mining stroke-related medical data. Methods Inf Med 2007；46(5):523-9.
37.Virnig BA, Kind S, McBean M, Fisher E. Geographic variation in hospice use prior to death. J Am Geriatr Soc 2000；48(9):1117-25.
38.World Health Organization 1990.
39.Yoo JY, Chun JH. Determining factors of intention to actual use of charged long-term care services for the aged. J Prev Med Pub Health 2005；38(1):16-24. |
| 顯示於類別: | [醫務管理系(所)] 博碩士論文
|
文件中的檔案:
| 檔案 |
描述 |
大小 | 格式 | 瀏覽次數 |
|---|
| index.html | | 0Kb | HTML | 1616 | 檢視/開啟 |
|
在CNU IR中所有的資料項目都受到原著作權保護.
|
