臺灣博碩士論文加值系統

全民健保之主要目的在於提昇醫療品質，並分擔就醫時的財務風險，減少國人就醫之財務障礙，但健保開辦至今以來，財務問題一直是最大隱憂，其原因包含保險制度、民眾就醫習慣、及醫療資源浪費等問題，而其中造成健保財務惡化的最大原因就是醫療資源的浪費。
針對醫療費用的管控，本研究提出一費用分析架構藉以即時分析醫療費用掌控醫療院所的申報概況，對於異常院所及醫師的管控，則利用異常監控管理系統追蹤管理，使其改善異常情形。經由健保局的實際驗證，確實分析出異常浮報的院所，並有效的掌控醫療院所申報情形，縮短分析作業時程，改善異常情形進而減少醫療費用的浪費。另一方面，透過分析流程管理系統記錄使用者分析異常院所的步驟，進而獲取分析經驗，提供分析醫療費用時的支援決策功能。
另外，本研究整合貝氏分類、決策樹、Fuzzy Pattern Clustering與Fuzzy c-Means Clustering等資料探勘技術，提出一異常篩選架構應用於申報異常案件之篩選，並以健保真實資料進行實作驗證，研究成果顯示資料分類率高達98.64%，敏感度達90.1%，證實此異常篩選架構的確可行，對於現行健保局抽樣審查作業有極大的幫助。

The main purpose of National Health Insurance (NHI) is to promote the medical quality, to share the financial risk of medical treatment, and to alleviate the financial burden of each individual. However, since it has been established, the financial shortfall of NHI has been the focal point of many debates. The reason includes the consumers'' behaviors, the waste of health resources, and the insurance system itself. Among these various causes, the most trouble one is the abuse of medical resources.
In this thesis, aiming at the control of medical expenditure, not only do we propose an integrated model of data analysis and knowledge discovery for the expense control of NHI, but also develop a management model for monitoring the anomalous claims of medical services. A prototype implemented in the NHI reveals that the claims of medical services could be effectively controlled. Besides, shortening the time of analysis process, improving the abnormal situation, and decreasing the waste of medical expenditure are all bonuses to this system. On the other hand, we can also record the process of analyzing abnormal hospitals to get experiences, which could be offered as a decision support while we analyze the medical expenditure.
Finally, the simulation results show that the data classification rate is up to 98.64%, and the sensitivity is up to 90.1%. These results present that this automatic selection of abnormal medical expense filings model is effective. It will do great help to the present NHI in the sampling audit operation.

圖 目 錄X
表 目 錄XI
1、緒論1
1.1背景1
1.2研究範疇2
1.3論文組織2
2.1健保費用審查制度3
2.1.1審查作業3
2.1.2審查困境5
2.2資料探勘6
2.2.1資料探勘步驟6
2.2.2資料探勘技術8
3、健保醫療費用管理系統之設計與實現17
3.1系統架構17
3.2費用分析與統計18
3.2.1分析方法18
3.2.2業務統計22
3.3分析流程管理23
3.5系統實作25
4、整體面異常篩選27
4.1、分析架構設計27
4.1.1整體醫療費用分析28
4.1.2成長率分析29
4.1.3疾病結構與醫令分析29
4.2、整體指標異常推論31
5、個別面異常篩選36
5.1 資料處理36
5.1.1資料選取36
5.1.2 處理與轉換37
5.2 異常篩選架構建立38
5.3 回饋與修正47
5.4 驗證與評估47
5.4.1 驗證方法47
5.4.2 實驗結果49
5.4.3 結果評估55
6、結論57
6.1 研究成果57
6.2 未來工作58
參考文獻60

[1] Berry, Michael J.A. and Gordon Linoff, “Data Mining Techniques- For Marketing, Sales, and Customer Support,” Wiley Computer Publishing, 1997, pp51~62.
[2] Cabena, P., Pablo Hadjinlan and Rolf Stadler etc., “Discovering Data Mining From Concept to Implementation,” Prentice Hall, Inc., 1998,pp41~59.
[3] Curet, O., Jackson, M. and Tarar, A, “Designing And Evaluating A Case-Based Learning And Reasoning Agent In Unstructured Decision Making,” IEEE International Conference on Volume: 4, pp. 2487 —2492, 1996.
[4] E. Trauwaert, On The Meaning of Dunn’s Partition Confficient for Fuzzy Clusters, Fuzzy Sets and Systems pp217~242, 1998.
[5] Finin, T., “ID3 Algorithm,” http://www.cs.umbc.edu/471/notes/18/sld025.htm
[6] George J. Klir , “Fuzzy Sets and Fuzzy Logic Theory and Applications,” Prentice-Hall International, Inc. ,pp357~378
[7] J.C. Bezdek. Pattern recognition with fuzzy objective function algorithms. Plenum, New York, 1981.
[8] J.C.Bezdek, Cluster validity with fuzzy set, J.Cybernet. p58~73 , 1974.
[9] J.C.Dunn, A fuzzy relative of the ISODATA process and its use in detecting compact well-separated clusters, J. Cybern., 3:32, 1974.
[10] Jin JIA and Keiichi ABE, “Improvement of Decision Tree Generation by Using Instance-Based Learning and Clustering Method,” IEEE International Conference on Volume: 1, pp.696 —701, 1996.
[11]Michael Berthold,David J.Hand “Intelligent Data Analysis,” Springer, pp129~166, 1999.
[12] Pyle, D., “Data Preparation For Data Mining,” Morgan Kaufmann Publishers, Inc., 1999.
[13]Thomas H. Cormen, Charles E. Leiserson, Ronald L. Rivest, “Introduction to Algorithms,” MIT Press, pp314~319, 1990.
[14] USAMA M. FAYYAD et al., “Advances in Knowledge Discovery and Data Mining ,” MIT Press, Cambridge, Mass., 1996
[15] 中央健康保險局, “全民健康保險醫療費用專業審查抽樣作業要點,” 中央健康保險局, 1996。
[16] 中央健康保險局, “全民健康保險醫療費用申報狀況,” 中央健康保險局, http://www.nhi.gov.tw/stat/06z3-1.htm, 2000。
[17] 方世榮, “統計學導論,” 華泰文化事業公司, 1998。
[18] 林信忠撰, “資料發掘技術應用于健保醫療費用稽核之研究,” 元智大學,1999。
[19] 葉怡成編著, “類神經網路模式應用與實作,” 儒林出版社, 2000。
[20] 趙士儀撰, “以主成份分析法處理定量資料缺失值問題,” 元智大學, 2000。
[21] 戴久永著, “統計概念與方法,” 三民書局出版, 1994
[22] 藍中賢撰, “結合模糊集合理論與貝氏分類法之資料探勘技術 應用於健保局醫療費用審查作業,” 元智大學, 2000
[23] 胡坤德, “貝氏可能值推測方法之研究,” 東海學報 ,pp95-166 , 1995。
[24] “全民健康保險醫事服務機構醫療服務審查辦法,” 行政院衛生署,1995
[25] 陳團景, “健保醫療費用審查費用之標準化與制度化,” 全民健保醫療服務機構醫療服務專業審查研討會會議記錄, 1997。
[26] 范錚強, “中央健康保險局決策輔助系統之整體需求規劃,” 中央大學資訊管理學系, pp13-16, 1996
[27] 沈富雄, “全民健康保險的缺失與改革,” 行政院衛生署衛生報導雜誌社 , 2000, http://www.doh.gov.tw/new/moth/page2.html
[28] 陳宗獻, “檢視醫療浪費,” 行政院衛生署衛生報導雜誌社 , 2000, http://www.doh.gov.tw/new/moth/page26.html
[29] 吳運東, “健保財務問題之癥結與解套,” 行政院衛生署衛生報導雜誌社 , 2000, http://www.doh.gov.tw/new/moth/page24.html, 2000
[30] 朱樹勳, “全民健保如何開源與節流？”行政院衛生署衛生報導雜誌社 , 2000, http://www.doh.gov.tw/new/moth/page19.html
[31] 陳國團, “實話說健保「非不能、實不敢為也」,” 行政院衛生署衛生報導雜誌社 , 2000, http://www.doh.gov.tw/new/moth/page30.html
[32] 譚嘉慧撰, “模糊分類適切性分析,” 中原大學, 2000.