臺灣博碩士論文加值系統

醫療疏失每年都在重複的發生，產生醫療疏失的問題非常多，醫生本身的專業能力、精神狀況、時間壓力、藥物劑量誤判…等多種原因導致醫療疏失的問題產生，只要能克服部分誤診的情況就能讓許多患者得到更正確的治療，本研究使用透明分類器進行研究，利用UCI公開資料集所提供的11個醫療資料集進行研究，對每一個資料集進行平衡數據，之後分別針對每一個資料集裡面的特徵尋找交集特徵，之後將找到的交集特徵整合成一個特徵集合應用在測試資料中，本研究發現正常或異常筆數的多寡都會有交集的特徵，且可以使用極少的資料得到良好的績效結果，藉此解決醫療資料不易取得的問題。

Medical negligence occurs repeatedly every year, and there are many problems of medical negligence. Doctors' own professional ability, mental state, time pressure, misjudgment of drug dosage... and other reasons lead to the problem of medical negligence. As long as some misdiagnoses can be overcome Many patients can be treated more correctly. This study uses a transparent classifier to conduct research, using 11 medical data sets provided by the UCI public data set to conduct research, balance data for each data set, and then separately for each data set. The features in the data set search for intersection features, and then integrate the found intersection features into a feature set and apply it to the test data. This study found that the number of normal or abnormal will have intersection characteristics, and can use very little data to obtain excellent performance results, thus solving the problem of difficult access to medical data.

目錄
摘要 I
ABSTRACT II
目錄 III
表目錄 IV
圖目錄 V
壹、 緒論 1
1.1 研究背景 1
1.2 研究動機 1
1.3 研究目的 1
貳、 文獻回顧 2
2.1 醫學資料 2
2.2 特徵選擇 2
2.3 異常檢測 2
2.4 透明分類器 3
2.5 不平衡數據 3
參、 方法 4
3.1 方法概述 4
3.2 前置處理 7
3.2.1 上採樣 7
3.2.2 資料重構 8
3.2.3 離散化 11
3.2.4 數據編碼 12
3.2.5 一致性 12
3.3 透明分類器 13
3.4 透明分類器閥值 14
3.4.1 閥值設定 14
3.4.2 閥值挑選 14
3.5 評估指標 16
肆、 實驗 18
4.1 實驗資料 18
4.2 上採樣之影響 18
4.3 實驗結果 19
伍、 結論 25
參考文獻 26

Agrawal, R., & Srikant, R. (1994). Fast algorithms for mining association rules in large databases. In Proceedings of the 20th international conference on very largedatabases (pp. 487–499).
Al-Maolegi M. & Arkok B. (2013). An improved apriori algorithm for association rules of mining. Int J Nat Lang Comput 2014;3:21–9.
Asadi, S., SeyedEhsan, Roshan & Michael W.Kattan(2021).Random forest swarm optimization-based for heart diseases diagnosis. Journal of Biomedical Informatics, 115. doi: 10.1016/j.jbi.2021.103690.
Alshayeji, M.H., Ellethy, H., Abed, S. & Gupta, R.(2021).Computer-aided detection of breast cancer on the Wisconsin dataset: An artificial neural networks approach. Biomedical Signal Processing and Control, 71, Part A. doi: 10.1016/j.bspc.2021.103141.
Alwohaibi, M., Alzaqebah, M., M.Alotaibi, N., Abeer M., Alzahrani & Zouch, M.(2021).A hybrid multi-stage learning technique based on brain storming optimization algorithm for breast cancer recurrence prediction. Journal of King Saud University - Computer and Information Sciences. doi: 10.1016/j.jksuci.2021.05.004.
Bellman, R.(1957). Dynamic Programming.Princeton University Press.
Blum, A.L. & Langley, P.(1997).Selection of relevant features and examples in machine learning. Artif Artificial Intelligence, 97 (1–2), pp. 245-271.
Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.(2002). SMOTE: Synthetic Minority Over-sampling Technique, Journal Of Artificial Intelligence Research, Volume 16, pages 321-357, 2002.
Cheng, T., Junkai, J., Yajiao, T., Shangce, G., Zheng, T. & Yuki, T.(2020).A novel machine learning technique for computer-aided diagnosis. Engineering Applications of Artificial Intelligence. 92. doi:10.1016/j.engappai.2020.103627.
Hawkins, D. (1980). Identification of Outliers, Chapman and Hall, London.
Hollis KF(2016). To share or not to share: ethical acquisition and use of medical data. AMIA Jt Summits Transl Sci Proc 2016;2016:420–7.
Hartono, P.(2018). A transparent cancer classifier, Health Informatics J. 2020 Mar;26(1):190-204, doi: 10.1177/1460458218817800
Huang, C., Huang, X., Fang, Y., Xu, J., Qu, Y. , Zhai, P., Fan, L., Yin, H., Xu, Y. & Li, J.(2020).Sample imbalance disease classification model based on association rule feature selection. Pattern Recognition Letters, 133, 280-286. doi: 10.1016/j.patrec.2020.03.016.
Li, G. & Jason J.Jung(2021). Dynamic relationship identification for abnormality detection on financial time series. Pattern Recognition Letters, 145, 194-199.
Mushtaq, Z., Yaqub, A., Sani, S. & Khalid, A.(2019).Effective K-nearest neighbor classifications for Wisconsin breast cancer data sets. Electrical Engineering, 43, 80-92. doi: 10.1080/02533839.2019.1676658.
Newaz, A., Ahmed, N. & Shahriyar Haq, F.(2021).Survival prediction of heart failure patients using machine learning techniques. Informatics in Medicine Unlocked, 26. doi: 10.1016/j.imu.2021.100772.
Pai, H.-T, Wu, F. & P.-Y. S. Hsueh(2014).A Relative Patterns Discovery for Enhancing Outlier Detection in Categorical Data. Decision Support Systems, 67. doi:10.1016/j.dss.2014.08.006.
Pai, H.-T & Hsu, C.-C (2021). Explainable analytics: Understanding causes, correcting errors, and increasingly achieving perfect accuracy from nature of distinguishable patterns, Research Square, doi: 10.21203/rs.3.rs-1130288/v1.
Pashley, G.L., Kahn, M.B., Williams, G., Mentiplay, B.F., Banky, M. & Clark R.A.(2021). Assessment of upper limb abnormalities using the Kinect: Reliability, validity and detection accuracy in people living with acquired brain injury. Journal of Biomechanics, 129. doi: 10.1016/j.jbiomech.2021.110825.
Richard, A., Mayag, B., Talbot, F., Tsoukias, A. & Meinard, Y(2020). Transparency of Classification Systems for Clinical Decision Support, Information Processing and Management of Uncertainty in Knowledge-Based Systems, 1239: 99–113, doi: 10.1007/978-3-030-50153-2_8
Sreejith, S., Khanna Nehemiah, H. & Kannan, A.(2020).Clinical data classification using an enhanced SMOTE and chaotic evolutionary feature selection. Computers in Biology and Medicine, 126. doi: 10.1016/j.compbiomed.2020.103991.
Tawfik, D.S., Profit, J., Morgenthaler, T.I., Satele, D.V. , Sinsky, C.A., Dyrbye, L.N., Tutty, M.A., West, C.P., Shanafelt, T.D.(2018).Physician Burnout, Well-being, and Work Unit Safety Grades in Relationship to Reported Medical Errors. Mayo Clin Proc, 93(11), 1571-1580. doi: 10.1016/j.mayocp.2018.05.014
Wang, Y. C. & Cheng, C. H.(2021).A multiple combined method for rebalancing medical data with class imbalances. Computers in Biology and Medicine, 134. doi: 10.1016/j.compbiomed.2021.104527.
Yadav, C, Wang, S., Kumar, M.(2013). Algorithm and approaches to handle large Data- A Survey. International Journal of computer science and network, 2(3).
中華民國統計資訊網(2020)。醫療與其他醫事機構執業醫事人員數及每萬人口執業醫事人員數-年。取自: https://statdb.dgbas.gov.tw/pxweb/Dialog/statfile9L.asp。最後瀏覽日期: 2021/12/13。
中華民國醫師公會全國聯合會(2021)。從住院醫師適用勞基法談醫師合理工時。臺灣醫界，64卷2期， P34 – 41。