運用資料探勘分析尿失禁患者居家復健及醫療過程於輔助醫生進行尿失禁治療

Using Data Mining Analysis Home Rehabilitation and Treatment on Urinary Incontinence Patients to Assist Physicians Treat Urinary Incontinence

賀立夫(Li-Fu Ho)

指導教授 ： 陳瑞發

淡江大學/工學院/資訊工程學系碩士班/碩士(2015年)

https://doi.org/10.6846/TKU.2015.00522

摘要

目前大多數醫師對尿失禁的診斷方式，以患者口頭描述的病情做為判斷病情嚴重性的依據，醫師根據經驗來判定該患者應採用藥物治療、手術治療或復健運動等治療方式。醫師目前使用的醫療系統缺少分析機制，在沒有使用儀器檢查的情況下，醫師診治時有可能忽略部分患者的隱藏因子，因而不容易做出最佳的診斷方式。
本研究將病患進行復健所蒐集的資料，整合現有的看診系統，使醫生對於病患的病症能夠提出更有效的治療方法。並利用資料探勘技術，將整個療程的詳細資料進行分析，並將分析後的資料彙整，利用平板的方式呈現。可利於醫師能夠在看診時即時查看分析後的資料，事後可利用此系統在看診過程中利用即時的分析結果對病患進行檢討與建議，適用於特殊族群或個案。透過以上分析模組推測患者的治療成效，利於醫師對於之後診療過程能夠對於整體分析的結果，對患者提出更佳的治療建議，也可讓醫師在檢視病患療程時，可以有更詳細的分析資料，提供醫師參考。

關鍵字

尿失禁 ； 世界衛生組織生活品質問卷 ； 資料探勘 ； 決策樹

並列摘要

Most physicians in the diagnosis of Urinary Incontinence, patients with oral disease severity as the basis for judgment. According to the experience of the physicians to determine the patient should be treated with medication, surgery or rehabilitation exercise. physicians used outpatient department lack of analysis information. In the absence of using instrument, when physicians in the medical treatment, there may have overlooked hidden factors and not easy to make the best diagnostic modality.
In this study, collecting the rehabilitation data of patients and integrating with existing outpatient department systems. Physicians can make more effective treatment with the patient's condition. Using the data mining technology to analysis the details of the entire treatment to aggregate the data and to present by mobile device.
Speculated that the effectiveness of treatment of patients through the above analysis modules, which will help physicians proposes better treatment recommendations to patients. It can provided more detailed analysis of data for references when physicians review patient treatment.

並列關鍵字

Urinary incontinence ； World Health Organization Quality of Life ； Data Mining ； Decision Tree

參考文獻

[1] 郭哲余 and 鄭勵君, "規律運動介入對應力型尿失禁婦女健康體適能影響之研究," 運動與健康研究, vol. 2, pp. 67-87, 2012.

[9] J. M. Keller, M. R. Gray, and J. A. Givens, "A fuzzy k-nearest neighbor algorithm," Systems, Man and Cybernetics, IEEE Transactions on, pp. 580-585, 1985.

[2] A. Silberschatz and A. Tuzhilin, "What makes patterns interesting in knowledge discovery systems," Knowledge and Data Engineering, IEEE Transactions on, vol. 8, pp. 970-974, 1996.

[3] V. Vapnik, The nature of statistical learning theory: Springer Science & Business Media, 2013.

[4] B. Archer, U. D. Annakkage, B. Jayasekara, and P. Wijetunge, "Accurate prediction of damping in large interconnected power systems with the aid of regression analysis," Power Systems, IEEE Transactions on, vol. 23, pp. 1170-1178, 2008.