跳到主要內容

臺灣博碩士論文加值系統

(44.222.189.51) 您好!臺灣時間:2024/05/18 17:04
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

: 
twitterline
研究生:陳彥勝
研究生(外文):CHEN,YEN-SHENG
論文名稱:運用資料探勘技術於腰椎管狹窄保守治療之成效預測
論文名稱(外文):Using Data Mining Technology to Predict the Results of Conservative Therapy for Lumbar Spinal Stenosis
指導教授:侯東旭侯東旭引用關係
指導教授(外文):HOU,TUNG-HSU
口試委員:侯東旭駱景堯劉書助
口試委員(外文):HOU, TUNG-HSULOW, CHIN-YAOLIU, SHU-CHU
口試日期:2017-06-26
學位類別:碩士
校院名稱:國立雲林科技大學
系所名稱:工業工程與管理系
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:2017
畢業學年度:105
語文別:中文
論文頁數:103
中文關鍵詞:腰椎管狹窄保守治療資料探勘倒傳遞類神經網路決策樹支持向量機預測
外文關鍵詞:Lumbar spinal stenosisData miningBack Propagation neural networkDecision treeSupport Vector MachinePrediction
相關次數:
  • 被引用被引用:2
  • 點閱點閱:215
  • 評分評分:
  • 下載下載:15
  • 收藏至我的研究室書目清單書目收藏:0
目前對於診斷出患有腰椎管狹窄症的患者,採取的治療方法有保守治療與手術治療。由於手術治療屬於侵入性的治療,因此患者通常會以保守治療為優先選擇。但每位腰椎管狹窄患者在保守治療的成效有所不同,然而其中可能造成保守治療成效不同最後還是進行開刀的原因或者規則是值得去探討的議題。另一方面則是在沒有一個可以確定腰椎管狹窄保守治療患者最後是否開刀的診斷系統之下,醫療專業人員也不容易做出最佳的診斷提供予患者。為了解決以上的問題,本研究將對腰椎管狹窄患者進行病歷資料與MRI影像診斷資料收集,透過資料探勘技術,將全部資料進行分析與彙整,找尋影響腰椎管狹窄保守治療患者最後是否開刀之重要因子與規則,並建立出ㄧ個有效的腰椎管狹窄保守治療患者最後是否開刀之預測模型。
研究結果顯示使用了綜合羅吉斯回歸與決策樹特徵選取配合C5.0決策樹後,得到了重要的特徵為分別為:椎間盤高度降低、年齡、血壓差、骨骼骨頭痛、性別等。在腰椎管狹窄保守治療患者最後是否開刀的預測模型中,以綜合羅吉斯回歸與決策樹倒傳遞類神經網路之預測測試正確率為94.87%、靈敏度為0.9、特異度為1、AUC為0.952。透過以上資料探勘技術對於腰椎管狹窄保守治療患者最後是否開刀,提供醫療專業人員在診斷上有更多的參考,進而給予腰椎管狹窄患者治療建議,避免導致病情更加嚴重。相信對於醫療服務品質會有所提升,減少醫療上不必要的浪費。

Conservative treatment and surgical treatment methods are usually used for the patients of lumbar spinal stenosis. Surgical treatment is an invasive treatment for lumbar spinal stenosis patients, so patients usually choose conservative treatment. But there are different results of conservative therapy for lumbar spinal stenosis. The reasons or rules of different results of conservative therapy for lumbar spinal stenosis are a worthy of study problem for the medical profession. Unfortunately, there has not a system used to predict the results of conservative therapy for lumbar spinal stenosis by now, so medical professionals are not easy to make the best diagnosis for patients.
In order to solve this problem, this study uses medical records and MRI imaging data of lumbar spinal stenosis and uses data mining technology to find the key factors and rules of treatment results of conservative treatment and to establish a predictive model for predicting the results of conservative treatment for lumbar spinal stenosis.
The result indicates that is combined with the logistic regression and decision tree feature selection method enhance C5.0 decision tree, and the important factors were as follows: disc height reduction, age, diastolic blood pressure, bone pain and gender. In the predictive model for predicting the results of conservative treatment for lumbar spinal stenosis, the best model is logistic regression and decision tree feature selection method combined with Back Propagation neural network model, and the accuracy reaches 94.87%, the sensitivity reaches 0.9; the specificity reaches 1; and AUC reaches 0.952.

摘要 ...i
ABSTRACT ...ii
誌謝 ...iii
目錄 ...iv
表目錄 ...vii
圖目錄 ...x
第一章 緒論 ...1
1.1研究背景與動機 ...1
1.2研究目的 ...3
1.3研究範圍與限制 ...4
1.4研究流程 ...4
第二章 文獻探討 ...6
2.1腰椎管狹窄 ...6
2.1.1腰椎管狹窄治療 ...7
2.2.2資料探勘技術應用於腰椎管狹窄 ...9
2.2類神經網路理論與醫療應用 ...10
2.2.1類神經網路的基本結構 ...11
2.2.2倒傳遞類神經網路 ...15
2.2.3倒傳遞類神經網路應用於醫療 ...17
2.3決策樹理論與醫療應用 ...17
2.3.1決策樹應用於醫療 ...21
2.4羅吉斯回歸理論與醫療應用 ...22
2.4.1羅吉斯回歸應用於醫療 ...23
2.5支持向量機理論與醫療應用 ...24
2.5.1支持向量機應用於醫療 ...27
2.6類別資料不平衡問題 ...28
2.6.1 解決類別資料不平衡方法 ...29
第三章 研究方法 ...31
3.1研究步驟與架構 ...31
3.2資料收集 ...33
3.3資料前置處理 ...35
3.4腰椎管狹窄保守治療患者最後是否進行開刀之資料平衡處理 ...36
3.5腰椎管狹窄保守治療患者最後是否進行開刀之特徵選取 ...36
3.6倒傳遞類神經網路模型建立參數設定 ...37
3.7 C5.0決策樹模型建立與參數設定 ...39
3.8支持向量機模型建立與參數設定 ...40
3.9模型績效評估 ...41
第四章 實驗結果與分析 ...44
4.1腰椎管狹窄資料處理 ...44
4.2類別資料平衡 ...46
4.3特徵選取 ...47
4.4 C5.0決策樹預測與規則模型 ...52
4.4.1原始資料類別不平衡狀態C5.0決策樹預測模型 ...53
4.4.2資料類別平衡狀態C5.0決策樹預測模型 ...54
4.4.3資料類別平衡狀態C5.0決策樹規則模型 ...56
4.4.4 C5.0決策樹模型績效比較 ...59
4.5 倒傳遞類神經網路預測模型 ...62
4.5.1倒傳遞類神經網路模型績效比較 ...69
4.6 支持向量機預測模型 ...70
4.6.1支持向量機模型績效比較 ...78
4.7各種模型績效比較 ...79
第五章 結論與建議 ...83
5.1結論 ...83
5.2建議 ...84
參考文獻 ...85


中文文獻
1.李文雄(2016)。以資料探勘技術探討顱內動脈及顱外動脈狹窄的相關因子之研究。國立中正大學資訊管理系醫療資訊管理研究所,碩士學位論文。
2.江昭龍(2015)。醫療檢驗數據之腎臟疾病鑑別。資訊科技國際期刊,9 (2),頁43-49。
3.周亭余(2014)。乳癌預測模型之探討。成功大學醫學資訊研究所,碩士學位論文。
4.邱世全(2010)。應用人工智慧判斷新生兒患病理性黃疸輔助鑑別診斷之研究。虎尾科技大學工業工程與管理研究所,碩士學位論文。
5.陳銘樹、王建智、王麗雁(2008)。應用決策樹演算法以探究高科技員工潛在的糖尿病之危險因子。健康管理學刊,6(2),頁135-146。
6.許敦韋、凌憬峰、郭萬祐。核磁共振影像在良性和惡性腦腫瘤之自動偵測與分類上的應用。北市醫放雜誌,6(1),頁37-44。
7.楊正三、葉明龍、莊麗月、陳禹融、楊正宏(2008)。利用資訊增益與瀰集演算法於基因微陣列之特徵選取與分類問題。資訊科技國際期刊,2 (2),頁50-62。
8.蔡孟潔(2005)。應用邏輯斯迴歸於冠狀動脈心臟病之研究。元智大學工業工程與管理學系,碩士學位論文。
9.廖俊傑、林文燦(2013)。應用資料探勘於癌症醫療費用之解析。國立勤益科技大學工業工程與管理系研究所,碩士學位論文。
10.張哉炯、施國強、溫榮彬、葉漢深(2001)。老年腰椎間盤突出症的特點及手術方法。中國矯型外科雜誌,8(1),頁28-29。
11.張語恬、朱基銘、簡戊鑑、周雨青、楊燦、羅慶徽 (2007)。比較三種資料探勘演算法預測子宮頸癌五年存活的外部通用性效能。台灣家庭醫學雜誌,17(4),頁222-238.
12.張琪、周琳、陳亮、張晉昕、溫興煊、何賢英(2015)。決策樹模型用於结核病治療方案的分類和預判。中華疾病控制雜誌,19(5),頁510-513。
13.陳渝新(2007)。黄韌帶增生肥厚致腰椎管狹窄的MRI表現。重慶醫學,36(12),頁1181-1182。
14.陳隆昇、林立為(2009)。植基倒傳遞類神經網路之不平衡資料處理機制。TAAI 2009 第十四屆人工智慧與應用研討會,台中,台灣。
15.陳佳怡(2013)。利用資料採礦技術於巴金森氏症之微陣列基因篩選。輔仁大學統計資訊學系應用統計所,碩士學位論文。
16.葉楓、饒飄雪(2016)。基于Logistic回歸、ANN、SVM的乳腺癌復發影響因素研究。計算機系統應用,25(7),頁259-263。
17.簡維隆、楊燕珠(2012)。以資料探勘技術預測老人跌倒之風險。大同大學資訊經營研究所,碩士學位論文。
18.簡禎富、許嘉裕(2014)。資料挖礦與大數據分析。新北市:前程文化。
19.羅嘯、黄異飛(2015)。腰椎管狹窄症的診斷與治療現況。新疆醫學,10,頁1527-1529。


英文文獻
1.Amundsen, T., Weber, H., Nordal, H. J., Magnaes, B., Abdelnoor, M., & Lilleås, F. (2000). Lumbar spinal stenosis: conservative or surgical management?: A prospective 10-year study. Spine, 25(11), 1424-1436.
2.Azimi, P., Benzel, E., Shahzadi, S., Azhari, S., & Mohammadi, H. R. (2014). Prediction of Surgical Satisfaction in Patients with Lumbar Spinal Canal Stenosis Using Artificial Neural Networks. Journal of Research in Medical Sciences.
3.Azimi, P., Benzel, E. C., Shahzadi, S., Azhari, S., & Mohammadi, H. R. (2014). Use of artificial neural networks to predict surgical satisfaction in patients with lumbar spinal canal stenosis: clinical article. Journal of Neurosurgery: Spine, 20(3), 300-305.
4.Bradley, A. P. (1997). The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern recognition, 30(7), 1145-1159.
5.Batista, G. E., Prati, R. C., & Monard, M. C. (2004). A study of the behavior of several methods for balancing machine learning training data. ACM Sigkdd Explorations Newsletter, 6(1), 20-29.
6.Backstrom, K. M., Whitman, J. M., & Flynn, T. W. (2011). Lumbar spinal stenosis-diagnosis and management of the aging spine. Manual therapy, 16(4), 308-317.
7.Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16, 321-357.
8.Chang, F., Chang, L. C., & Huang, H. L. (2002a). Real‐time recurrent learning neural network for stream‐flow forecasting. Hydrological Processes, 16(13), 2577-2588.
9.Chang, F. J. and Chen, Y. C. (2003b). Estuary water-stage forecasting by using radial basis function neural network. Journal of Hydrology, 270(1), 158-166.
10.Chang, Y., Singer, D. E., Wu, Y. A., Keller, R. B., & Atlas, S. J. (2005). The effect of surgical and nonsurgical treatment on longitudinal outcomes of lumbar spinal stenosis over 10 years. Journal of the American Geriatrics Society, 53(5), 785-792.
11.Friedman, J., Hastie, T., & Tibshirani, R. (2001). The elements of statistical learning (Vol. 1): Springer series in statistics Springer, Berlin.
12.Fritz, J. M., Cleland, J. A., & Childs, J. D. (2007). Subgrouping patients with low back pain: evolution of a classification approach to physical therapy. journal of orthopaedic & sports physical therapy, 37(6), 290-302.
13.Fernández, A., del Jesus, M. J., & Herrera, F. (2009). On the influence of an adaptive inference system in fuzzy rule based classification systems for imbalanced data-sets. Expert Systems with Applications, 36(6), 9805-9812.
14.Group, P. R. (1986). Parallel distributed processing: Explorations in the microstructure of cognition: Vol. 1. Foundations. Cambridge, MA: MIT Press.
15.Han, J. and Kamber, M. (2006). Data Mining: Concepts and Techniques, 2nd editionMorgan Kaufmann Publishers. San Francisco, CA, USA.
16.Hotelling, H. (1933). Analysis of a complex of statistical variables into principal components. Journal of educational psychology, 24(6), 417.
17.Huang, M.-L. and Chen, H.-Y. (2005). Development and comparison of automated classifiers for glaucoma diagnosis using Stratus optical coherence tomography. Investigative ophthalmology & visual science, 46(11), 4121-4129.
18.Idler, C., Zucherman, J. F., Yerby, S., Hsu, K. Y., Hannibal, M., & Kondrashov, D. (2008). A novel technique of intra-spinous process injection of PMMA to augment the strength of an inter-spinous process device such as the X STOP. Spine, 33(4), 452-456.
19.Kubat, M. and Matwin, S. (1997). Addressing the curse of imbalanced training sets: one-sided selection. In ICML (Vol. 97, pp. 179-186).
20.Lewis, D. D. and Catlett, J. (1994). Heterogeneous uncertainty sampling for supervised learning. In Proceedings of the eleventh international conference on machine learning (pp. 148-156).
21.Lee, C. I., Tsai, C. J., Wu, T. Q., & Yang, W. P. (2008). An approach to mining the multi-relational imbalanced database. Expert Systems with Applications, 34(4), 3021-3032.
22.Lee, S., Lee, J. W., Yeom, J. S., Kim, K.-J., Kim, H.-J., Chung, S. K., & Kang, H. S. (2010). A practical MRI grading system for lumbar foraminal stenosis. American Journal of Roentgenology, 194(4), 1095-1098.
23.Linoff, G. S. and Berry, M. J. (2011). Data mining techniques: for marketing, sales, and customer relationship management: John Wiley & Sons.
24.Malfair, D. and Beall, D. P. (2007). Imaging the degenerative diseases of the lumbar spine. Magnetic resonance imaging clinics of North America, 15(2), 221-238.
25.Murphy, D. R., Hurwitz, E. L., Gregory, A. A., & Clary, R. (2006). A non-surgical approach to the management of lumbar spinal stenosis: a prospective observational cohort study. BMC Musculoskeletal Disorders, 7(1), 1.
26.Person, K. (1901). On Lines and Planes of Closest Fit to System of Points in Space. Philiosophical Magazine, 2, 559-572.
27.Padmaja, T. M., Dhulipalla, N., Bapi, R. S., & Krishna, P. R. (2007). Unbalanced data classification using extreme outlier elimination and sampling techniques for fraud detection. In International conference on machine learning and cybernetics on advanced computing and communications, 2007. ADCOM 2007. International Conference on 511-516.
28.Smola, A. J., & Schölkopf, B. (1998). Learning with kernels (p. 210). GMD-Forschungszentrum Informationstechnik
29.Simotas, A. C. (2001). Nonoperative treatment for lumbar spinal stenosis. Clinical orthopaedics and related research, 384, 153-161.
30.Spratt, K., Keller, T., Szpalski, M., Vandeputte, K., & Gunzburg, R. (2004). A predictive model for outcome after conservative decompression surgery for lumbar spinal stenosis. European Spine Journal, 13(1), 14-21.
31.Schwedt, T. J., Chong, C. D., Wu, T., Gaw, N., Fu, Y., & Li, J. (2015). Accurate classification of chronic migraine via brain magnetic resonance imaging. Headache: The Journal of Head and Face Pain, 55(6), 762-777.
32.Verbiest, H. (1954). A radicular syndrome from developmental narrowing of the lumbar vertebral canal. J Bone Joint Surg Br, 36-B(2), 230-237.
33.V. N. Vapnik.(1995). The Nature of Statistical Learning Theory, Springer-Verlag, NY, USA.
34.Villers, D. and Barnard, E. (1992). Back-propagation neural nets with one and two layers. IEEE Transactions on Neural Networks, 4(1), 136-141.
35.Vo, A. N., Kamen, L. B., Shih, V. C., Bitar, A. A., Stitik, T. P., & Kaplan, R. J. (2005). Rehabilitation of orthopedic and rheumatologic disorders. 5. Lumbar spinal stenosis. Archives of physical medicine and rehabilitation, 86, 69-76.
36.Weinstein, J. N., Tosteson, T. D., Lurie, J. D., Tosteson, A., Blood, E., Herkowitz, H., Hilibrand, A. (2010). Surgical versus non-operative treatment for lumbar spinal stenosis four-year results of the Spine Patient Outcomes Research Trial (SPORT). Spine, 35(14), 1329.
37.Whitman, J. M., Flynn, T. W., Childs, J. D., Wainner, R. S., Gill, H. E., Ryder, M. G., & Fritz, J. M. (2006). A comparison between two physical therapy treatment programs for patients with lumbar spinal stenosis: a randomized clinical trial. Spine, 31(22), 2541-2549.
38.Wilkens, P., Scheel, I. B., Grundnes, O., Hellum, C., & Storheim, K. (2013). Prognostic factors of prolonged disability in patients with chronic low back pain and lumbar degeneration in primary care: a cohort study. Spine, 38(1), 65-74.
39.Yeh, D.-Y., Cheng, C.-H., & Chen, Y.-W. (2011). A predictive model for cerebrovascular disease using data mining. Expert Systems with Applications, 38(7), 8970-8977.
40.Zaletnyik, P. (1999). Coordinate transformation with neural networks and with polynomials in Hungary. Geodézia és Kartográfia, 10,12-18.
41.Zucherman, J., Hsu, K., Hartjen, C., Mehalic, T., Implicito, D., Martin, M., Johnson, D., Skidmore, G., Vessa, P., Dwyer, W., Puccio, S., Cauthen, J., & Ozuna, R. (2004). A prospective randomized multi-center study for the treatment of lumbar spinal stenosis with the X STOP interspinous implant: 1-year results. European Spine Journal, 13(1), 22-31.
42.Zhang Ye., Zhang Han., Yin Bincan., & Zhao Yuhong. (2016). Building Disease Prediction Model Using Support Vector Machine-Case Study of Severe Acute Pancreatitis. New Technology of Library and Information Service, 32(2), 83-89.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top