跳到主要內容

臺灣博碩士論文加值系統

(44.200.194.255) 您好!臺灣時間:2024/07/24 06:29
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:徐睿朋
研究生(外文):HSU, JUI-PENG
論文名稱:應用機器學習演算法於失智症量表數據以預測失智症
論文名稱(外文):Applying Machine Learning Algorithms to Dementia Scale Data to Predict Dementia
指導教授:陳宏銘陳宏銘引用關係
指導教授(外文):CHEN, HONG-MING
口試委員:邱百誼黃皇男陳宏銘
口試委員(外文):CHIU, PAI-YIHUANG, HUANG-NANCHEN, HONG-MING
口試日期:2022-01-21
學位類別:碩士
校院名稱:東海大學
系所名稱:應用數學系
學門:數學及統計學門
學類:數學學類
論文種類:學術論文
論文出版年:2022
畢業學年度:110
語文別:中文
論文頁數:113
中文關鍵詞:失智症邏輯斯迴歸隨機森林旋轉森林XGBoost
外文關鍵詞:DementiaLogistic regressionRandom forestRotation forestXGBoost
相關次數:
  • 被引用被引用:2
  • 點閱點閱:480
  • 評分評分:
  • 下載下載:124
  • 收藏至我的研究室書目清單書目收藏:0
本論文透過失智症資料建立預測模型,使用的資料為臨床失智症量表與認知功能評估問卷結果,應用機器學習演算法,包括邏輯斯迴歸、決策樹與隨機森林、旋轉森林、核旋轉森林、XGBoost 演算法建立預測模型,比較各演算法模型的準確度與靈敏度,診斷結果分為兩個面向,根據醫師改良的臨床失智症量表 (Clinical Dementia Rating, CDR),將診斷結果分成正常、輕度認知障礙、失智三類 (Group 3),以及正常、輕度認知障礙、輕度失智、中度失智、重度失智五類 (Group 5) 兩種,再根據 4162 位受試者於此量表的作答情況,對應其診斷結果訓練模型,並且透過重要度分析篩選相對重要的題目。其中旋轉森林與 XGBoost 的模型在預測受試者對應 Group 3 與 Group 5 時,準確度都分別達到約 0.94 與 0.9 相對優異。透過重要度分析從 50 道題目中選出 5 題再訓練模型,兩種方法對應 Group 3 與 Group 5 時準確度都分別達到約 0.88 與 0.74。
在資料(二)認知功能評估問卷結果使用,根據 17474 位受試者的性別、年紀、教育程度,以及其認知功能障礙篩檢量表 (Cognitive Abilities Screening Instrument, CASI)、簡易心智量表 (Mini Mental State Examination, MMSE)、蒙特利爾認知評估 (Montreal Cognitive Assessment, MoCA) 三種量表中其中一種的總分,對應其診斷結果 Group 3,分為三個部分,第一部分失智症全年齡分析,第二部分按照年紀的分群與第三部分認知功能異的模型建立與分析資料的準確度與靈敏度,第一部分準確度最高為 隨機森林 0.743,第二部分準確度最高為 76 歲以上的分群最高達到 0.809,第三部分認知功能異常分群準確度最高為 0.877,這樣的結果在過去失智症診斷準確度比較有相對優異的進步。
This thesis builds a predictive model based on dementia data. The data used are the results of the Clinical Dementia Rating and Cognitive Function Assessment Interview. Machine learning algorithms are applied, including logistic regression, decision tree and random forest, rotation forest, kernel rotation forest and XGBoost algorithms establish prediction models, compare the accuracy and sensitivity of each algorithm model, and the diagnosis results are divided into two aspects. According to the physician's modified Clinical Dementia Rating (CDR), the diagnosis results are divided into Three categories of normal, mild cognitive impairment, and dementia (Group 3), and two categories of normal, mild cognitive impairment, mild dementia, moderate dementia, and severe dementia (Group 5), according to 4162 respondents. The subjects' responses to this scale were trained on the model corresponding to their diagnostic results, and relatively important questions were screened through importance analysis. Among them, the models of Rotation Forest and XGBoost have relatively excellent accuracies of about 0.94 and 0.9 respectively when predicting that the subjects correspond to Group 3 and Group 5. Through importance analysis, 5 questions were selected from the 50 questions to retrain the model. When the two methods corresponded to Group 3 and Group 5, the accuracy reached about 0.88 and 0.74, respectively.
In the data (2) Cognitive Function Assessment Interview results are used, according to the gender, age, education level of 17,474 subjects, as well as their Cognitive Abilities Screening Instrument (CASI), Mini–Mental State Examination (MMSE), Montreal Cognitive Assessment (MoCA). The total score of one of the three scales, corresponding to its diagnosis result Group 3, is divided into three parts, the first part is an analysis of all ages of dementia, the third The second part is grouped by age and the third part is the accuracy and sensitivity of model building and analysis of different cognitive functions. The first, second and third part has the highest accuracy of 0.743 for random forests, 0.809 for groups over 76 years old and 0.877, such a result has relatively excellent progress.
摘要 3
目錄 5
第一章緒論 8
1.1 研究背景 8
1.2 研究動機與目的 9
1.3 論文架構 9
第二章名詞介紹與文獻回顧 11
2.1 輕度認知障礙 11
2.2 失智症 11
2.3 失智症量表 13
2.4 機器學習跨領域應用 14
第三章研究方法 16
3.1 邏輯斯迴歸 16
3.1.1 正則化 20
3.1.2 多元邏輯斯迴歸 20
3.2 決策樹 21
3.2.1 ID3演算法 22
3.2.2 C4.5演算法 26
3.2.3 剪枝 29
3.2.4 CART演算法 32
3.3 隨機森林 34
3.3.1 自助抽樣法 34
3.3.2 隨機森林演算法 35
3.3.3 重要度分析 36
3.4 旋轉森林 37
3.4.1 主成分分析 37
3.4.2 核技巧 39
3.4.3 核主成分分析 42
3.4.4 旋轉森林演算法 44
3.4.5 核旋轉森林演算法 45
3.5 XGBoos 45
3.6 混淆矩陣 48
3.7 k折交叉驗證法 50
第四章實驗結果—臨床失智症量表 52
4.1 資料描述 52
4.2 邏輯斯迴歸之分析 56
4.3 隨機森林之分析 57
4.4 旋轉森林之分析 61
4.5 核旋轉森林之分析 64
4.6 XGBoost之分析 66
4.7 機器學習方法比較 71
第五章實驗結果—認知功能評估問卷 76
5.1 資料(二)資料描述 76
5.2 第一部分失智症全年齡分析 79
5.2.1 CASI失智症全年齡分析 79
5.2.2 MMSE失智症全年齡分析 81
5.2.3 MoCA失智症全年齡分析 82
5.3 第二部分-按照年紀的分群 84
5.3.1 邏輯斯迴歸之CASI分析 85
5.3.2 邏輯斯迴歸之MMSE分析 85
5.3.3 邏輯斯迴歸之MoCA分析 87
5.3.4 隨機森林之CASI 分析 87
5.3.5 隨機森林之MMSE 分析 89
5.3.6 隨機森林之MoCA 分析 91
5.3.7 XGBoost之 CASI 分析 92
5.3.8 XGBoost之 MMSE 分析 94
5.3.9 XGBoost之 MoCA 分析 95
5.3.10 機器學習方法比較 97
5.4 第三部分 認知功能異常 (Cognitive Impairment (CI)) 99
第六章 結論與未來展望 105
參考文獻 113
[1] 張盛彥 (2017)。〈利用決策量表的機器學習進行老年失智症之分類研究〉。東海大學應用數學系碩士論文.
[2] 杜歆楷 (2019)。〈藉由機器學習探究失智症分群的非平衡數據問題〉。東海大學應用數學系碩士論文.
[3] 李航 (2012)。《統計學習方法》。北京: 清華大學出版社.
[4] 楊凱、侯艷、李康 (2015)。〈隨機森林變量重要性評分及其研究進展〉。哈爾 濱醫科大學公共衛生學院.
[5] 陳順宇 (2005)。《多變量分析》。台北: 華泰書局.
[6] 內政部統計通報 109 年第 10 週. (2021) 取自 https://www.moi.gov.tw/cp.aspx?n=10493.
[7] 國家發展委員會. (2021) 取自 https://www.ndc.gov.tw.
[8] 社團法人台灣失智症協會. (2021) 取自 http://www.tada2002.org.tw.
[9] 老人失智症的用藥安全. (2021) 取自 https://tpech.gov.taipei/News_Content.aspx?n=E64A67F6FCE63AEC&s=F76A570894D33B6A.
[10] 衛生福利部. (2021) 取自 https://www.mohw.gov.tw/mp-1.html.

[11] L’hˆopital’s rule. (2021) 取自 https://www.mathsisfun.com/calculus/l-hopitals-rule.html.
[12] Medlineplus [internet]. Bethesda (MD): National Library of Medicine (US); Mild Cognitive Impairment; [updated 2018 Oct 22; viewed 2021 Nov 25; cited 2022 Jan 5]; Available from: https://medlineplus.gov/mildcognitiveimpairment.html.
[13] Medlineplus [internet]. Bethesda (MD): National Library of Medicine (US); Dementia; [updated 2021 Jun 26; viewed 2021 Nov 25; cited 2022 Jan 5]; Available from: https://medlineplus.gov/dementia.html.
[14] Deepika Bansal, Rita Chhikara, Kavita Khanna, and Poonam Gupta. Comparative analysis of various machine learning algorithms for detecting dementia. Procedia computer science, 132:1497–1502, 2018.
[15] Gopi Battineni, Nalini Chintalapudi, and Francesco Amenta. Machine learning in medicine: Performance calculation of dementia prediction by support vector machines (svm). Informatics in Medicine Unlocked, 16:100200, 2019.
[16] Leo Breiman. Bagging predictors. Machine learning, 24(2):123–140, 1996.
[17] Leo Breiman. Random forests. Machine learning, 45(1):5–32, 2001.
[18] Leo Breiman, Jerome H Friedman, Richard A Olshen, and Charles J Stone. Clas- sification and regression trees. Routledge, 2017.
[19] Tianqi Chen and Carlos Guestrin. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discov- ery and data mining, pages 785–794, 2016.
[20] Pai-Yi Chiu, Haipeng Tang, Cheng-Yu Wei, Chaoyang Zhang, Guang-Uei Hung, and Weihua Zhou. Nmd-12: A new machine-learning derived screening instrument to detect mild cognitive impairment and dementia. PloS one, 14(3):e0213430, 2019.
[21] Joseph R Cockrell and Marshal F Folstein. Mini-mental state examination. Prin- ciples and practice of geriatric psychiatry, pages 140–141, 2002.
[22] Corinna Cortes and Vladimir Vapnik. Support-vector networks. Machine learning, 20(3):273–297, 1995.
[23] Rahul C Deo. Machine learning in medicine. Circulation, 132(20):1920–1930, 2015.
[24] Thomas J DiCiccio and Bradley Efron. Bootstrap confidence intervals. Statistical science, 11(3):189–228, 1996.
[25] Meherwar Fatima, Maruf Pasha, et al. Survey of machine learning algorithms for disease diagnostic. Journal of Intelligent Learning Systems and Applications, 9(01):1, 2017.
[26] Nir Friedman, Dan Geiger, and Moises Goldszmidt. Bayesian network classifiers. Machine learning, 29(2):131–163, 1997.
[27] Michel Goedert and Maria Grazia Spillantini. A century of alzheimer’s disease. science, 314(5800):777–781, 2006.
[28] Chloe Gui and Victoria Chan. Machine learning in medicine. University of Western Ontario Medical Journal, 86(2):76–78, 2017.
[29] Hasmet A Hanagasi, Zeynep Tufekcioglu, and Murat Emre. Dementia in parkin- son’s disease. Journal of the neurological sciences, 374:26–31, 2017.
[30] Tin Kam Ho. Random decision forests. In Proceedings of 3rd international con- ference on document analysis and recognition, volume 1, pages 278–282. IEEE, 1995.
[31] S Hoops, S Nazem, AD Siderowf, JE Duda, SX Xie, MB Stern, and D Weintraub. Validity of the moca and mmse in the detection of mci and dementia in parkinson disease. Neurology, 73(21):1738–1745, 2009.
[32] David W Hosmer Jr, Stanley Lemeshow, and Rodney X Sturdivant. Applied logistic regression, volume 398. John Wiley & Sons, 2013.
[33] Costantino Iadecola. The pathobiology of vascular dementia. Neuron, 80(4):844– 866, 2013.
[34] M Powell Lawton and Elaine M Brody. Assessment of older people: self- maintaining and instrumental activities of daily living. The gerontologist, 9(3 Part 1):179–186, 1969.
[35] J Lehrner, R Kalchmayr, W Serles, A Olbrich, E Pataraia, S Aull, J Bacher, F Leutmezer, G Gro ̈ppel, L Deecke, et al. Health-related quality of life (hrqol), activity of daily living (adl) and depressive mood disorder in temporal lobe epilepsy patients. Seizure, 8(2):88–92, 1999.
[36] Huijuan Lu, Yaqiong Meng, Ke Yan, and Zhigang Gao. Kernel principal component analysis combining rotation forest method for linearly inseparable data. Cognitive Systems Research, 53:111–122, 2019.
[37] Ian McKeith. Dementia with lewy bodies. Handbook of clinical Neurology, 84:531– 548, 2007.
[38] James Mercer. Xvi. functions of positive and negative type, and their connection the theory of integral equations. Philosophical transactions of the royal society of London. Series A, containing papers of a mathematical or physical character, 209(441-458):415–446, 1909.
[39] Douglas C Montgomery, Elizabeth A Peck, and G Geoffrey Vining. Introduction to linear regression analysis. John Wiley & Sons, 2021.
[40] John C Morris. Clinical dementia rating: a reliable and valid diagnostic and staging measure for dementia of the alzheimer type. International psychogeriatrics, 9(S1):173–176, 1997.
[41] John C Morris, Albert Heyman, Richard C Mohs, JP Hughes, Gerald van Belle, GDME Fillenbaum, ED Mellits, and C Clark. The consortium to establish a reg- istry for alzheimer’s disease (cerad): I. clinical and neuropsychological assessment of alzheimer’s disease. Neurology, 1989.
[42] David Neary, Julie Snowden, and David Mann. Frontotemporal dementia. The Lancet Neurology, 4(11):771–780, 2005.
[43] Karl Pearson. Liii. on lines and planes of closest fit to systems of points in space.
The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Sci- ence, 2(11):559–572, 1901.
[44] Ronald C Petersen, Glenn E Smith, Stephen C Waring, Robert J Ivnik, Eric G Tangalos, and Emre Kokmen. Mild cognitive impairment: clinical characterization and outcome. Archives of neurology, 56(3):303–308, 1999.
[45] Eric Pfeiffer. A short portable mental status questionnaire for the assessment of organic brain deficit in elderly patients. Journal of the American Geriatrics Society, 23(10):433–441, 1975.
[46] Alvin Rajkomar, Jeffrey Dean, and Isaac Kohane. Machine learning in medicine. New England Journal of Medicine, 380(14):1347–1358, 2019.
[47] Irina Rish. An empirical study of the naive bayes classifier. In IJCAI 2001 workshop on empirical methods in artificial intelligence, volume 3, pages 41–46. IBM New York, 2001.
[48] Juan Jos ́e Rodriguez, Ludmila I Kuncheva, and Carlos J Alonso. Rotation forest: A new classifier ensemble method. IEEE transactions on pattern analysis and machine intelligence, 28(10):1619–1630, 2006.
[49] Frank Rosenblatt. Principles of neurodynamics. perceptrons and the theory of brain mechanisms. Technical report, Cornell Aeronautical Lab Inc Buffalo NY, 1961.
[50] Bernhard Scho ̈lkopf, Alexander Smola, and Klaus-Robert Mu ̈ller. Kernel princi- pal component analysis. In International conference on artificial neural networks, pages 583–588. Springer, 1997.
[51] Walter J Schulz-Schaeffer. The synaptic pathology of α-synuclein aggregation in dementia with lewy bodies, parkinson’s disease and parkinson’s disease dementia. Acta neuropathologica, 120(2):131–143, 2010.
[52] J. Shim, S. Kang, and S. Cho. Kernel rotation forests for classification. In 2020 IEEE International Conference on Big Data and Smart Computing (BigComp), pages 406–409, 2020.
[53] Jenni AM Sidey-Gibbons and Chris J Sidey-Gibbons. Machine learning in medicine: a practical introduction. BMC medical research methodology, 19(1):1–18, 2019.
[54] Aram So, Danial Hooshyar, Kun Woo Park, and Heui Seok Lim. Early diagnosis of dementia from clinical data by machine learning techniques. Applied Sciences, 7(7):651, 2017.
[55] Yan-Yan Song and LU Ying. Decision tree methods: applications for classification and prediction. Shanghai archives of psychiatry, 27(2):130, 2015.
[56] Evelyn L Teng, Kazuo Hasegawa, Akira Homma, Yukimuchi Imai, Eric Larson, Amy Graves, Keiko Sugimoto, Takenori Yamaguchi, Hideo Sasaki, Darryl Chiu, et al. The cognitive abilities screening instrument (casi): a practical test for cross-cultural epidemiological studies of dementia. International psychogeriatrics, 6(1):45–58, 1994.
[57] Jussi Tohka, Elaheh Moradi, and Heikki Huttunen. Comparison of feature selection techniques in machine learning for anatomical brain mri in dementia. Neuroinfor- matics, 14(3):279–296, 2016.
[58] Svante Wold, Kim Esbensen, and Paul Geladi. Principal component analysis. Chemometrics and intelligent laboratory systems, 2(1-3):37–52, 1987.
[59] Fubao Zhu, Xiaonan Li, Daniel Mcgonigle, Haipeng Tang, Zhuo He, Chaoyang Zhang, Guang-Uei Hung, Pai-Yi Chiu, and Weihua Zhou. Analyze informant- based questionnaire for the early diagnosis of senile dementia using deep learning. IEEE Journal of Translational Engineering in Health and Medicine, 8:1–6, 2019.
[60] Fubao Zhu, Xiaonan Li, Haipeng Tang, Zhuo He, Chaoyang Zhang, Guang-Uei Hung, Pai-Yi Chiu, and Weihua Zhou. Machine learning for the preliminary diag- nosis of dementia. Scientific Programming, 2020, 2020.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊