跳到主要內容

臺灣博碩士論文加值系統

(34.204.180.223) 您好!臺灣時間:2021/08/05 23:53
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

我願授權國圖
: 
twitterline
研究生:傅俊閔
研究生(外文):Chun-Min Fu
論文名稱:傾向分數混合模式於校正遵從性偏差的應用
論文名稱(外文):Propensity score mixed model for correcting non-compliance bias
指導教授:陳秀熙陳秀熙引用關係
指導教授(外文):Hsiu-Hsi Chen
口試委員:簡國龍陳祈玲
口試委員(外文):Kuo-Liong ChienChi-Ling Chen
口試日期:2015-05-26
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:流行病學與預防醫學研究所
學門:醫藥衛生學門
學類:公共衛生學類
論文種類:學術論文
論文出版年:2015
畢業學年度:103
語文別:英文
論文頁數:62
中文關鍵詞:傾向分數平衡分數不遵從大腸癌篩檢傾向分數混和模式
外文關鍵詞:propensity scorebalancing scorenon-compliancecolorectal cancer screeningpropensity score mixed model
相關次數:
  • 被引用被引用:1
  • 點閱點閱:90
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
背景
  無論是在隨機分派試驗,或是觀察性研究,例如全人口的篩檢計畫要轉介陽性病患,常會遇到不遵從(non-compliance)的問題。常使用的立意治療分析(Intention-to-treat)在不遵從者的追蹤結果不完整的情況,可能就無法使用。考慮使用兩治療組的初始的共變數資訊,我們提出傾向分數(propensity score)方法來解決這個問題。傾向分數由Rosenbaum and Rubin提出後,儘管已被廣泛使用,但以強可忽略治療分派條件(SITA, strongly ignorable treatment assignment)為基礎的平衡分數(balancing score)相關於傾向分數的邏輯仍常難以理解。
目的及方法
  這篇研究的目的為 (1) 發展在SITA前提之下,使用平衡分數估計治療效果操作標準的邏輯推論。(2) 使用一個隨機分派試驗,我們呈現傾向分數混合模式如何能給予產生更細緻的平衡分數,以透過配對、分層、共變數分析,來評估治療效果。(3) 應用傾向分數混合模式於兩個隨機分派試驗,以及應用於全人口基礎的大腸癌篩檢計畫中,糞便潛血反應陽性的轉介,對於因大腸癌死亡的影響。
結果
  根據以SITA為前提使用平衡分數的推導,使用隨機分派試驗資料模擬,顯示傾向分數混合模式和傾向分數固定模式比起來,可以產生更接近真實治療效果的估計。傾向分數混合模式納入隨機效果(random effect),也對治療組的遵從者(complier)和控制組的潛在遵從者(potential noncomplier)之間的比較,能產生真實治療效果的不偏估計。當傾向分數固定模式使用在大腸癌篩檢轉介大腸鏡篩檢計畫時,遵從者(接受轉介者)相對於非遵從者(不接受轉介者),死亡率相對風險為0.60 (95%信賴區間0.49 ~ 0.74),和粗死亡率相對風險比起來,只有輕微下降,但若用傾向分數混合模式,可大幅下降至0.49 (95%信賴區間0.36 ~ 0.66)。
結論
  我們在SITA的假定之下,發展對於平衡分數操作的邏輯推論,並提供傾向分數分析的分析架構。接著我們提出傾向分數混合模式,讓平衡分數能夠儘量細緻,期能達到更準確的治療效果評估。傾向分數混和模式成功地應用在追蹤訊息不完整的非遵從問題,也應用在當兩治療組的基礎共變數有不平衡的情況。


Background
The non-compliance problem is often encountered not only in the randomized controlled trials (RCTs) but also in observational studies, such as population-based screening program for the referral of screen-positive participants. Intentional-to-treat method often used for solving this problem in the RCTs may not be possibly applied when the follow-up outcome among the non-compliers is not available. Propensity score method is therefore proposed as an alternative by making use of information on the imbalance of baseline covariates between the two groups. In spite of its usefulness, the logics for balancing score function in relation to propensity score function based on strongly ignorable treatment assignment (SITA) are still elusive since it was proposed by Rosenbaum and Rubin.
Objectives and methods
The objectives of this thesis were to (1) develop philosophical logics of operational criteria using the balancing score given SITA to approximately estimate the true treatment effect; (2) demonstrate how a new propensity score mixed effect model can render the balancing score finer following (1); to approximate the true treatment effect through matching, stratification, and covariance adjustment based on one randomized controlled trial; (3) apply the PS-mixed effect model to two randomized controlled trials and also the referral of FIT (fecal immunochemical test) positive participants in nationwide population-based colorectal cancer screening.
Results
Based on the development of philosophical logics of operational criteria using balancing score given SITA, the simulated results using the randomized controlled trial data showed the proposed propensity score mixed-effect (PS-mixed) model rendered the estimates of efficacy closer to true treatment effect compared with the fix-effect model. The application of this propensity score mixed-effect model with the incorporation of random-effect also gave an unbiased estimate of true treatment effect by comparing the outcome of compliers in the experimental group with that of potential compliers in the control group. While the propensity score fixed-effect model was applied to colorectal cancer screening program, the efficacy of colonoscopy (the compliers (referral) versus the non-compliers(non-referral)) gave an estimate of relative rate (RR) of the risk for death from CRC of 0.60 (95% Confidence interval: 0.49 ~ 0.74), only slightly different from the crude estimate of 0.64 (95% Confidence interval: 0.52 ~ 0.78), but substantially different from the adjusted estimate of 0.49 (95% Confidence interval: 0.36 ~0.66) based on the application of the propensity score mixed-effect model.
Conclusion
In a nutshell, we developed philosophical logics for operational criteria pertaining to SITA and provided the analytical framework for the propensity score analysis. We then proposed the PS-mixed model to render balancing score function as fine as possible to make the estimate of treatment effect given the PS-mixed model as close as to the true treatment effect. The proposed PS-mixed model was successfully applied to the non-compliance problem encountered in the RCT while incomplete follow-up outcome is not available and also in the observational studies when the two treatment groups have the imbalance of baseline characteristics.

口試委員會審定書 ………………………………………………… i
致謝 ………………………………………………………………… ii
中文摘要 …………………………………………………………… iii
英文摘要(Abstract)……………………………………………… v
目錄 ………………………………………………………………… viii
圖目錄 ……………………………………………………………… x
表目錄 ……………………………………………………………… xi

論文正文
Chapter I Introduction……………………………………………………………………… 1
Chapter II Literature Review………………………………………………………………. 4
1. Originality of Propensity Score Analysis …………………………………………… 4
2. Balancing scores, propensity score, and strongly ignorable treatment assignment (SITA) ………………………………………… 4
3. Theory of propensity score analysis ………………………………………………… 5
4. Non-compliance issue in the randomized controlled trials………………………… 11
Chapter III Methodological Development…………………………………………………… 14
1. Philosophical logics of operational criteria for the propensity score method ………………………………………………………14
2. Basic evaluation with propensity score methods ……………………………………… 17
3. Fixed effect and random effect propensity score model ………… 17
4. Propensity score adjustment for non-compliance ………… 18
Chapter IV Data Description………………………………………20
Chapter V Results…………………………………………………… 23
1. Performance of propensity score with two adjusted method ………23
2. Fixed and Mixed effect propensity score model………………………………… 26
3. Application of the propensity score method to non-compliance……………… 27
4. Efficacy of colonoscopy referral compared with non-referral group ……… 28
Chapter VI Discussion ……….……………………………………………………………… 31
1. Operational criteria for strongly ignorable treatment assignment (SITA) ……… 31
2. Balancing score and propensity score mixed (PS-mixed) model ……………… 32
3. Applications to non-compliance problem ………………………………………… 33
4. Methodological concerns ………………………………………………………… 34
Reference ……………………………………………………………………………………… 38

[1]P. R. Rosenbaum and D. B. Rubin, “The central role of the propensity score in observational studies for causal effects,” Biometrika, vol. 70, no. 1, pp. 41–55, Apr. 1983.
[2]R. B. D’Agostino, “Propensity score methods for bias reduction in the comparison of a treatment to a non-randomized control group,” Stat. Med., vol. 17, no. 19, pp. 2265–2281, Oct. 1998.
[3]N. Porta, C. Bonet, and E. Cobo, “Discordance between reported intention-to-treat and per protocol analyses,” J. Clin. Epidemiol., vol. 60, no. 7, pp. 663–669, Jul. 2007.
[4]A. Sommer and S. L. Zeger, “On estimating efficacy from clinical trials,” Stat. Med., vol. 10, no. 1, pp. 45–52, Jan. 1991.
[5]J. Cuzick, R. Edwards, and N. Segnan, “Adjusting for non-compliance and contamination in randomized clinical trials,” Stat. Med., vol. 16, no. 9, pp. 1017–1029, May 1997.
[6]D. B. Rubin, “Comment,” J. Am. Stat. Assoc., vol. 75, no. 371, pp. 591–593, Spring 1980.
[7]M. A. Hamilton, “Choosing the parameter for a 2 x 2 table or a 2 x 2 x 2 table analysis,” Am. J. Epidemiol., vol. 109, no. 3, pp. 362–375, Mar. 1979.
[8]P. C. Austin, “An Introduction to Propensity Score Methods for Reducing the Effects of Confounding in Observational Studies,” Multivar. Behav. Res., vol. 46, no. 3, pp. 399–424, May 2011.
[9]P. C. Austin, “Some methods of propensity-score matching had superior performance to others: results of an empirical investigation and Monte Carlo simulations,” Biom. J. Biom. Z., vol. 51, no. 1, pp. 171–184, Feb. 2009.
[10]A. Skrondal and S. Rabe-Hesketh, “Latent Variable Modelling: A Survey*,” Scand. J. Stat., vol. 34, no. 4, pp. 712–745, Spring 2007.
[11]M. Jakubowski, “Latent variables and propensity score matching: a simulation study with application to data from the Programme for International Student Assessment in Poland,” Empir. Econ., vol. 48, no. 3, 2014.
[12]A. J. Vickers, R. W. Rees, C. E. Zollman, R. McCarney, C. M. Smith, N. Ellis, P. Fisher, and R. V. Haselen, “Acupuncture for chronic headache in primary care: large, pragmatic, randomised trial,” BMJ, vol. 328, no. 7442, p. 744, Mar. 2004.
[13]A. J. Vickers, “Whose data set is it anyway? Sharing raw data from randomized trials,” Trials, vol. 7, p. 15, May 2006.
[14]L. L.-C. Hsieh, C.-H. Kuo, L. H. Lee, A. M.-F. Yen, K.-L. Chien, and T. H.-H. Chen, “Treatment of low back pain by acupressure and physical therapy: randomised controlled trial,” BMJ, vol. 332, no. 7543, pp. 696–700, Mar. 2006.
[15]J. D. Hardcastle, J. O. Chamberlain, M. H. Robinson, S. M. Moss, S. S. Amar, T. W. Balfour, P. D. James, and C. M. Mangham, “Randomised controlled trial of faecal-occult-blood screening for colorectal cancer,” Lancet, vol. 348, no. 9040, pp. 1472–1477, Nov. 1996.
[16]O. Kronborg, C. Fenger, J. Olsen, O. D. Jrgensen, and O. Sndergaard, “Randomised study of screening for colorectal cancer with faecal-occult-blood test,” Lancet, vol. 348, no. 9040, pp. 1467–1471, Nov. 1996.
[17]J. S. Mandel, J. H. Bond, T. R. Church, D. C. Snover, G. M. Bradley, L. M. Schuman, and F. Ederer, “Reducing Mortality from Colorectal Cancer by Screening for Fecal Occult Blood,” N. Engl. J. Med., vol. 328, no. 19, pp. 1365–1371, 13 1993.
[18]T.-H. Chiang, S.-L. Chuang, S. L.-S. Chen, H.-M. Chiu, A. M.-F. Yen, S. Y.-H. Chiu, J. C.-Y. Fann, C.-K. Chou, Y.-C. Lee, M.-S. Wu, and H.-H. Chen, “Difference in performance of fecal immunochemical tests with the same hemoglobin cutoff concentration in a nationwide colorectal cancer screening program,” Gastroenterology, vol. 147, no. 6, pp. 1317–1326, Dec. 2014.
[19]H.-M. Chiu, S. L.-S. Chen, A. M.-F. Yen, S. Y.-H. Chiu, J. C.-Y. Fann, Y.-C. Lee, S.-L. Pan, M.-S. Wu, C.-S. Liao, H.-H. Chen, S.-L. Koong, and S.-T. Chiou, “Effectiveness of fecal immunochemical testing in reducing colorectal cancer mortality from the One Million Taiwanese Screening Program,” Cancer, May 2015.
[20]M. A. Brookhart, S. Schneeweiss, K. J. Rothman, R. J. Glynn, J. Avorn, and T. Stürmer, “Variable selection for propensity score models,” Am. J. Epidemiol., vol. 163, no. 12, pp. 1149–1156, Jun. 2006.
[21]P. R. Rosenbaum, “Model-Based Direct Adjustment,” J. Am. Stat. Assoc., vol. 82, no. 398, pp. 387–394, Spring 1987.
[22]P. R. Rosenbaum and D. B. Rubin, “Reducing Bias in Observational Studies Using Subclassification on the Propensity Score,” J. Am. Stat. Assoc., vol. 79, no. 387, pp. 516–524, Spring 1984.
[23]P. C. Austin, “Balance diagnostics for comparing the distribution of baseline covariates between treatment groups in propensity-score matched samples,” Stat. Med., vol. 28, no. 25, pp. 3083–3107, Nov. 2009.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關論文
 
無相關期刊
 
無相關點閱論文