近年來，隨著技術的飛速發展，我們可以比以前更容易地收集數據。然而，相對於製造業中所應用的相關方法，醫學中所使用的統計相關方法仍稍顯不足。過去，醫院只透過簡單的統計方法或以工作經驗來進行實驗，並產生了大量的“經驗法則”，但卻無法解決大量的數據和辨認連續過程(手術或是治療)之間的相互作用，從而導致醫療上的誤判。

本研究集中在外科重症加護病房(intensive care unit)中的插管/拔管決策。我們將機器學習應用於關於拔管決策的真實數據。由於每個病人的狀況，體質和住院時間長短不同，因此需要逐一診斷出每個病例的上述措施，並對插管/拔管治療的進行個別判斷。由於上述原因，從醫院收集到的數據不完整、不一致，使得方法在應用上相對不穩定也不好解釋。

在這項研究中，我們著重在資料上的預處理，並以資料科學的手法建立拔管預測模型，透過問題定義、資料預處理、變數篩選、支援向量機、提升邏輯回歸(Boosting Logistic Regression)、交互驗證等，強調如何提高拔管成功率來協助臨床上的拔管決策，其模型預測的準確率達到81.5%。另一方面，本研究提出貝式決策模型，除了修正拔管預測的機率，進行拔管決策後驗機率的推論外，更進一步地計算資料科學預測模型所提供的資訊價值，從而提升“精密醫學”的決策過程。

Nowadays, with the rapid development in technology, we can collect the data more easily and efficiently than before. However, the typical statistical methodologies applied in medicine are not comprehensive when comparing to those applied in manufacturing. In the past, endotracheal extubation in the hospital simply conducted the experiments by simple statistics or clinical experience and then it generates lots of “rule of thumbs” which cannot address large dataset effectively, identify the interactions among the sequential processes, and thus might lead to misclassification in the medical treatment.

This study focuses on the intubate/extubate treatments in the surgical intensive care unit (ICU). We apply the machine learning methodologies to the real setting regarding the decision of extubation. Since each patient shows different nature, status, constitution, and the length of staying in the ICU, the above measures are extracted by each individual and lead to the case-by-case decision of the intubate/extubate treatments. With the difficulty mentioned above, the data collected from the hospital is usually incomplete and inconsistent and this issue makes the application unstable as well as difficult.

In this study, we apply the data science framework and establish the extubation prediction model, involving definition of the problem, data preprocessing, variable selection, support vector machine, boosting logistic regression, cross validation etc. Emphasizing on how to improve the success rate of extubation to assist the clinical extubation decision, and the accuracy rate is up to 81.5%. On the other hand, this paper proposes a Bayesian decision framework to correct the probability of the prediction result, inference the posterior probability, and quantify the value of information provided by our proposed model, so as to enhance the decision-making process of “Precision Medicine”.

Bianchi, M. T., Alexander, B. M., & Cash, S. S. (2009). Incorporating uncertainty into medical decision making: an approach to unexpected test results. Medical Decision Making, 29(1), 116-124.
Dehghani, A., Abdeyazdan, G., & Davaridolatabadi, E. (2016). An Overview of the Predictor Standard Tools for Patient Weaning from Mechanical Ventilation. Electronic physician, 8(2), 1955.
Epstein, S. K., Ciubotaru, R. L., & Wong, J. B. (1997). Effect of failed extubation on the outcome of mechanical ventilation. Chest, 112(1), 186-192.
Esteban, A., Frutos, F., Tobin, M. J., Alía, I., Solsona, J. F., Valverdu, V., Tomás, R. (1995). A comparison of four methods of weaning patients from mechanical ventilation. New England Journal of Medicine, 332(6), 345-350.
Esteban, A., Frutos-Vivar, F., Ferguson, N. D., Arabi, Y., Apezteguía, C., González, M., Soares, M.-A. (2004). Noninvasive positive-pressure ventilation for respiratory failure after extubation. New England Journal of Medicine, 350(24), 2452-2460.
Frutos-Vivar, F., Ferguson, N. D., Esteban, A., Epstein, S. K., Arabi, Y., Apezteguía, C., D’empaire, G. (2006). Risk factors for extubation failure in patients following a successful spontaneous breathing trial. CHEST Journal, 130(6), 1664-1671.
Galmacci, G. (1996). Collinearity detection in linear regression models. Computational Economics, 9(3), 215-227.
Hernandez, G., Fernandez, R., Luzon, E., Cuena, R., & Montejo, J. C. (2007). The early phase of the minute ventilation recovery curve predicts extubation failure better than the minute ventilation recovery time. CHEST Journal, 131(5), 1315-1322.
Henriquez, R. R., & Korpi-Steiner, N. (2016). Bayesian Inference Dilemma in Medical Decision-Making: A Need for User-Friendly Probabilistic Reasoning Tools. Clinical Chemistry, 62(9), 1285-1286.
Herrle, S. R., Corbett Jr, E. C., Fagan, M. J., Moore, C. G., & Elnicki, D. M. (2011). Bayes’ theorem and the physical examination: probability assessment and diagnostic decision-making. Academic medicine: journal of the Association of American Medical Colleges, 86(5), 618.
Kim, S., Kim, W., & Park, R. W. (2011). A comparison of intensive care unit mortality prediction models through the use of data mining techniques. Healthcare informatics research, 17(4), 232-243.
Kulkarni, A. P., & Agarwal, V. (2008). Extubation failure in intensive care unit: predictors and management. Indian Journal of Critical Care Medicine, 12(1), 1.
Liu, Y., Wei, L.-Q., Li, G.-Q., Lv, F.-Y., Wang, H., Zhang, Y.-H., & Cao, W.-L. (2010). A decision-tree model for predicting extubation outcome in elderly patients after a successful spontaneous breathing trial. Anesthesia & Analgesia, 111(5), 1211-1218.
Matic, I., Titlic, M., Dikanovic, M., Jurjevic, M., Jukic, I., & Tonkic, A. (2007). Effects of APACHE II score on mechanical ventilation; prediction and outcome. Acta anaesthesiologica Belgica, 58(3), 177.
McConville, J. F., & Kress, J. P. (2012). Weaning patients from the ventilator. New England Journal of Medicine, 367(23), 2233-2239.
Miller, R. L., & Cole, R. P. (1996). Association between reduced cuff leak volume and postextubation stridor. Chest, 110(4), 1035-1040.
Miu, T., Joffe, A. M., Yanez, N. D., Khandelwal, N., Dagal, A. H., Deem, S., & Treggiari, M. M. (2013). Predictors of re-intubation in critically ill patients. Respiratory Care, respcare. 02527.
Mokhlesi, B., Tulaimat, A., Gluckman, T. J., Wang, Y., Evans, A. T., & Corbridge, T. C. (2007). Predicting extubation failure after successful completion of a spontaneous breathing trial. Respiratory Care, 52(12), 1710-1717.
Mueller, M., Almeida, J. S., Stanislaus, R., & Wagner, C. L. (2013). Can machine learning methods predict extubation outcome in premature infants as well as clinicians? Journal of neonatal biology, 2.
Ortega, R., Connor, C., Rodriguez, G., & Spencer, C. (2014). Endotracheal extubation. The New England Journal of Medicine, 370
Peñuelas, Ó., Thille, A. W., & Esteban, A. (2015). Discontinuation of ventilatory support: new solutions to old dilemmas. Current opinion in critical care, 21(1), 74-81.
Ramon, J., Fierens, D., Güiza, F., Meyfroidt, G., Blockeel, H., Bruynooghe, M., & Van Den Berghe, G. (2007). Mining data from intensive care patients. Advanced Engineering Informatics, 21(3), 243-256.
Robriquet, L., Georges, H., Leroy, O., Devos, P., D'escrivan, T., & Guery, B. (2006). Predictors of extubation failure in patients with chronic obstructive pulmonary disease. Journal of critical care, 21(2), 185-190.
Thille, A. W., Harrois, A., Schortgen, F., Brun-Buisson, C., & Brochard, L. (2011). Outcomes of extubation failure in medical intensive care unit patients. Critical care medicine, 39(12), 2612-2618.
Thille, A. W., Richard, J.-C. M., & Brochard, L. (2013). The decision to extubate in the intensive care unit. American journal of respiratory and critical care medicine, 187(12), 1294-1302.
Whiting, J., Gowardman, J., & Huntington, D. (2006). The effect of extubation failure on outcome in a multidisciplinary Australian intensive care unit. Critical Care and Resuscitation, 8(4), 328.
Zeng, J.-H., Lee, C.-Y., Lee, S.-Y., Kuo, P.-H., Lu R.-B. (2015). Data Mining for Genome-Wide Association Studies: An Empirical Study of Han-Chinese Patients with Bipolar Disorder. 2015 Chinese Institute of Industrial Engineers (CIIE) Conference & Annual Meeting, Taichung, Taiwan. (in Chinese)