跳到主要內容

臺灣博碩士論文加值系統

(18.204.48.64) 您好!臺灣時間:2021/08/03 13:38
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:陳逸瑋
研究生(外文):CHEN, YI-WEI
論文名稱:運用機器學習模型預測加護病房患者之死亡率
論文名稱(外文):Using Machine Learning Models to Predict Mortality of Patients in Intensive Care Units
指導教授:黃河銓黃河銓引用關係
指導教授(外文):HUANG, HO-CHUAN
口試委員:楊棠堯陳聰毅
口試委員(外文):YANG, TANG-YAOCHEN, TSONG-YI
口試日期:2020-07-27
學位類別:碩士
校院名稱:國立高雄科技大學
系所名稱:智慧商務系
學門:電算機學門
學類:電算機一般學類
論文種類:學術論文
論文出版年:2020
畢業學年度:108
語文別:中文
論文頁數:85
中文關鍵詞:加護病房死亡率預測機器學習輕型梯度提升器
外文關鍵詞:Intensive Care UnitMortality predictionMachine learningLightGBM
相關次數:
  • 被引用被引用:0
  • 點閱點閱:57
  • 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:1
加護病房(Intensive Care Unit,ICU)是現代醫療保健中最重要的部分組成之 一,目前市面上已有開發多個加護病房死亡率評分系統,但卻發現醫院使用加護 病房評分系統評估患者死亡率,死亡率普遍都被高估。因此,本研究目的希望藉 由機器學習來預測加護病房患者死亡率預測,利用現今強大的演算技術提高死亡 率預測的準確度,並利用資料探勘的技術找出其中影響死亡率的重要因素,協助 臨床人員做正確的判斷。

本研究利用機器學習技術針對加護病房患者進行死亡率預測,本研究使用的 資料來源為 WiDS Datathon 2020,總共 91,713 筆真實資料,180 個特徵欄位。首 先針對資料變數項缺失值過多或雜亂數據進行篩選清除,針對特徵選取的部分, 利用輕型梯度提升器(LightGBM)演算法進行特徵重要性分析,針對特徵資料進 行探索性分析(EDA)計算每個特徵相較於其他特徵的相關係數,將具高度相關性 特徵依重要程度進行特徵篩選。本研究利用隨機減少多數法(Ramdom Under- Sampling)處理資料不平衡問題。最後總共為 6,884 筆資料,53 個欄位進行預測, 以 7:3 的比例做訓練集與測試集。本研究使用 LightGBM、XGBoost、Random Forest 與 SVM 針對加護病房患者進行死亡率之預測。

經由分析結果發現,在整體死亡率方面,LightGBM 針對加護病房患者死亡 率預測,準確率達 81.0%,精準度達 80.1%,召回率達 82.9%,F1-Score 達 81.5%, AUC 達到 81.0%,具有良好的表現,表示該模型針對此資料死亡率預測的分類 能力效果較佳。另外,本研究針對加護病房罹患糖尿病與肝硬化患者進行個別死 亡率的預測,實驗結果發現,LightGBM 在罹患糖尿病患者死亡率預測的部分有 不錯的分類效果,準確率達到 77.6%,AUC 達到 77.7%。LightGBM 雖然針對罹 患肝硬化患者死亡率預測準確率仍有 74.2%,AUC 為 74.3%,但在評估模型 F1- Score 與召回率的表現不算亮眼,分別為 70.1%與 64.0%。綜合上述,LightGBM 為本研究預測死亡率較準確的演算法,另外針對糖尿病患者也有不錯的準確性。
Intensive Care Unit (ICU) is one of the most important mechanism of modern medical care. Although several ICU scoring systems exist currently in the market, the mortality rate assessed by the ICU scoring system is, however, generally overestimated in the hospital system. Therefore, the purpose of this study is to employ machine learning technologies to predict the mortality of patients in the ICU, taking advantage of current powerful technology to improve the accuracy of mortality prediction.

The data source used in this study is from the WiDS Datathon 2020 dataset, a total of 91,713 real data with 180 feature fields. Missing values or cluttered data have been identified and removed. In terms of feature selection, this study employs Lightweight Gradient Booster (LightGBM) algorithm to analyze the importance of feature fields, and uses Explore Data Analysis (EDA) to explore the correlation coefficient of feature fields. In addition, the Random under-sampling method was also used to deal with the issue of imbalance data. Finally, a total of 6,884 data with 53 feature fields are obtained from data preprocessing for data analysis and prediction. Different algorithms, such as LightGBM, XGBoost, Random Forest and Support Vector Machine (SVM), were used to predict the mortality of patients in ICUs.

The research results showed that in terms of overall mortality, LightGBM had better prediction performance than other models did (accuracy rate= 81.0%, precision rate= 80.1%, recall rate= 82.9%, F1-score= 81.5%, and AUC score= 81.0%). In addition, this study also predicted the mortality of patients with diabetes and cirrhosis in the ICU. The results found that LightGBM had a good classification performance on the prediction of the mortality of patients with diabetes (accuracy rate= 77.6%, and AUC score= 77.7%). Although LightGBM had a good effect on prediction the mortality of patients with cirrhosis (accuracy rate= 74.2%, and AUC score= 74.3%), however,the performance in the evaluation model is not excellent (F1-score= 70.1%, and recall rate= 64.0%). In conclusion, LightGBM is a more accurate algorithm for predicting mortality in this study, and it also had good accuracy for diabetic patients.
摘 要i
ABSTRACTii
致謝iv
目錄v
表目錄vii
圖目錄viii
一、緒論 1
1.1研究背景與動機1
1.2研究目的3
1.3論文架構4
二、文獻探討5
2.1加護病房之定義5
2.2死亡率預測5
2.3預測評分系統6
2.3.1急性生理與慢性健康評分7
2.3.2簡化急性生理評分8
2.3.3相繼器官衰竭評分8
2.4機器學習9
2.4.1輕型梯度提升器11
2.4.2極限梯度提升器13
2.4.3隨機森林14
2.4.4支持向量機17
2.5資料不平衡19
三、研究方法21
3.1研究設計21
3.2資料蒐集21
3.3資料前處理22
3.4特徵選取23
3.5資料不平衡處理23
3.6分類演算法24
3.7評估指標25
3.7.1混淆矩陣25
3.7.2接收者操作特徵曲線27
3.7.3曲線下面積28
四、結果與討論30
4.1患者資料統計分析30
4.2糖尿病患者資料統計分析37
4.3肝硬化患者資料統計分析44
4.4特徵選取分析51
4.5分類器建模結果52
4.5.1建模結果52
4.5.2糖尿病患者建模結果55
4.5.3肝硬化患者建模結果58
4.5.4分類器結果之討論61
五、結論與建議64
5.1研究結論64
5.2研究限制65
5.3研究建議66
參考文獻67


參考文獻:
王淑惠(2009),成人加護病房疾病嚴重度分數系統。重症醫學雜誌,176-189。
吳少玲、郭斐如、明勇(2007),重症單位急性混亂患者之評估與護理。護理雜誌,67-71。
李欣海(2013),隨機森林模型在分類與回歸分析中的應用。應用昆蟲學報,1190-1197。
林貴滿(1998),當代中重症護理學。台北:匯華圖書,3-18。
林麗華(2002),加護病房分級評鑑之研究。國立陽明大學醫管系碩士論文。
唐高駿、薛貴霞、蔡建和、陳秀丹(2005),加護病房成本效益。中華民國急救加護醫學會雜誌,139-145。
張鈺、陳珺、王曉峰、劉飛(2017),Xgboost在滾動軸承故障診斷中的應用。噪音與振動控制,166-170。
郭許達(1998),加護病房的設計和疾病嚴重度指標。台北:金銘書局。
齊玉美(2003),不對稱性分類分析之研究,國立中山大學資訊管理系碩士論文。
謝劍斌、興軍亮、張立甯、方宇強、李沛秦、劉通、閆瑋、王勇、沈傑、張政、 譚筠、胡俊(2016),改變未來20 年最重要的 20 個視覺機器學習理論深讀, 佳魁資訊。
韓玉、施海龍,、曲波、武玉欣、劉潔(2014),隨機森林方法在醫學中的應用。中國預防醫學雜誌,79-81。
顏志鴻、郭英哲(2011),使用 Fisher 線性判別分析之快速行人偵測系統。國立勤益科技大學電機工程系碩士論文。
Abu-Samah, A., Razak, N. N. A., Suhaimi, F. M., Jamaludin, U. K., & Chase, G. (2018). Linking Bayesian network and intensive care units data: a glycemic control study. Paper presented at the TENCON 2018-2018 IEEE Region 10 Conference.
Armony, M., Chan, C. W., & Zhu, B. (2018). Critical care capacity management: Understanding the role of a step down unit. Production and Operations Management, 27(5), 859-883.
Barddal, J. P., Enembreck, F., Gomes, H. M., Bifet, A., & Pfahringer, B. (2019). Boosting decision stumps for dynamic feature selection on data streams. Information Systems, 83, 13-29.
Beck, D. H., Smith, G. B., Pappachan, J. V., & Millar, B. (2003). External validation of the SAPS II, APACHE II and APACHE III prognostic models in South England: a multicentre study. Intensive care medicine, 29(2), 249-256.
Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32.
Castella, X., Artigas, A., Bion, J., & Kari, A. (1995). A comparison of severity of illness scoring systems for intensive care unit patients: results of a multicenter, multinational study. Critical care medicine, 23(8), 1327-1335.
Ceriani, R., Mazzoni, M., Bortone, F., Gandini, S., Solinas, C., Susini, G., & Parodi, O. (2003). Application of the sequential organ failure assessment score to cardiac surgical patients. Chest, 123(4), 1229-1239.
Chan, C., Chan, E., Ng, D., Chow, P., & Kwok, K. (2006). Application of artificial neural networks to establish a predictive mortality risk model in children admitted to a paediatric intensive care unit. Singapore medical journal, 47(11), 928.
Chan, C.-L., & Ting, H.-W. (2011). Constructing a novel mortality prediction model with Bayes theorem and genetic algorithm. Expert Systems wChan, C. W., Farias, V. F., & Escobar, G. J. (2017). The impact of delays on service times in the intensive care unit. Management Science, 63(7), 2049-2072.ith Applications, 38(7), 7924-7928.
Chan, C. W., Farias, V. F., & Escobar, G. J. (2017). The impact of delays on service times in the intensive care unit. Management Science, 63(7), 2049-2072.
Chan, C. W., Green, L. V., Lekwijit, S., Lu, L., & Escobar, G. (2019). Assessing the impact of service level when customer needs are uncertain: An empirical investigation of hospital step-down units. Management Science, 65(2), 751-775.
Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. Paper presented at the Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining.
Chen, T., Xu, J., Ying, H., Chen, X., Feng, R., Fang, X., . . . Wu, J. (2019). Prediction of Extubation Failure for Intensive Care Unit Patients Using Light Gradient Boosting Machine. IEEE Access, 7, 150960-150968.
Cheng, L., Chen, X., De Vos, J., Lai, X., & Witlox, F. (2019). Applying a random forest method approach to model travel mode choice behavior. Travel behaviour and society, 14, 1-10.
Christensen, S., Johansen, M. B., Christiansen, C. F., Jensen, R., & Lemeshow, S. (2011). Comparison of Charlson comorbidity index with SAPS and APACHE scores for prediction of mortality following intensive care. Clinical epidemiology, 3, 203.
Deng, X., Liu, Q., Deng, Y., & Mahadevan, S. (2016). An improved method to construct basic probability assignment based on the confusion matrix for classification problem. Information Sciences, 340, 250-261.
Dinh, A., Miertschin, S., Young, A., & Mohanty, S. D. (2019). A data-driven approach to predicting diabetes and cardiovascular disease with machine learning. BMC medical informatics and decision making, 19(1), 211.
Ferreira, F. L., Bota, D. P., Bross, A., Mélot, C., & Vincent, J.-L. (2001). Serial evaluation of the SOFA score to predict outcome in critically ill patients. Jama, 286(14), 1754-1758.
Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of statistics, 1189-1232.
Fueglistaler, P., Amsler, F., Schüepp, M., Fueglistaler-Montali, I., Attenberger, C., Pargger, H., . . . Gross, T. (2010). Prognostic value of Sequential Organ Failure Assessment and Simplified Acute Physiology II score compared with trauma scores in the outcome of multiple-trauma patients. The American Journal of Surgery, 200(2), 204-214.
Ghasemi, P., & Raoufy, M. R. (2016). Prediction of mortality in patients with sepsis using detrended fluctuation analysis of heart rate variability. Paper presented at the 2016 23rd Iranian Conference on Biomedical Engineering and 2016 1st International Iranian Conference on Biomedical Engineering (ICBME).
Ghosh, S., Feng, M., Nguyen, H., & Li, J. (2015). Hypotension risk prediction via sequential contrast patterns of ICU blood pressure. IEEE journal of biomedical and health informatics, 20(5), 1416-1426.
Halpern, N. A., & Pastores, S. M. (2010). Critical care medicine in the United States 2000–2005: an analysis of bed numbers, occupancy rates, payer mix, and costs. Critical care medicine, 38(1), 65-71.
Ho, K. M., Knuiman, M., Finn, J., & Webb, S. A. (2008). Estimating long-term survival of critically ill patients: the PREDICT model. PLoS one, 3(9), e3226.
Houthooft, R., Ruyssinck, J., van der Herten, J., Stijven, S., Couckuyt, I., Gadeyne, B., . . . Dhaene, T. (2015). Predictive modelling of survival and length of stay in critically ill patients using sequential organ failure scores. Artificial intelligence in medicine, 63(3), 191-207.
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning (Vol. 112): Springer.
Kampichler, C., Wieland, R., Calmé, S., Weissenberger, H., & Arriaga-Weiss, S. (2010). Classification in conservation biology: a comparison of five machine-learning methods. Ecological Informatics, 5(6), 441-450.
Kang, M. W., Kim, J., Kim, D. K., Oh, K.-H., Joo, K. W., Kim, Y. S., & Han, S. S. (2020). Machine learning algorithm to predict mortality in patients undergoing continuous renal replacement therapy. Critical Care, 24(1), 42.
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., . . . Liu, T.-Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Paper presented at the Advances in neural information processing systems.
Kim, Y., Toh, K.-A., Teoh, A. B. J., Eng, H.-L., & Yau, W.-Y. (2012). An online AUC formulation for binary classification. Pattern recognition, 45(6), 2266-2279.
Knaus, W. A., Draper, E. A., Wagner, D. P., & Zimmerman, J. E. (1985). APACHE II: a severity of disease classification system. Critical care medicine, 13(10), 818-829.
Knaus, W. A., Zimmerman, J. E., Wagner, D. P., Draper, E. A., & Lawrence, D. E. (1981). APACHE-acute physiology and chronic health evaluation: a physiologically based classification system. Critical care medicine, 9(8), 591-597.
Kneale, C., & Brown, S. D. (2018). Uncharted forest: A technique for exploratory data analysis. Talanta, 189, 71-78.
Koziarski, M., Krawczyk, B., & Woźniak, M. (2019). Radial-Based oversampling for noisy imbalanced data classification. Neurocomputing, 343, 19-33.
Kubat, M., & Matwin, S. (1997). Addressing the curse of imbalanced training sets: one-sided selection. Paper presented at the Icml.
Kuzniewicz, M. W., Vasilevskis, E. E., Lane, R., Dean, M. L., Trivedi, N. G., Rennie, D. J., . . . Dudley, R. A. (2008). Variation in ICU risk-adjusted mortality: impact of methods of assessment and potential confounders. Chest, 133(6), 1319-1327.
Lai, C. S., Tao, Y., Xu, F., Ng, W. W., Jia, Y., Yuan, H., . . . Locatelli, G. (2019). A robust correlation analysis framework for imbalanced and dichotomous data with uncertainty. Information Sciences, 470, 58-77.
Le Gall, J.-R., Lemeshow, S., & Saulnier, F. (1993). A new simplified acute physiology score (SAPS II) based on a European/North American multicenter study. Jama, 270(24), 2957-2963.
Le Gall, J.-R., Loirat, P., Alperovitch, A., Glaser, P., Granthil, C., Mathieu, D., . . . Villers, D. (1984). A simplified acute physiology score for ICU patients. Critical care medicine, 12(11), 975-977.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. nature, 521(7553), 436-444.
Ledoux, D., Canivet, J.-L., Preiser, J.-C., Lefrancq, J., & Damas, P. (2008). SAPS 3 admission score: an external validation in a general intensive care population. Intensive care medicine, 34(10), 1873.
Lemeshow, S., Teres, D., Klar, J., Avrunin, J. S., Gehlbach, S. H., & Rapoport, J. (1993). Mortality Probability Models (MPM II) based on an international cohort of intensive care unit patients. Jama, 270(20), 2478-2486.
Li, J., Dong, M., & Zhao, W. (2015). Admissions optimisation and premature discharge decisions in intensive care units. International Journal of Production Research, 53(24), 7329-7342.
Li, S., & Zhang, X. (2019). Research on orthopedic auxiliary classification and prediction model based on XGBoost algorithm. Neural Computing and Applications, 1-9.
Li, X., & Wang, Y. (2013). Applying various algorithms for species distribution modelling. Integrative Zoology, 8(2), 124-135.
Lin, K., Hu, Y., & Kong, G. (2019). Predicting in-hospital mortality of patients with acute kidney injury in the ICU using random forest model. International journal of medical informatics, 125, 55-61.
Liu, T., Guan, Y., & Lin, Y. (2017). Research on modulation recognition with ensemble learning. EURASIP Journal on Wireless Communications and Networking, 2017(1), 179.
Li-wei, H. L., Adams, R. P., Mayaud, L., Moody, G. B., Malhotra, A., Mark, R. G., & Nemati, S. (2014). A physiological time series dynamics-based approach to patient monitoring and outcome prediction. IEEE journal of biomedical and health informatics, 19(3), 1068-1076.
Luaces, O., Taboada, F., Albaiceta, G. M., Domínguez, L. A., Enríquez, P., Bahamonde, A., & Group, G. (2009). Predicting the probability of survival in intensive care unit patients from a small number of variables and training examples. Artificial intelligence in medicine, 45(1), 63-76.
Luo, G. (2016). PredicT-ML: a tool for automating machine learning model building with big clinical data. Health information science and systems, 4(1), 5.
McCabe, W. R., & Jackson, G. G. (1962). Gram-negative bacteremia: I. Etiology and ecology. Archives of internal medicine, 110(6), 847-855.
Mesbahi, M. R., Rahmani, A. M., & Hosseinzadeh, M. (2017). Highly reliable architecture using the 80/20 rule in cloud computing datacenters. Future Generation Computer Systems, 77, 77-86.
Moridani, M. K., Setarehdan, S. K., Nasrabadi, A. M., & Hajinasrollah, E. (2015). New algorithm of mortality risk prediction for cardiovascular patients admitted in intensive care unit. International journal of clinical and experimental medicine, 8(6), 8916.
Nassar Jr, A. P., Mocelin, A. O., Nunes, A. L. B., Giannini, F. P., Brauer, L., Andrade, F. M., & Dias, C. A. (2012). Caution when using prognostic models: a prospective comparison of 3 recent prognostic models. Journal of critical care, 27(4), 423. e421-423. e427.
Nemeth, M., Borkin, D., & Michalconok, G. (2019). The Comparison of Machine-Learning Methods XGBoost and LightGBM to Predict Energy Development. Paper presented at the Proceedings of the Computational Methods in Systems and Software.
Nielsen, D. (2016). Tree boosting with xgboost-why does xgboost win" every" machine learning competition? NTNU,
Obermeyer, Z., & Emanuel, E. J. (2016). Predicting the future—big data, machine learning, and clinical medicine. The New England journal of medicine, 375(13), 1216.
Pätilä, T., Kukkonen, S., Vento, A., Pettilä, V., & Suojaranta-Ylinen, R. (2006). Relation of the sequential organ failure assessment score to morbidity and mortality after cardiac surgery. The Annals of thoracic surgery, 82(6), 2072-2078.
Poole, D., Rossi, C., Latronico, N., Rossi, G., Finazzi, S., & Bertolini, G. (2012). Comparison between SAPS II and SAPS 3 in predicting hospital mortality in a cohort of 103 Italian ICUs. Is new always better? Intensive care medicine, 38(8), 1280-1288.
Poorinmohammad, N., Mohabatkar, H., Behbahani, M., & Biria, D. (2015). Computational prediction of anti HIV‐1 peptides and in vitro evaluation of anti HIV‐1 activity of HIV‐1 P24‐derived peptides. Journal of peptide science, 21(1), 10-16.
Qiu, H., Luo, L., Su, Z., Zhou, L., Wang, L., & Chen, Y. (2020). Machine learning approaches to predict peak demand days of cardiovascular admissions considering environmental exposure. BMC medical informatics and decision making, 20, 1-11.
Ricamato, M. T., & Tortorella, F. (2011). Partial AUC maximization in a linear combination of dichotomizers. Pattern recognition, 44(10-11), 2669-2677.
Rouzbahman, M., Jovicic, A., & Chignell, M. (2016). Can cluster-boosted regression improve prediction of death and length of stay in the ICU? IEEE journal of biomedical and health informatics, 21(3), 851-858.
Silva, I., Moody, G., Scott, D. J., Celi, L. A., & Mark, R. G. (2012). Predicting in-hospital mortality of icu patients: The physionet/computing in cardiology challenge 2012. Paper presented at the 2012 Computing in Cardiology.
Singer, M., Deutschman, C. S., Seymour, C. W., Shankar-Hari, M., Annane, D., Bauer, M., . . . Coopersmith, C. M. (2016). The third international consensus definitions for sepsis and septic shock (Sepsis-3). Jama, 315(8), 801-810.
Song, Y., Jiao, X., Qiao, Y., Liu, X., Qiang, Y., Liu, Z., & Zhang, L. (2019). Prediction of Double-High Biochemical Indicators Based on LightGBM and XGBoost. Paper presented at the Proceedings of the 2019 International Conference on Artificial Intelligence and Computer Science.
Suykens, J. A., & Vandewalle, J. (1999). Least squares support vector machine classifiers. Neural processing letters, 9(3), 293-300.
Thabtah, F., Abdelhamid, N., & Peebles, D. (2019). A machine learning autism classification based on logistic regression analysis. Health information science and systems, 7(1), 12.
Thanathornwong, B. (2018). Bayesian-based decision support system for assessing the needs for orthodontic treatment. Healthcare informatics research, 24(1), 22-28.
Ting, H.-W., Chen, M.-S., Hsieh, Y.-C., & Chan, C.-L. (2010). Good mortality prediction by Glasgow Coma Scale for neurosurgical patients. Journal of the Chinese Medical Association, 73(3), 139-143.
Torlay, L., Perrone-Bertolotti, M., Thomas, E., & Baciu, M. (2017). Machine learning–XGBoost analysis of language networks to classify patients with epilepsy. Brain informatics, 4(3), 159-169.
Valentini, G. (2002). Gene expression data analysis of human lymphoma using support vector machines and output coding ensembles. Artificial intelligence in medicine, 26(3), 281-304.
Vapnik, V. (2013). The nature of statistical learning theory: Springer science & business media.
Vincent, J.-L., Moreno, R., Takala, J., Willatts, S., De Mendonça, A., Bruining, H., . . . Thijs, L. G. (1996). The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction/failure. In: Springer-Verlag.
Song, X., Sun, X., & Zhao, Y. (2018). Abnormal user identification based on XGBoost algorithm. Journal of Measurement Science & Instrumentation, 9(4).
Yang, F., Wang, H.-z., Mi, H., & Cai, W.-w. (2009). Using random forest for reliable classification and cost-sensitive learning for medical diagnosis. BMC bioinformatics, 10(S1), S22.
Zhang, W., Ji, H., & Zhang, H. (2017). Application of XGBoost algorithm in e-commerce product recommendation [J]. Internet of things technologies, 7(2), 102-104.
Zimmerman, J. E., Kramer, A. A., McNair, D. S., & Malila, F. M. (2006). Acute Physiology and Chronic Health Evaluation (APACHE) IV: hospital mortality assessment for today’s critically ill patients. Critical care medicine, 34(5), 1297-1310.
電子全文 電子全文(網際網路公開日期:20250826)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top