請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88670完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 賴飛羆 | zh_TW |
| dc.contributor.advisor | Feipei Lai | en |
| dc.contributor.author | 蘇彰甫 | zh_TW |
| dc.contributor.author | Chang-Fu Su | en |
| dc.date.accessioned | 2023-08-15T17:18:15Z | - |
| dc.date.available | 2023-11-09 | - |
| dc.date.copyright | 2023-08-15 | - |
| dc.date.issued | 2023 | - |
| dc.date.submitted | 2023-07-31 | - |
| dc.identifier.citation | [1] G. D. Perkins et al., "Cardiac arrest and cardiopulmonary resuscitation outcome reports: update of the Utstein Resuscitation Registry Templates for Out-of-Hospital Cardiac Arrest: a statement for healthcare professionals from a task force of the International Liaison Committee on Resuscitation (American Heart Association, European Resuscitation Council, Australian and New Zealand Council on Resuscitation, Heart and Stroke Foundation of Canada, InterAmerican Heart Foundation, Resuscitation Council of Southern Africa, Resuscitation Council of Asia); and the American Heart Association Emergency Cardiovascular Care Committee and the Council on Cardiopulmonary, Critical Care, Perioperative and Resuscitation," (in eng), Circulation, vol. 132, no. 13, pp. 1286-300, Sep 29 2015, doi: https://doi.org/10.1161/cir.0000000000000144.
[2] R. M. Merchant et al., "Incidence of treated cardiac arrest in hospitalized patients in the United States," (in eng), Critical care medicine, vol. 39, no. 11, pp. 2401-6, Nov 2011, doi: https://doi.org/10.1097/CCM.0b013e3182257459. [3] L. W. Andersen, M. J. Holmberg, K. M. Berg, M. W. Donnino, and A. Granfeldt, "In-Hospital Cardiac Arrest: A Review," Jama, vol. 321, no. 12, pp. 1200-1210, Mar 26 2019, doi: https://doi.org/10.1001/jama.2019.1696. [4] L. M. Chen, B. K. Nallamothu, J. A. Spertus, Y. Li, and P. S. Chan, "Association between a hospital's rate of cardiac arrest incidence and cardiac arrest survival," (in eng), JAMA internal medicine, vol. 173, no. 13, pp. 1186-95, Jul 8 2013, doi: https://doi.org/10.1001/jamainternmed.2013.1026. [5] M. Schluep, B. Y. Gravesteijn, R. J. Stolker, H. Endeman, and S. E. Hoeks, "One-year survival after in-hospital cardiac arrest: A systematic review and meta-analysis," Resuscitation, vol. 132, pp. 90-100, Nov 2018, doi: https://doi.org/10.1016/j.resuscitation.2018.09.001. [6] S. M. Fernando et al., "Pre-arrest and intra-arrest prognostic factors associated with survival after in-hospital cardiac arrest: systematic review and meta-analysis," BMJ (Clinical research ed.), vol. 367, p. l6373, Dec 4 2019, doi: https://doi.org/10.1136/bmj.l6373. [7] C. P. Subbe, M. Kruger, P. Rutherford, and L. Gemmel, "Validation of a modified Early Warning Score in medical admissions," QJM, vol. 94, no. 10, pp. 521-6, Oct 2001, doi: https://doi.org/10.1093/qjmed/94.10.521. [8] M. M. Churpek, T. C. Yuen, C. Winslow, D. O. Meltzer, M. W. Kattan, and D. P. Edelson, "Multicenter Comparison of Machine Learning Methods and Conventional Regression for Predicting Clinical Deterioration on the Wards," Critical care medicine, vol. 44, no. 2, pp. 368-74, Feb 2016, doi: https://doi.org/10.1097/CCM.0000000000001571. [9] M. Green, H. Lander, A. Snyder, P. Hudson, M. Churpek, and D. Edelson, "Comparison of the Between the Flags calling criteria to the MEWS, NEWS and the electronic Cardiac Arrest Risk Triage (eCART) score for the identification of deteriorating ward patients," (in eng), Resuscitation, vol. 123, pp. 86-91, Feb 2018, doi: https://doi.org/10.1016/j.resuscitation.2017.10.028. [10] B. Bartkowiak et al., "Validating the Electronic Cardiac Arrest Risk Triage (eCART) Score for Risk Stratification of Surgical Inpatients in the Postoperative Setting: Retrospective Cohort Study," (in eng), Annals of surgery, Jan 12 2018, doi: https://doi.org/10.1097/sla.0000000000002665. [11] M. M. Churpek et al., "Multicenter development and validation of a risk stratification tool for ward patients," American journal of respiratory and critical care medicine, vol. 190, no. 6, pp. 649-55, Sep 15 2014, doi: https://doi.org/10.1164/rccm.201406-1022OC. [12] F. Sessa et al., "Heart rate variability as predictive factor for sudden cardiac death," (in eng), Aging (Albany NY), vol. 10, no. 2, pp. 166-177, 2018, doi: https://doi.org/10.18632/aging.101386. [13] N. Liu et al., "An Intelligent Scoring System and Its Application to Cardiac Arrest Prediction," IEEE Transactions on Information Technology in Biomedicine, vol. 16, no. 6, pp. 1324-1331, 2012, doi: https://doi.org/10.1109/TITB.2012.2212448. [14] M. A. Akel, K. A. Carey, C. J. Winslow, M. M. Churpek, and D. P. Edelson, "Less is more: Detecting clinical deterioration in the hospital with machine learning using only age, heart rate, and respiratory rate," (in eng), Resuscitation, vol. 168, pp. 6-10, Nov 2021, doi: https://doi.org/10.1016/j.resuscitation.2021.08.024. [15] J. Kim, M. Chae, H. J. Chang, Y. A. Kim, and E. Park, "Predicting Cardiac Arrest and Respiratory Failure Using Feasible Artificial Intelligence with Simple Trajectories of Patient Data," (in eng), J Clin Med, vol. 8, no. 9, Aug 29 2019, doi: https://doi.org/10.3390/jcm8091336. [16] K.-J. Cho et al., "Detecting Patient Deterioration Using Artificial Intelligence in a Rapid Response System," (in eng), Critical care medicine, vol. 48, no. 4, pp. e285-e289, Apr 2020, doi: https://doi.org/10.1097/ccm.0000000000004236. [17] T. J. Hodgetts et al., "Incidence, location and reasons for avoidable in-hospital cardiac arrest in a district general hospital," (in eng), Resuscitation, vol. 54, no. 2, pp. 115-23, Aug 2002, doi: https://doi.org/10.1016/s0300-9572(02)00098-9. [18] P. G. Lyons, D. P. Edelson, and M. M. Churpek, "Rapid response systems," (in eng), Resuscitation, vol. 128, pp. 191-197, Jul 2018, doi: https://doi.org/10.1016/j.resuscitation.2018.05.013. [19] B. K. Nallamothu et al., "How Do Resuscitation Teams at Top-Performing Hospitals for In-Hospital Cardiac Arrest Succeed? A Qualitative Study," (in eng), Circulation, vol. 138, no. 2, pp. 154-163, Jul 10 2018, doi: https://doi.org/10.1161/circulationaha.118.033674. [20] M. E. Smith et al., "Early warning system scores for clinical deterioration in hospitalized patients: a systematic review," Annals of the American Thoracic Society, vol. 11, no. 9, pp. 1454-65, Nov 2014, doi: https://doi.org/10.1513/AnnalsATS.201403-102OC. [21] J. Ludikhuize, M. Borgert, J. Binnekade, C. Subbe, D. Dongelmans, and A. Goossens, "Standardized measurement of the Modified Early Warning Score results in enhanced implementation of a Rapid Response System: a quasi-experimental study," (in eng), Resuscitation, vol. 85, no. 5, pp. 676-82, May 2014, doi: https://doi.org/10.1016/j.resuscitation.2014.02.009. [22] S. H. Kim et al., "Predicting severe outcomes using national early warning score (NEWS) in patients identified by a rapid response system: a retrospective cohort study," Scientific Reports, vol. 11, no. 1, p. 18021, 2021/09/09 2021, doi: https://doi.org/10.1038/s41598-021-97121-w. [23] M. M. Churpek, T. C. Yuen, S. Y. Park, R. Gibbons, and D. P. Edelson, "Using electronic health record data to develop and validate a prediction model for adverse outcomes in the wards*," (in eng), Critical care medicine, vol. 42, no. 4, pp. 841-8, Apr 2014, doi: https://doi.org/10.1097/ccm.0000000000000038. [24] S. van Buuren and K. Groothuis-Oudshoorn, "mice: Multivariate Imputation by Chained Equations in R," J Stat Softw, vol. 45, no. 3, pp. 1-67, 12/12/ 2011, doi: https://doi.org/10.18637/jss.v045.i03. [25] J. m. Kwon, Y. Lee, Y. Lee, S. Lee, and J. Park, "An Algorithm Based on Deep Learning for Predicting In-Hospital Cardiac Arrest," Journal of the American Heart Association, vol. 7, no. 13, Jun 26 2018, doi: https://doi.org/10.1161/JAHA.118.008678. [26] H.-K. Chang et al., "Early Detecting In-Hospital Cardiac Arrest Based on Machine Learning on Imbalanced Data," 2019 IEEE International Conference on Healthcare Informatics (ICHI), pp. 1-10, 10-13 June 2019 2019, doi: https://doi.org/10.1109/ICHI.2019.8904504. [27] S. Hochreiter and J. r. Schmidhuber, "Long short-term memory," (in eng), Neural Comput, vol. 9, no. 8, pp. 1735-80, Nov 15 1997, doi: https://doi.org/10.1162/neco.1997.9.8.1735. [28] C. Esteban, O. Staeck, S. Baier, Y. Yang, and V. Tresp, "Predicting Clinical Events by Combining Static and Dynamic Information Using Recurrent Neural Networks," 2016 IEEE International Conference on Healthcare Informatics (ICHI), pp. 93-101, 4-7 Oct. 2016 2016, doi: https://doi.org/10.1109/ICHI.2016.16. [29] F. Pedregosa et al., "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, vol. 12, no. null, pp. 2825–2830, 2011, doi: https://doi.org/10.48550/arXiv.1201.0490. [30] X. Wu et al., "Top 10 algorithms in data mining," Knowledge and Information Systems, vol. 14, no. 1, pp. 1-37, 2008/01/01 2008, doi: https://doi.org/10.1007/s10115-007-0114-2. [31] Y. Freund and R. E. Schapire, "Experiments with a new boosting algorithm," Proceedings of the Thirteenth International Conference on International Conference on Machine Learning (ICML '96), pp. 148–156, 1996, doi: https://dl.acm.org/doi/10.5555/3091696.3091715. [32] R. E. Schapire, "A brief introduction to boosting," Proceedings of the 16th international joint conference on Artificial intelligence - Volume 2, pp. 1401–1406, 1999, doi: https://dl.acm.org/doi/10.5555/1624312.1624417. [33] H. Tin Kam, "Random decision forests," Proceedings of 3rd International Conference on Document Analysis and Recognition, vol. 1, pp. 278-282 vol.1, 14-16 Aug. 1995 1995, doi: https://doi.org/10.1109/ICDAR.1995.598994. [34] D. Böhning, "Multinomial logistic regression algorithm," Ann Inst Stat Math, vol. 44, no. 1, pp. 197-200, 1992/03/01 1992, doi: https://doi.org/10.1007/BF00048682. [35] J. H. Friedman, "Stochastic gradient boosting," Comput Stat Data Anal, vol. 38, no. 4, pp. 367-378, 2002/02/28/ 2002, doi: https://doi.org/10.1016/S0167-9473(01)00065-2. [36] L. Breiman, J. Friedman, R. Olshen, and C. Stone, Classification And Regression Trees. 2017, pp. 1-358. [37] D. J. Hand and K. Yu, "Idiot's Bayes: Not So Stupid after All?," Int Stat Rev, vol. 69, no. 3, pp. 385-398, 2001, doi: https://doi.org/10.2307/1403452. [38] C. Cortes and V. Vapnik, "Support-vector networks," Machine Learning, vol. 20, no. 3, pp. 273-297, 1995/09/01 1995, doi: https://doi.org/10.1007/BF00994018. [39] S. Abe, Support vector machines for pattern classification (Advances in pattern recognition). London: Springer, 2005, pp. xiv, 343 p. [40] E. Fix and J. L. Hodges, "Discriminatory Analysis. Nonparametric Discrimination: Consistency Properties," Int Stat Rev, vol. 57, no. 3, pp. 238-247, 1989, doi: https://doi.org/10.2307/1403797. [41] P.-N. Tan, M. Steinbach, A. Karpatne, and V. Kumar, Introduction to Data Mining (2nd Edition). Pearson, 2018. [42] J. R. Quinlan, C4.5: Programs for Machine Learning. Elsevier Science, 2014. [43] L. Breiman, "Arcing the Edge Technical Report 486; Statistics Department," University of California: Berkeley, CA, USA, 1997. [44] G. Chandrashekar and F. Sahin, "A survey on feature selection methods," Comput Electr Eng, vol. 40, no. 1, pp. 16-28, 2014/01/01/ 2014, doi: https://doi.org/10.1016/j.compeleceng.2013.11.024. [45] S. Khalid, T. Khalil, and S. Nasreen, "A survey of feature selection and feature extraction techniques in machine learning," 2014 Science and Information Conference, pp. 372-378, 27-29 Aug. 2014 2014, doi: https://doi.org/10.1109/SAI.2014.6918213. [46] S. M. Lundberg and S.-I. Lee, "A unified approach to interpreting model predictions," Advances in neural information processing systems, vol. 30, 2017, doi: https://doi.org/10.48550/arXiv.1705.07874. [47] S. M. Lundberg et al., "From local explanations to global understanding with explainable AI for trees," Nature Machine Intelligence, vol. 2, no. 1, pp. 56-67, 2020/01/01 2020, doi: https://doi.org/10.1038/s42256-019-0138-9. [48] C.-F. Su, S.-I. Chiu, J.-S. R. Jang, and F. Lai, "Improved inpatient deterioration detection in general wards by using time-series vital signs," Scientific Reports, vol. 12, no. 1, p. 11901, 2022/07/13 2022, doi: http://doi.org/10.1038/s41598-022-16195-2. [49] J. D. Chalmers et al., "Severity assessment tools to guide ICU admission in community-acquired pneumonia: systematic review and meta-analysis," Intensive Care Medicine, vol. 37, no. 9, pp. 1409-1420, 2011/09/01 2011, doi: https://doi.org/10.1007/s00134-011-2261-x. [50] R. Robert et al., "Influence of ICU-bed availability on ICU admission decisions," Annals of Intensive Care, vol. 5, no. 1, p. 55, 2015/12/30 2015, doi: https://doi.org/10.1186/s13613-015-0099-z. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88670 | - |
| dc.description.abstract | 住院期間的心跳驟停（In-hospital cardiac arrest, IHCA）是嚴重的事件，常伴隨高死亡率，各大研究亦強調了早期識別和早期介入對於改善患者預後的重要性。部份的心跳驟停是突然地發生，沒有伴隨明顯徵兆，因此開發自動化的預測模型以識別高風險患者並及時進行介入是非常重要的。本研究引入了兩個創新的預測模型：『時間序列早期預警分數（Time-Series Early Warning Score, TEWS）』和『可解釋的時間序列早期預警分數（Explainable Time-Series Early Warning Score, TEWS-X）』。這兩個模型只使用常規量測的生命徵象資料來提供較為準確且可解釋的IHCA預測，使醫療提供者能夠採取主動措施，提高患者安全性。
TEWS模型通過結合多個時間窗口的特徵，再加上類神經網路對於特徵趨勢和模式的處理能力，實現了更高的預測準確性。此外，TEWS-X模型通過採用基於決策樹的機器學習方法和SHAP值，對醫療照顧者解釋其預測結果，使醫療照顧者可依此結果作出臨床決策。這些模型可以無縫地集成到現有的照護流程中，無需中斷工作流程，進而提升病人安全並優化資源分配。 | zh_TW |
| dc.description.abstract | In-hospital cardiac arrest (IHCA) is a critical event associated with high mortality rates. Early identification and intervention are crucial for improving patient outcomes. This study introduces two innovative predictive models: the Time-Series Early Warning Score (TEWS) and the Explainable Time-Series Early Warning Score (TEWS-X), designed to leverage vital signs data and provide accurate and explainable predictions of IHCA.
The TEWS model utilizes vital signs data from six time windows (48 hours) to predict IHCA occurrences and performs superior IHCA prediction performance compared to alternative classification algorithms. Incorporating features from multiple time windows significantly improves prediction accuracy, with an area under the receiver operating characteristic curve (AUROC) of 0.808, surpassing the performance of MEWS (AUROC of MEWS: 0.649). The TEWS-X model incorporates a tree-based machine learning approach and SHAP values to enhance model explainability, enabling insights into feature importance and supporting transparent decision-making, facilitating an understanding of the critical factors influencing IHCA risk. These models can seamlessly integrate into existing care processes, improving patient safety without disrupting workflow. The TEWS and TEWS-X models represent significant advancements in IHCA prediction and explainability. By leveraging vital signs data and incorporating explainable modeling techniques, these models empower healthcare providers to identify patients at risk of IHCA and intervene promptly and proactively. Further research is needed to validate the models in diverse healthcare settings and explore additional data sources for enhanced predictive capabilities. Implementing the TEWS and TEWS-X models can improve patient outcomes and optimize resource allocation in the management of IHCA. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-08-15T17:18:15Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2023-08-15T17:18:15Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 論文口試委員審定書 ii
誌謝 iii 中文摘要 iv Abstract v CONTENTS vii LIST OF FIGURES xi LIST OF TABLES xiii Chapter 1 Introduction 1 1.1 Motivation 1 1.2 Purpose 5 Chapter 2 Literature Review 7 2.1 Importance of IHCA Prediction 7 2.2 Modified Early Warning Score (MEWS) 11 2.3 Model of IHCA Prediction 14 Chapter 3 Materials and Method for TEWS (Time-Series Early Warning Score) 19 3.1 Ethics Declarations 20 3.2 Setting and Study Population 20 3.3 Main Outcome 24 3.4 Model Development 25 3.4.1 Data Preprocessing 25 3.4.2 Handing Imbalanced Data 26 3.4.3 TEWS Model Development 27 3.5 Performance Evaluation 29 3.6 Feature Selection 31 Chapter 4 Materials and Method for TEWS-X (Explainable Time-Series Early Warning Score) 33 4.1 Ethics Declarations 34 4.2 Setting and Study Population 34 4.3 Main Outcome 35 4.4 Model Development 37 4.4.1 Data Preprocessing 37 4.4.2 Handling Imbalanced Data 39 4.4.3 TEWS-X Model Development 40 4.5 Performance Evaluation 41 4.6 Expandability with SHAP 42 Chapter 5 Result 43 5.1 Result for TEWS (Time-Series Early Warning Score) 43 5.1.1 Performance with one, three, and six time windows. 45 5.1.2 Performance with Features Chosen via SBS Algorithm 48 5.2 Result for TEWS-X (Explainable Time-Series Early Warning Score) 51 5.2.1 Performance of TEWS-X 51 5.2.2 Feature Importance Difference Visualization 54 5.2.3 Feature Impact Amplitude and Distribution Visualization 56 5.2.4 Feature Impact Distribution Visualization 58 5.2.5 Local Feature Importance Visualization 61 Chapter 6 Discussion 63 6.1 TEWS (Time-Series Warning Score) 63 6.2 TEWS-X (Explainable Time-Series Early Warning Score) 68 6.3 Implementation of TEWS/TEWS-X 72 Chapter 7 Conclusion 76 Reference 78 | - |
| dc.language.iso | en | - |
| dc.subject | 住院病人心跳驟停 | zh_TW |
| dc.subject | 生命徵象 | zh_TW |
| dc.subject | 早期警訊系統 | zh_TW |
| dc.subject | 機器學習 | zh_TW |
| dc.subject | 可解釋人工智慧 | zh_TW |
| dc.subject | Early Warning Score | en |
| dc.subject | Vital sign | en |
| dc.subject | Machine Learning | en |
| dc.subject | IHCA Prediction | en |
| dc.subject | Explainable AI | en |
| dc.title | 以機器學習模型偵測一般病房住院病人惡化 | zh_TW |
| dc.title | Inpatient deterioration detection in general wards using machine learning model | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 111-2 | - |
| dc.description.degree | 博士 | - |
| dc.contributor.oralexamcommittee | 傅楸善;趙坤茂;陳縕儂;孫維仁;陳晉興;吳耀銘;汪大暉;黃樹林 | zh_TW |
| dc.contributor.oralexamcommittee | Chiou-Shann Fuh;Kun-Mao Chao;Yun-Nung Chen;Wei-Zen Sun;Jin-Shing Chen;Yao-Ming Wu;Ta-Hui Wang ;Shu-Lin Hwang | en |
| dc.subject.keyword | 住院病人心跳驟停,早期警訊系統,生命徵象,機器學習,可解釋人工智慧, | zh_TW |
| dc.subject.keyword | IHCA Prediction,Early Warning Score,Vital sign,Machine Learning,Explainable AI, | en |
| dc.relation.page | 82 | - |
| dc.identifier.doi | 10.6342/NTU202302444 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2023-08-01 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 生醫電子與資訊學研究所 | - |
| 顯示於系所單位： | 生醫電子與資訊學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-111-2.pdf | 2.25 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。