請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/95893完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 陳柏華 | zh_TW |
| dc.contributor.advisor | Albert Y. Chen | en |
| dc.contributor.author | 董文晴 | zh_TW |
| dc.contributor.author | Wen-Ching Tung | en |
| dc.date.accessioned | 2024-09-19T16:14:24Z | - |
| dc.date.available | 2024-09-20 | - |
| dc.date.copyright | 2024-09-19 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-08-14 | - |
| dc.identifier.citation | C. D. Newgard et al., “National guideline for the field triage of injured patients: Recommendations of the National Expert Panel on Field Triage, 2021,” Journal of Trauma and Acute Care Surgery, vol. 93, no. 2, pp. e49–e60, Aug. 2022, doi: 10.1097/TA.0000000000003627.
J. R. Lupton et al., “Under-Triage and Over-Triage Using the Field Triage Guidelines for Injured Patients: A Systematic Review,” Prehospital Emergency Care, vol. 27, no. 1, pp. 38–45, Jan. 2023, doi: 10.1080/10903127.2022.2043963. N. Binney, C. Hyde, and P. M. Bossuyt, “On the Origin of Sensitivity and Specificity,” Ann Intern Med, vol. 174, no. 3, pp. 401–407, Mar. 2021, doi: 10.7326/M20-5028. A. Ardolino, G. Sleat, and K. Willett, “Outcome measurements in major trauma—Results of a consensus meeting,” Injury, vol. 43, no. 10, pp. 1662–1666, Oct. 2012, doi: 10.1016/j.injury.2012.05.008. H. R. Champion et al., “The Major Trauma Outcome Study: establishing national norms for trauma care.,” J Trauma, vol. 30, no. 11, pp. 1356–65, Nov. 1990. T. L. Holbrook, J. P. Anderson, W. J. Sieber, D. Browner, and D. B. Hoyt, “Outcome after Major Trauma,” The Journal of Trauma: Injury, Infection, and Critical Care, vol. 45, no. 2, pp. 315–324, Aug. 1998, doi: 10.1097/00005373-199808000-00018. W. Li, G. Mok, and B. Nolan, “Pre-hospital trauma triage: Outcomes of interfacility transferred trauma patients meeting pre-hospital triage criteria,” Trauma, vol. 25, no. 3, pp. 229–237, Jul. 2023, doi: 10.1177/14604086211064447. E. A. J. van Rein et al., “Effectiveness of prehospital trauma triage systems in selecting severely injured patients: Is comparative analysis possible?,” Am J Emerg Med, vol. 36, no. 6, pp. 1060–1069, Jun. 2018, doi: 10.1016/j.ajem.2018.01.055. R. S. Morris et al., “Field-Triage, Hospital-Triage and Triage-Assessment: A Literature Review of the Current Phases of Adult Trauma Triage,” Journal of Trauma and Acute Care Surgery, vol. 90, no. 6, pp. e138–e145, Jun. 2021, doi: 10.1097/TA.0000000000003125. F. J. Voskens et al., “Accuracy of Prehospital Triage in Selecting Severely Injured Trauma Patients,” JAMA Surg, vol. 153, no. 4, p. 322, Apr. 2018, doi: 10.1001/jamasurg.2017.4472. S. Gianola et al., “Accuracy of pre-hospital triage tools for major trauma: a systematic review with meta-analysis and net clinical benefit,” World Journal of Emergency Surgery, vol. 16, no. 1, p. 31, Dec. 2021, doi: 10.1186/s13017-021-00372-1. C. A. Sewalt et al., “Trauma models to identify major trauma and mortality in the prehospital setting,” British Journal of Surgery, vol. 107, no. 4, pp. 373–380, Mar. 2020, doi: 10.1002/bjs.11304. M. Scerbo et al., “Prehospital triage of trauma patients using the Random Forest computer algorithm,” Journal of Surgical Research, vol. 187, no. 2, pp. 371–376, Apr. 2014, doi: 10.1016/j.jss.2013.06.037. N. Kosaraju, S. R. Sankepally, and K. Mallikharjuna Rao, “Categorical Data: Need, Encoding, Selection of Encoding Method and Its Emergence in Machine Learning Models—A Practical Review Study on Heart Disease Prediction Dataset Using Pearson Correlation,” 2023, pp. 369–382. doi: 10.1007/978-981-19-6631-6_26. J. T. Hancock and T. M. Khoshgoftaar, “Survey on categorical data for neural networks,” J Big Data, vol. 7, no. 1, p. 28, Dec. 2020, doi: 10.1186/s40537-020-00305-w. K. Potdar, T. S., and C. D., “A Comparative Study of Categorical Variable Encoding Techniques for Neural Network Classifiers,” Int J Comput Appl, vol. 175, no. 4, pp. 7–9, Oct. 2017, doi: 10.5120/ijca2017915495. D. Reilly, M. Taylor, P. Fergus, C. Chalmers, and S. Thompson, “The Categorical Data Conundrum: Heuristics for Classification Problems—A Case Study on Domestic Fire Injuries,” IEEE Access, vol. 10, pp. 70113–70125, 2022, doi: 10.1109/ACCESS.2022.3187287. Subha, “How to handle categorical features?” Accessed: Jul. 03, 2024. [Online]. Available: https://medium.com/@pingsubhak/how-to-handle-categorical-features-50e68c9f416a Krishnakanth Naik Jarapala, “Categorical Data Encoding Techniques.” Accessed: Jul. 03, 2024. [Online]. Available: https://medium.com/aiskunks/categorical-data-encoding-techniques-d6296697a40f S. Bishnoi, N. Al-Ansari, M. Khan, S. Heddam, and A. Malik, “Classification of Cotton Genotypes with Mixed Continuous and Categorical Variables: Application of Machine Learning Models,” Sustainability, vol. 14, no. 20, p. 13685, Oct. 2022, doi: 10.3390/su142013685. J. T. Hancock and T. M. Khoshgoftaar, “CatBoost for big data: an interdisciplinary review,” J Big Data, vol. 7, no. 1, p. 94, Dec. 2020, doi: 10.1186/s40537-020-00369-8. J. Hancock and T. M. Khoshgoftaar, “Medicare Fraud Detection using CatBoost,” in 2020 IEEE 21st International Conference on Information Reuse and Integration for Data Science (IRI), IEEE, Aug. 2020, pp. 97–103. doi: 10.1109/IRI49571.2020.00022. SEOUL NATIONAL UNIVERSITY HOSPITAL, “PATOS (Pan-Asian Trauma Outcome Study).” Accessed: Jul. 03, 2024. [Online]. Available: http://lems.re.kr/eng/pan-asian-trauma-outcomes-study-patos/?ckattempt=3 SEOUL NATIONAL UNIVERSITY HOSPITAL, “PATOS (PATOS Overview).” Accessed: Jul. 03, 2024. [Online]. Available: http://lems.re.kr/eng/patos-overview-2/ L. Thompson, M. Hill, and G. Shaw, “Defining major trauma: a literature review,” Br Paramed J, vol. 4, no. 1, pp. 22–30, Jun. 2019, doi: 10.29045/14784726.2019.06.4.1.22. Y.-C. Chien et al., “Comparison of on-scene Glasgow Coma Scale with GCS-motor for prediction of 30-day mortality and functional outcomes of patients with trauma in Asia,” European Journal of Emergency Medicine, vol. 31, no. 3, pp. 181–187, Jun. 2024, doi: 10.1097/MEJ.0000000000001110. C. Anne Kelly, A. Upex, and D. N. Bateman, “Comparison of consciousness level assessment in the poisoned patient using the alert/verbal/painful/unresponsive scale and the glasgow coma scale,” Ann Emerg Med, vol. 44, no. 2, pp. 108–113, Aug. 2004, doi: 10.1016/j.annemergmed.2004.03.028. A. F. McNarry and D. R. Goldhill, “Simple bedside assessment of level of consciousness: comparison of two simple assessment scales with the Glasgow Coma scale*,” Anaesthesia, vol. 59, no. 1, pp. 34–37, Jan. 2004, doi: 10.1111/j.1365-2044.2004.03526.x. H. R. CHAMPION, W. J. SACCO, W. S. COPES, D. S. GANN, T. A. GENNARELLI, and M. E. FLANAGAN, “A Revision of the Trauma Score,” The Journal of Trauma: Injury, Infection, and Critical Care, vol. 29, no. 5, pp. 623–629, May 1989, doi: 10.1097/00005373-198905000-00017. T. Hernández-Del-Toro, F. Martínez-Santiago, and A. Montejo-Ráez, “Assessing classifier’s performance,” in Biosignal Processing and Classification Using Computational Learning and Intelligence, Elsevier, 2022, pp. 131–149. doi: 10.1016/B978-0-12-820125-1.00018-X. Evgueni Petrov, “Model analysis / Feature importance.” Accessed: Jul. 14, 2024. [Online]. Available: https://catboost.ai/en/docs/concepts/fstr Connortann, “Welcome to the SHAP documentation.” Accessed: Jul. 03, 2024. [Online]. Available: https://shap.readthedocs.io/en/latest/index.html Yandex, “CatBoost.” Accessed: Jul. 03, 2024. [Online]. Available: https://catboost.ai/ Sara Vegetti and Ivan Meroi, “XGBoost? CatBoost? LightGBM?” Accessed: Aug. 01, 2024. [Online]. Available: https://www.joinplank.com/articles/xgboost-catboost-lightgbm Uttam Kumar, “Boosting Techniques Battle: CatBoost vs XGBoost vs LightGBM vs scikit-learn GradientBoosting vs Hierarchical GB.” Accessed: Aug. 01, 2024. [Online]. Available: https://www.linkedin.com/pulse/boosting-techniques-battle-catboost-vs-xgboost-lightgbm-uttam-kumar Brain John, “When to Choose CatBoost Over XGBoost or LightGBM [Practical Guide].” Accessed: Aug. 01, 2024. [Online]. Available: https://neptune.ai/blog/when-to-choose-catboost-over-xgboost-or-lightgbm “CatBoost scale_pos_weight.” Accessed: Jul. 03, 2024. [Online]. Available: https://catboost.ai/en/docs/references/training-parameters/common#scale_pos_weight LyzhinIvan, “CatBoost feature selection tutorial.” Accessed: Jul. 03, 2024. [Online]. Available: https://github.com/catboost/catboost/blob/master/catboost/tutorials/feature_selection/select_features_tutorial.ipynb | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/95893 | - |
| dc.description.abstract | 在交通系統中，意外事故帶來的傷亡是備受關注且亟需解決的議題。在這些需緊急送醫的傷患中，難以判斷其創傷輕重程度，將這些患者送至較遠的創傷中心或較近的地區醫院，為急難救助的一大難題。美國外科醫學會對現場檢傷提出期望，希望使檢傷不足的比例小於百分之五，過度檢傷的比例小於百分之三十五，提供傷患合適的救治，降低死傷比例。在過去的研究中，許多檢傷工具是以死亡率進行傷患的分診。現有的檢傷工具，準確度無法滿足美國外科醫學會的期望。事實上創傷的判定繁複且包含人體許多部位的屬性資料。
本研究希望運用能處理屬性資料的機器學習方式，以 ISS 分數為判斷重大創傷的依據，並以此為預測目標，建立到院前判斷是否為重大創傷的檢傷模型，且希望使模型達成美國外科醫學會對現場檢傷的期望。 此研究以機器學習模型 CatBoost，並以2016年至2020年的Pan-Asian Trauma Outcomes Study (PATOS)資料集為研究範本，進行模型的訓練。初始結果顯示在韓國與台灣地區都能有十分亮眼的表現，經由參數的調整更可達到美國外科醫學會檢傷不足比例小於等於5%，過度檢傷比例小於等於35%的期望。依欄位對模型預測的重要性進行篩選後，在大幅減少所需欄位的情況下，也可符合美國外科醫學會的期望。希望未來能將此系統運用於到院前的現場分診，幫助急難救助人員選擇合宜的醫療院所，使傷患獲得最適當治療、降低其死傷比例。 | zh_TW |
| dc.description.abstract | Accidents and trauma attributed to the transportation system operations are a crucial issue worldwide. There are global efforts to reduce mortality and morbidity from major trauma, and the prehospital triage is one of the core initiatives. Over and under triage generate various problems and both should be avoided. Thus, the American College of Surgeons set up goals of less than 5% of under triage and less than 35% of over triage. In previous studies, many triage tools were analyzed by mortality. In addition, several prevailing triage techniques that are based on vital signs cannot meet ACS expectations. The triage procedures are very complicated and involve a lot of categorical data.
We want to use ISS scores as judgment criteria, and use machine learning techniques that can process categorical data to build a prehospital triage model that meets ACS goals. This research uses CatBoost, a machine learning model to train and analyze the PATOS data. The preliminary results show promising outcomes in Korea and Taiwan. Both less than 5% under triage and less than 35% over triage can be achieved via parameter adjustment. We further refined the model with minimal number of parameters, while maintaining triage sensitivity and specificity. We expect to apply our research to prehospital triage practice, facilitating better hospital selection that leads to optimal treatment and outcome. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-09-19T16:14:24Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-09-19T16:14:24Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 中文摘要 ........................................................................................................................... i
ABSTRACT .................................................................................................................... ii LIST OF FIGURES ....................................................................................................... vi LIST OF TABLES ......................................................................................................... ix ABBREVIATION .......................................................................................................... xi Chapter 1 INTRODUCTION ........................................................................................... 1 1.1 Background and Motivation ......................................................................... 1 1.2 Objective ....................................................................................................... 5 Chapter 2 LITERATURE REVIEW ................................................................................ 6 2.1 Pre-hospital major trauma triage (Pre-hospital triage tools) ........................ 6 2.2 Machine Learning for handling Categorical data ....................................... 12 2.2.1 Categorical Data Encoding Techniques ................................................ 13 2.2.2 Machine Learning Models for Categorical Data ................................... 16 2.3 Research gap and summary ........................................................................ 18 Chapter 3 METHODOLOGY ........................................................................................ 19 3.1 Dataset Description........................................................................................... 19 3.2 Data Pre-processing .......................................................................................... 20 3.2.1 Row selection ........................................................................................ 20 3.2.2 Column Selection .................................................................................. 21 3.3.3 Data Overview - Korea, Malaysia and Taiwan Data Screened ............. 25 3.3 Model Evaluation ............................................................................................. 26 3.3.1 Confusion matrix ................................................................................... 26 3.3.2 Feature importance ................................................................................ 28 3.4 Model Introduction ........................................................................................... 30 3.4.1 Parameter adjustment – “scale_pos_weight” ........................................ 32 3.4.2 Feature Selection ................................................................................... 33 Chapter 4 RESULTS ...................................................................................................... 34 4.1 Results of three countries models ............................................................... 34 4.2 Primary results of our models ..................................................................... 38 4.2.1 Taiwan Models ............................................................................... 39 4.2.2 Korea Models ................................................................................. 42 4.2.3 Malaysia Models ............................................................................ 45 4.3 Results after Feature Selection ................................................................... 48 4.3.1 Taiwan Models ............................................................................... 49 4.3.2 Korea Models ................................................................................. 51 4.4 External Validation ..................................................................................... 53 4.4.1 Taiwan Models ............................................................................... 53 4.4.2 Korea Models ........................................................................................ 54 4.5 Model Performance in Patients with and without TBI ............................... 55 4.5.1 Taiwan Models ...................................................................................... 56 4.5.2 Korea Models ........................................................................................ 58 4.6 Limitations .................................................................................................. 59 4.7 Summary ........................................................................................................... 60 Chapter 5 CONCLUSION .............................................................................................. 63 REFERENCES ............................................................................................................... 66 APPENDIX A Detailed Results ..................................................................................... 71 | - |
| dc.language.iso | en | - |
| dc.title | 到院前分類重大創傷之人工智慧模型 | zh_TW |
| dc.title | Machine Learning for Pre-hospital Major Trauma Triage Classification | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 馬惠明;王宗倫;金冠成 | zh_TW |
| dc.contributor.oralexamcommittee | Matthew Huei-Ming Ma;Tzong-Luen Wang;Kuan-Chen Chin | en |
| dc.subject.keyword | 到院前現場分診,重大創傷,CatBoost, | zh_TW |
| dc.subject.keyword | Pre-hospital field triage,major trauma,CatBoost, | en |
| dc.relation.page | 78 | - |
| dc.identifier.doi | 10.6342/NTU202404186 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2024-08-14 | - |
| dc.contributor.author-college | 工學院 | - |
| dc.contributor.author-dept | 土木工程學系 | - |
| 顯示於系所單位： | 土木工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-112-2.pdf 未授權公開取用 | 3.85 MB | Adobe PDF |
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。