臺灣博碩士論文加值系統

敗血症是一種危及生命的病症，由於其復雜多變的症狀，早期預測具有挑戰性。本研究通過使用基於自注意力(Self Attention)為基礎的深度學習數值插補技術，整合不同類型的數據，提高了敗血症的預測能力。我提出了一種新的預測框架，利用深度學習進行數據插補和分類並對各種插補模型和分類網絡進行了研究，結果顯示自注意力為基礎的模型表現超越了其他模型。在早期敗血症預測方面，我的方法超越了先前的模型，能夠更有效提前七小時預測敗血症的發生。在MIMIC-IV資料庫中使用六小時的資料結合自注意力的插補和分類模型有最好的效果，在提早五小時和七小時前預測敗血症發生分別獲得AUROC 0.79 和0.83。本研究提供了一套可行性的框架，並深入比較不同插補模型的特點, 展示了自注意力為基礎的模型在資料處理和敗血症早期預測的潛力。

Sepsis is a life-threatening condition, and its early prediction poses challenges due to its complex and variable symptoms. In this study, I improved the predictive ability of sepsis by integrating different types of data using a deep learning numerical imputation technique based on self-attention. I proposed a novel prediction framework that utilizes deep learning for data imputation and classification. Various imputation models and classification networks were investigated, and the results showed that the self-attention-based framework outperformed other models. In terms of early sepsis prediction, my approach surpassed previous models by being able to predict the occurrence of sepsis seven hours in advance more effectively. The combination of six hours of data from the MIMIC-IV database with self-attention-based imputation and classification models yielded the best performance, achieving AUROC of 0.83 and 0.79 for five hours and seven hours early prediction of sepsis respectively. This study presents a feasible framework and provides an in-depth comparison of different imputation models, showcasing the potential of self-attention-based models in data processing and early sepsis prediction.

Verification Letter from the Oral Examination Committee i
Acknowledgements iii
摘要v
Abstract vii
Contents ix
List of Figures xiii
List of Tables xvii
Denotation xix
Chapter 1 Introduction 1
1.1 Background 1
1.2 Research Problem 2
1.3 Significance and Contributions 3
1.4 Thesis Organization 4
Chapter 2 Literature Review 7
2.1 Previous Studies Related to the Diagnosis and Prediction of Sepsis 7
2.2 Summary of the Limitations and Gaps in Existing Research 10
Chapter 3 Materials and Methods 11
3.1 Data Description 11
3.2 Data Extraction and Pre-Processing 11
3.2.1 Definition of sepsis and its criteria 11
3.2.2 Data extraction from MIMIC-IV 14
3.2.3 Filtering outliers and item ids 16
3.2.4 Inclusion and exclusion 18
3.2.5 Determination of onset time 20
3.2.6 Regular time series 21
3.3 Model Design 23
3.3.1 Overview 24
3.3.2 Missing value imputation model 25
3.3.2.1 Last observation carried forward 25
3.3.2.2 LOCF with linear interpolation method 27
3.3.2.3 K-nearest neighbors imputation 28
3.3.2.4 Bidirectional Recurrent Imputation for Time Series 30
3.3.2.5 Self attention based transformers imputation 32
3.3.3 Time Series Classification Model 36
3.3.3.1 Long short-term memory fully convolutional networks 36
3.3.3.2 Temporal convolutional network 38
3.3.3.3 Transformer encoder and mlp network 39
3.4 Evaluation Metrics 41
Chapter 4 Results 47
4.1 Statistical Analysis of Study Population 47
4.2 Comparative Evaluation of Imputation Approaches 52
4.3 Analysis of Data Imputation 54
4.4 Results of Transformer MLP Performance 58
4.5 Results of Different Classifier Performance 62
4.6 Evaluating Model Performance across Different Timesteps 63
4.7 Discussion 67
Chapter 5 Conclusion 69
5.1 Summary of Main Findings 69
5.2 Significance and Implications of the Study 70
5.3 Limitations of the Study 71
5.4 Suggestions for Future Research 73
References 75
Appendix A — Tables 83
Appendix B — Figures 85

Wenjie Du, David Côté, and Yan Liu. Saits: Self-attention-based imputation for time series. Expert Systems with Applications, 219:119619, 2023.
Mervyn Singer, Clifford S Deutschman, Christopher Warren Seymour, Manu Shankar-Hari, Djillali Annane, Michael Bauer, Rinaldo Bellomo, Gordon R Bernard, Jean-Daniel Chiche, Craig M Coopersmith, et al. The third international consensus definitions for sepsis and septic shock (sepsis-3). Jama, 315(8):801–810, 2016.
Andrew Rhodes, Laura E Evans, Waleed Alhazzani, Mitchell M Levy, Massimo Antonelli, Ricard Ferrer, Anand Kumar, Jonathan E Sevransky, Charles L Sprung, Mark E Nunnally, et al. Surviving sepsis campaign: international guidelines for management of sepsis and septic shock: 2016. Intensive Care Medicine, 43:304–
377, 2017.
Konrad Reinhart, Ron Daniels, Niranjan Kissoon, Flavia R Machado, Raymond D Schachter, and Simon Finfer. Recognizing sepsis as a global health priority—a who resolution. New England Journal of Medicine, 377(5):414–417, 2017.
Carolin Fleischmann, André Scherag, Neill KJ Adhikari, Christiane S Hartog, Thomas Tsaganos, Peter Schlattmann, Derek C Angus, and Konrad Reinhart. Assessment of global incidence and mortality of hospital-treated sepsis. current estimates and limitations. American Journal of Respiratory and Critical Care Medicine, 193(3):259–272, 2016.
Viktor Y Dombrovskiy, Andrew A Martin, Jagadeeshan Sunderram, and Harold L Paz. Rapid increase in hospitalization and mortality rates for severe sepsis in the united states: a trend analysis from 1993 to 2003. Critical Care Medicine, 35(5):1244–1250, 2007.
Timothy G Buchman, Steven Q Simpson, Kimberly L Sciarretta, Kristen P Finne, Nicole Sowers, Michael Collier, Saurabh Chavan, Ibijoke Oke, Meghan E Pennini, Aathira Santhosh, et al. Sepsis among medicare beneficiaries: 1. the burdens of sepsis, 2012–2018. Critical Care Medicine, 48(3):276, 2020.
David W Shimabukuro, Christopher W Barton, Mitchell D Feldman, Samson J Mataraso, and Ritankar Das. Effect of a machine learning-based severe sepsis prediction algorithm on patient survival and hospital length of stay: a randomised clinical trial. BMJ Open Respiratory Research, 4(1):e000234, 2017.
Ricard Ferrer, Ignacio Martin-Loeches, Gary Phillips, Tiffany M Osborn, Sean Townsend, R Phillip Dellinger, Antonio Artigas, Christa Schorr, and Mitchell M Levy. Empiric antibiotic treatment reduces mortality in severe sepsis and septic shock from the first hour: results from a guideline-based performance improvement program. Critical Care Medicine, 42(8):1749–1755, 2014.
Michael Moor, Bastian Rieck, Max Horn, Catherine R Jutzeler, and Karsten Borgwardt. Early prediction of sepsis in the icu using machine learning: a systematic review. Frontiers in Medicine, 8:607952, 2021.
Belal Alsinglawi, Fady Alnajjar, Omar Mubin, Mauricio Novoa, Ola Karajeh, and Omar Darwish. Benchmarking predictive models in electronic health records: Sepsis length of stay prediction. In Advanced Information Networking and Applications: Proceedings of the 34th International Conference on Advanced Information Networking and Applications (AINA-2020), pages 258–267. Springer, 2020.
Hong-Fei Deng, Ming-Wei Sun, Yu Wang, Jun Zeng, Ting Yuan, Ting Li, Di-Huan Li, Wei Chen, Ping Zhou, Qi Wang, et al. Evaluating machine learning models for sepsis prediction: A systematic review of methodologies. Iscience, page 103651, 2021.
Roger C Bone, Robert A Balk, Frank B Cerra, R Phillip Dellinger, Alan M Fein, William A Knaus, Roland MH Schein, and William J Sibbald. Definitions for sepsis and organ failure and guidelines for the use of innovative therapies in sepsis. Chest, 101(6):1644–1655, 1992.
Thomas Desautels, Jacob Calvert, Jana Hoffman, Melissa Jay, Yaniv Kerem, Lisa Shieh, David Shimabukuro, Uli Chettipally, Mitchell D Feldman, Chris Barton, et al. Prediction of sepsis in the intensive care unit with minimal electronic health record data: a machine learning approach. JMIR Medical Informatics, 4(3):e5909, 2016.
Supreeth P Shashikumar, Qiao Li, Gari D Clifford, and Shamim Nemati. Multiscale network representation of physiological time series for early prediction of sepsis. Physiological Measurement, 38(12):2235, 2017.
Chen Lin, Yuan Zhang, Julie Ivy, Muge Capan, Ryan Arnold, Jeanne M Huddleston, and Min Chi. Early diagnosis and prediction of sepsis shock by combining static and dynamic information using convolutional-lstm. In 2018 IEEE International Conference on Healthcare Informatics (ICHI), pages 219–228. IEEE, 2018.
Matthieu Scherpf, Felix Gräßer, Hagen Malberg, and Sebastian Zaunseder. Predicting sepsis with a recurrent neural network using the mimic iii database. Computers in Biology and Medicine, 113:103395, 2019.
Michael Moor, Max Horn, Bastian Rieck, Damian Roqueiro, and Karsten Borgwardt. Early recognition of sepsis with gaussian process temporal convolutional networks and dynamic time warping. In Machine Learning for Healthcare Conference, pages 2–26. PMLR, 2019.
Naimahmed Nesaragi, Shivnarayan Patidar, and Veerakumar Thangaraj. A correlation matrix-based tensor decomposition method for early prediction of sepsis from clinical data. Biocybernetics and Biomedical Engineering, 41(3):1013–1024, 2021.
Margherita Rosnati and Vincent Fortuin. Mgp-atttcn: An interpretable machine learning model for the prediction of sepsis. Plos One, 16(5):e0251248, 2021.
Merve Apalak and Kamran Kiasaleh. Improving sepsis prediction performance using conditional recurrent adversarial networks. IEEE Access, 10:134466–134476, 2022.
Simon Meyer Lauritsen, Mads Ellersgaard Kalør, Emil Lund Kongsgaard, Katrine Meyer Lauritsen, Marianne Johansson Jørgensen, Jeppe Lange, and Bo Thiesson. Early detection of sepsis utilizing deep learning on electronic health record event sequences. Artificial Intelligence in Medicine, 104:101820, 2020.
Javier Enrique Camacho-Cogollo, Isis Bonet, Bladimir Gil, and Ernesto Iadanza. Machine learning models for early prediction of sepsis on large healthcare datasets. Electronics, 11(9):1507, 2022.
Xin Zhao, Wenqian Shen, Guanjun Wang, et al. Early prediction of sepsis based on machine learning algorithm. Computational Intelligence and Neuroscience, 2021, 2021.
Alistair Johnson, Lucas Bulgarelli, Tom Pollard, Steven Horng, Leo Anthony Celi, and Roger Mark. Mimic-iv. PhysioNet. Available online at: https://physionet.org/content/mimiciv/1.0/(accessed August 23, 2021), 2020.
J L Vincent, Rui Moreno, Jukka Takala, Sheila Willatts, Arnaldo De Mendonça, Hajo Bruining, CK Reinhart, PeterM Suter, and Lambertius G Thijs. The sofa (sepsisrelated organ failure assessment) score to describe organ dysfunction/failure: On behalf of the working group on sepsis-related problems of the european society of intensive care medicine (see contributors to the project in the appendix), 1996.
Jean-Louis Vincent. Dear sirs, i’m sorry to say that i don’t like you. Critical Care Medicine, 25(2):372–374, 1997.
Fethi Gül, Mustafa Kemal Arslantaş, İsmail Cinel, and Anand Kumar. Changing definitions of sepsis. Turkish Journal of Anaesthesiology and Reanimation, 45(3):129, 2017.
Alistair EW Johnson, David J Stone, Leo A Celi, and Tom J Pollard. The mimic code repository: enabling reproducibility in critical care research. Journal of the American Medical Informatics Association, 25(1):32–39, 2018.
Fahim Mahmud, Naqib Sad Pathan, and Muhammad Quamruzzaman. Early detection of sepsis in critical patients using random forest classifier. In 2020 IEEE Region 10 Symposium (TENSYMP), pages 130–133. IEEE, 2020.
Yao-Yi Kuo, Shu-Tien Huang, and Hung-Wen Chiu. Applying artificial neural network for early detection of sepsis with intentionally preserved highly missing realworld data for simulating clinical situation. BMC Medical Informatics and Decision Making, 21:1–11, 2021.
Zeyu Liu, Anahita Khojandi, Akram Mohammed, Xueping Li, Lokesh K Chinthala, Robert L Davis, and Rishikesan Kamaleswaran. Hema: A hierarchically enriched machine learning approach for managing false alarms in real time: A sepsis prediction case study. Computers in Biology and Medicine, 131:104255, 2021.
Zahra Eftekhari, Sally Mokhtari, Tushondra Thomas, Dongyun Yang, Liana Nikolaenko, Deron Johnson, Jana Dickter, Justine Abella Ross, Bernard Tegtmeier, Eileen P Smith, et al. Updated analysis: novel machine-learning-based sepsis prediction model for patients undergoing hematopoietic stem cell transplantation (early sepsis prediction/identification for transplant recipients: Esprit). Blood, 134:4477, 2019.
Olga Troyanskaya, Michael Cantor, Gavin Sherlock, Pat Brown, Trevor Hastie, Robert Tibshirani, David Botstein, and Russ B Altman. Missing value estimation methods for dna microarrays. Bioinformatics, 17(6):520–525, 2001.
Jiahua Chen and Jun Shao. Nearest neighbor imputation for survey data. Journal of Official Statistics, 16(2):113, 2000.
Alex Rubinsteyn and Sergey Feldman. fancyimpute: An imputation library for python.
Wei Cao, Dong Wang, Jian Li, Hao Zhou, Lei Li, and Yitan Li. Brits: Bidirectional recurrent imputation for time series. Advances in Neural Information Processing Systems, 31, 2018.
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in Neural Information Processing Systems, 30, 2017.
Andrea Galassi, Marco Lippi, and Paolo Torroni. Attention in natural language processing. IEEE Transactions on Neural Networks and Learning Systems, 32(10):4291–4308, 2020.
Xiang Li, Minglei Li, Pengfei Yan, Guanyi Li, Yuchen Jiang, Hao Luo, and Shen Yin. Deep learning attention mechanism in medical image analysis: Basics and beyonds. International Journal of Network Dynamics and Intelligence, pages 93–116, 2023.
Jin Fan, Ke Zhang, Yipan Huang, Yifei Zhu, and Baiping Chen. Parallel spatio-temporal attention-based tcn for multivariate time series prediction. Neural Computing and Applications, pages 1–10, 2021.
Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural Computation, 9(8):1735–1780, 1997.
Shaojie Bai, J Zico Kolter, and Vladlen Koltun. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. ArXiv Preprint ArXiv:1803.01271, 2018.
Gautam Krishna, Co Tran, Mason Carnahan, Yan Han, and Ahmed H Tewfik. Improving eeg based continuous speech recognition. ArXiv Preprint ArXiv:1911.11610, 2019.
Yonghao Jin, Fei Li, and Hong Yu. Hype: a high performing nlp system for automatically detecting hypoglycemia events from electronic health record notes. ArXiv Preprint ArXiv:1811.11945, 2018.
Tae Soo Kim and Austin Reiter. Interpretable 3d human action analysis with temporal convolutional networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 1623–1631. IEEE, 2017.
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE International Conference on Computer Vision, pages 1026– 1034, 2015.
Joon-myoung Kwon, Ye Rang Lee, Min-Seung Jung, Yoon-Ji Lee, Yong-Yeon Jo, Da-Young Kang, Soo Youn Lee, Yong-Hyeon Cho, Jae-Hyun Shin, Jang-Hyeon Ban, et al. Deep-learning model for screening sepsis using electrocardiography. Scandinavian Journal of Trauma, Resuscitation and Emergency Medicine, 29(1):1–
12, 2021.
Kim Huat Goh, Le Wang, Adrian Yong Kwang Yeow, Hermione Poh, Ke Li, Joannas Jie Lin Yeow, and Gamaliel Yu Heng Tan. Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare. Nature Communications, 12(1):711, 2021.