簡易檢索 / 詳目顯示

研究生: 黃梓維
Tzu-Wei Huang
論文名稱: 結合穿戴式脈波量測與分類分析應用於新冠肺炎疫苗之心血管副作用監測:Moderna及AZ廠牌疫苗
Integration of Wearable Pulse Measurement and Classification Analysis for Monitoring Cardiovascular Side Effects of COVID-19 Vaccines: A Study on Moderna and AstraZeneca Brands
指導教授: 許昕
Hsin Hsiu
口試委員: 劉如濟
Ju-Chi Liu
林上智
Shang-Chih Lin
學位類別: 碩士
Master
系所名稱: 應用科技學院 - 醫學工程研究所
Graduate Institute of Biomedical Engineering
論文出版年: 2023
畢業學年度: 111
語文別: 中文
論文頁數: 107
中文關鍵詞: COVID-19疫苗疫苗副作用非侵入性脈波測量心血管循環頻域分析機器學習脈波分佈區間分析法
外文關鍵詞: COVID-19 Vaccine, Vaccine Side Effects, Non-Invasive Pulse Wave Measurement, Cardiovascular Circulation, Frequency Domain Analysis, Machine Learning, Pulse Wave Distribution Interval Analysis Method
相關次數: 點閱:221下載:0
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

疫苗接種於控制COVID-19疫情中起著關鍵作用,但也存在著心血管副作用之風險。本研究延續BNT疫苗副作用所做之成果,利用非侵入式脈波測量和頻域分析檢測COVID-19疫苗,評估Moderna COVID‑19 vaccine (mRNA-127)和Oxford–AstraZeneca COVID-19 vaccine(AZD1222)接種後對心血管系統之影響。
本研究於251位接受疫苗接種的受試者中使用非侵入式脈波量測,進行為期1分鐘之動脈血壓波形感測和血管光容積感測,並根據受試者之副作用將其分為N組(無副作用)、C組(僅有心臟副作用)、V組(僅有血管副作用)、CV組(有心臟或血管副作用)。
利用40個脈波參數作為分析特徵,本研究使用兩種分類方法:(1)機器學習(ML)分析,使用脈波參數作為指標進行訓練,和本實驗室自主開發之(2)脈波分佈區間分析法。結果顯示接種後脈波特徵呈現明顯變化,這些變化對BPW和PPG頻域有顯著影響。而PDA分析之AUC達到0.76,明顯優於ML方法,且在評分指標上顯示更佳之結果。此外,各種因素均未對分類性能產生明顯之干擾效應。
目前研究結果指出,疫苗可能會引起血管僵硬性變化,導致血管彈性特性產生局部不匹配。本研究之成果有助於快速檢測與疫苗接種後心血管副作用相關之血管特性變化,對於穿戴式脈波量測系統於監測心血管副作用方面提供了新的方向。


Vaccination plays a crucial role in controlling the COVID-19 pandemic, yet there is a risk of cardiovascular side effects. This study builds upon the findings related to side effects of the BNT vaccine. Non-invasive pulse wave measurements and frequency domain analysis were employed to investigate the cardiovascular impact post-vaccination of the Moderna COVID‑19 vaccine (mRNA-127) and the Oxford–AstraZeneca COVID-19 vaccine (AZD1222).
For this research, non-invasive pulse wave measurements were taken on 251 subjects who received the vaccine, carrying out a 1-minute arterial blood pressure waveform detection and blood vessel photoplethysmography. Based on the side effects experienced by the participants, they were categorized into N group (no side effects), C group (only cardiac side effects), V group (only vascular side effects), and CV group (both cardiac and vascular side effects).
Utilizing 40 pulse wave parameters as analytical features, two classification methods were adopted in this study: (1) Machine Learning (ML) analysis, using pulse wave parameters as training indicators, and (2) Pulse Distribution Interval Analysis method developed independently by our laboratory. The results revealed significant variations in pulse wave characteristics post-vaccination, impacting both the BPW and PPG frequency domains. The AUC for the PDA analysis reached 0.76, significantly outperforming the ML method, showing superior results in scoring metrics. Furthermore, various factors didn't show notable interference effects on classification performance.
Current findings suggest that vaccines may induce vascular stiffness changes, leading to localized mismatches in vascular elasticity properties. The results of this study assist in rapidly detecting vascular characteristic changes related to cardiovascular side effects post-vaccination, offering a novel direction for wearable pulse wave measurement systems in monitoring cardiovascular side effects.

目錄 論文摘要 II Abstract III 致謝 IV 目錄 VII 圖目錄 IX 表目錄 XIII 第1章 緒論 1 1.1 研究背景 1 1.2 研究動機與目標 2 第2章 研究方法 3 2.1 實驗設計和數據收集 3 2.1.1 收案前測 3 2.1.2 收案後測 4 2.2 穿戴式脈波量測裝置之技術及其應用 10 2.2.1 心電訊號描述放大器(Electrocardiography, ECG) 11 2.2.2 動脈血壓波形感測器(Blood Pressure Waveform, BPW) 12 2.2.3 血管光容積感測器(Photoplethysmography, PPG) 15 2.2.4 資料擷取系統(Data Acquisition, DAQ)與訊號擷取介面 18 2.3 分析架構與流程 20 2.4 訊號切波與波形 22 2.5 BPW、PPG頻域參數 23 2.6 機器學習 24 2.7 脈波分佈區間分析法(Pulse Distribution Analysis, PDA) 27 第3章 研究結果 29 3.1 時域波形圖 29 3.2 頻域參數比較 31 3.2.1 BPW頻域參數 31 3.2.2 PPG頻域參數 47 3.3 干擾因素 57 3.3.1 BPW頻域參數 57 3.3.2 PPG頻域參數 62 3.4 線性回歸 66 3.4.1 BPW頻域參數 66 3.4.2 PPG頻域參數 70 第4章 結果討論 73 4.1 脈波參數變化 73 4.1.1 BPW頻域參數 73 4.1.2 PPG頻域參數 73 4.2 機器學習分析結果 76 4.2.1 BPW頻域參數 76 4.3 脈波分佈區間分析法之結果 79 4.3.1 BPW頻域參數 79 4.3.2 PPG頻域參數 81 4.4 干擾因素 84 4.4.1 Moderna-BPW頻域參數 84 4.4.2 Moderna-PPG頻域參數 85 4.5 線性回歸 87 4.5.1 Moderna-BPW頻域參數 87 4.5.2 Moderna-PPG頻域參數 88 第5章 研究結論 90 第6章 參考文獻 91

參考文獻
[1] Foo, R.; Wang, Y.; Zimmermann, W.H.; Backs, J.; Wang, D.W. Cardiovascular molecular mechanisms of disease with COVID-19. J. Mol. Cell Cardiol. 2020, 147, 64–73, doi:10.1016/j.yjmcc.2020.09.006.
[2] Dolgin, E. The tangled history of mRNA vaccines. Nature Biotechnology 2020, 38 (12), 1414-1418. doi:10.1038/s41587-020-00756-6.
[3] Polack, F. P.; Thomas, S. J.; Kitchin, N.; et al. Safety and Efficacy of the BNT162b2 mRNA Covid-19 Vaccine. N Engl J Med 2020, 383 (27), 2603-2615. doi:10.1056/NEJMoa2034577.
[4] Voysey, M.; Clemens, S. A. C.; Madhi, S. A.; et al. Safety and efficacy of the ChAdOx1 nCoV-19 vaccine (AZD1222) against SARS-CoV-2: an interim analysis of four randomised controlled trials in Brazil, South Africa, and the UK. Lancet 2021, 397 (10269), 99-111. doi:10.1016/S0140-6736(20)32661-1.
[5] Korber, B.; Fischer, W. M.; Gnanakaran, S.; et al. Tracking changes in SARS-CoV-2 Spike: evidence that D614G increases infectivity of the COVID-19 virus. Cell 2020, 182 (4), 812-827.e19. doi:10.1016/j.cell.2020.06.043.
[6] Su, H. C.; Anderson, D. E.; Young, B. E.; et al. Discovery and Genomic Characterization of a 382-Nucleotide Deletion in ORF7b and ORF8 during the Early Evolution of SARS-CoV-2. mBio 2020, 11 (4), e01610-20. doi:10.1128/mBio.01610-20.
[7] Fazlollahi, A.; Zahmatyar, M.; Noori, M.; Nejadghaderi, S.A.; Sullman, M.J.M.; Shekarriz-Foumani, R.; Kolahi, A.A.; Singh, K.; Safiri, S. Cardiac complications following mRNA COVID-19 vaccines: A systematic review of case reports and case series. Rev. Med. Virol. 2022, e2386, https://doi.org/10.1002/rmv.2386.
[8] Gargano, J. W.; Wallace, M.; Hadler, S. C. Use of mRNA COVID-19 Vaccine After Reports of Myocarditis Among Vaccine Recipients: Update from the Advisory Committee on Immunization Practices — United States, June 2021. MMWR. Morbidity and Mortality Weekly Report 2020, 70. doi:10.15585/mmwr.mm7027e2.
[9] Yoganathan, A.; Sajjad, M.S.; Harky, A. Cardiovascular disease and the impact of COVID-19. J. Card. Surg. 2020, 35, 1988–2001, doi:10.1111/jocs.14694.

[10] McNeil, M. M.; DeStefano, F. Vaccine-associated hypersensitivity. Journal of Allergy and Clinical Immunology 2020, 125 (2), 409-417. doi:10.1016/j.jaci.2018.12.988.
[11] Ravichandran, B.; Grimm, D.; Krüger, M.; Kopp, S.; Infanger, M.; Wehland, M. SARS-CoV-2 and hypertension. Physiol. Rep. 2021, 9, e14759, doi:10.14814/phy2.14759.
[12] Kharod, A. M.; Ramlogan, S.; Ross, P. A.; et al. Pediatric prehospital pulse oximetry use in the United States. Prehospital Emergency Care 2018, 22 (6), 718-725. doi:10.1080/10903127.2018.1439980.
[13] Li, C. W.; Syue, L. S.; Tsai, Y. S.; Li, M. C.; Lo, C. I.; Tsai, C. N.; et al. An overview of point-of-care ultrasound for soft tissue and musculoskeletal applications in an emergency department. Journal of the Intensive Care Society 2021, 22 (3), 255-263. doi:10.1177/1751143720967599.
[14] Saberian, P.; Mireskandari, S. M.; Baratloo, A. Comparing the efficacy of four different methods of pulse measurement in atrial fibrillation. Turkish Journal of Emergency Medicine 2021, 21 (2), 77-82. doi:10.4103/2452-2473.314667.
[15] Chen, C.-C.; Chang, C.-K.; Chiu, C.-C.; Yang, T.-Y.; Hao, W.-R.; Lin, C.-H.; Fang, Y.-A.; Jian, W.; Hsu, M.-H.; Yang, T.-L.; et al. Machine Learning Analyses Revealed Distinct Arterial Pulse Variability According to Side Effects of Pfizer-BioNTech COVID-19 Vaccine (BNT162b2). J. Clin. Med. 2022, 11, 6119. https://doi.org/10.3390/jcm11206119.
[16] Wu, L.W., OuYoung, T., Chiu, Y.C. et al. Discrimination between possible sarcopenia and metabolic syndrome using the arterial pulse spectrum and machine-learning analysis. Sci Rep 12, 21452 (2022). https://doi.org/10.1038/s41598-022-26074-5.
[17] 楊舒涵. 都卜勒微循環血流與動脈血壓波形指標應用於代謝症候群之研究. 國立臺灣科技大學醫學工程研究所碩士論文, 2015. 台北市.
[18] Hsiu, H.; Hsu, C.L.; Chen, C.T.; Hsu, W.C.; Lin, F.C. Effects of acupuncture on the harmonic components of the radial arterial blood-pressure waveform in stroke patients. Biorheology. 2013, 50, 293–309, doi:10.3233/BIR-130642.
[19] 許家良. 血壓波形的諧波分析應用於多囊性卵巢及中風之偵測及療效評估研究. 國立臺灣科技大學應用科技研究所博士論文, 2014. 台北市.
[20] 柳毅謙. 脈波量測穿戴式系統親和可靠提升整合之研究. 國立臺灣科技大學醫學工程研究所碩士論文, 2021. 台北市.
[21] 劉人銘. 循環量測應用於服用高血壓藥物患者之研究. 國立臺灣科技大學醫學工程研究所碩士論文, 2018. 台北市.
[22] Dagliati A, Marini S, Sacchi L, Cogni G, Teliti M, Tibollo V, De Cata P, Chiovato L, Bellazzi R. Machine Learning Methods to Predict Diabetes Complications. J Diabetes Sci Technol. 2018; 12(2): 295-302.
[23] Ellahham S. Artificial Intelligence: The Future for Diabetes Care. Am J Med. 2020; 133(8): 895-900.
[24] Sorelli M, Perrella A, Bocchi L. Detecting vascular age using the analysis of peripheral pulse. IEEE Trans Biomed Eng. 2018; 65(12): 2742-2750.
[25] 邱昱植. 結合穿戴式脈波量測、機器學習與脈波分佈區間分析(PDA)應用於肌少症早期評估及探討. 國立臺灣科技大學醫學工程研究所碩士論文, 2022. 台北市.
[26] 張哲愷. 穿戴式脈波量測系統結合機器學習與脈波變異度分析應用於新冠肺炎疫苗之心血管副作用監測. 國立臺灣科技大學醫學工程研究所碩士論文, 2022. 台北市.
[27] Lin, Y.-J.; Lee, C.-C.; Huang, T.-W.; Hsu, W.-C.; Wu, L.-W.; Lin, C.-C.; Hsiu, H. Using Arterial Pulse and Laser Doppler Analyses to Discriminate between the Cardiovascular Effects of Different Running Levels. Sensors 2023, 23, 3855. https://doi.org/10.3390/s23083855
[28] Sharif Naeini, R.; Cahalan, M. D. Arterial Pulse Waveform Characteristics Difference Between Diabetic and Non-Diabetic Individuals: A Case Study. Frontiers in Physiology 2021, 12. doi:10.3389/fphys.2021.675499.
[29] 翁婉玲. 穿戴式脈波量測系統結合機器學習於失智症及社區場域心智健康狀態評估. 國立臺灣科技大學醫學工程研究所碩士論文, 2021. 台北市.
[30] 陳冠彰. 循環訊號量測應用於乳癌患者病程監控之研究. 國立臺灣科技大學醫學工程研究所碩士論文, 2016. 台北市.
[31] Ridker PM, Bhatt DL, Pradhan AD, Glynn RJ, MacFadyen JG, Nissen SE; PROMINENT, REDUCE-IT, and STRENGTH Investigators. Inflammation and cholesterol as predictors of cardiovascular events among patients receiving statin therapy: a collaborative analysis of three randomised trials. Lancet. 2023; 401(10384): 1293-1301.
[32] Egan BM, Li J, Qanungo S, Wolfman TE. Blood pressure and cholesterol control in hypertensive hypercholesterolemic patients: national health and nutrition examination surveys 1988-2010. Circulation. 2013; 128(1): 29-41.
[33] Zheng M, Zhang X, Chen S, Song Y, Zhao Q, Gao X, Wu S. Arterial Stiffness Preceding Diabetes: A Longitudinal Study. Circ Res. 2020; 127(12): 1491-1498.
[34] DuPont JJ, Kenney RM, Patel AR, Jaffe IZ. Sex differences in mechanisms of arterial stiffness. Br J Pharmacol. 2019; 176(21): 4208-4225.
[35] Wang Y, Yin L, Hu B, Tse LA, Liu Y, Ma H, Li W. Association of heart rate with cardiovascular events and mortality in hypertensive and normotensive population: a nationwide prospective cohort study. Ann Transl Med. 2021; 9(11): 917.

無法下載圖示 全文公開日期 2028/08/30 (校內網路)
全文公開日期 2028/08/30 (校外網路)
全文公開日期 2028/08/30 (國家圖書館:臺灣博碩士論文系統)
QR CODE