簡易檢索 / 詳目顯示
| 研究生： |
王子卿 Wang, Zi-Qing |
|---|---|
| 論文名稱： |
使用穴位皮膚阻抗和光體積描記圖信號進行充血性心力衰竭的檢測和分期：一項可行性研究 Congestive Heart Failure detection and staging using Skin Impedance at acupoints and Photoplethysmogram Signal: a feasibility study |
| 指導教授： |
藍崑展
Lan, Kun-Chan |
| 學位類別： |
碩士 Master |
| 系所名稱： |
電機資訊學院 - 醫學資訊研究所 Institute of Medical Informatics |
| 論文出版年： | 2021 |
| 畢業學年度： | 109 |
| 語文別： | 英文 |
| 論文頁數： | 128 |
| 中文關鍵詞： | 心臟衰竭 、心臟衰竭分期 、穴道皮膚阻抗 、光體積描記圖訊號 、深度學習 、光體積描記圖訊號的襍訊檢測 |
| 外文關鍵詞： | congestive heart failure (CHF), CHF staging, skin impedance at acupoints, photoplethysmography signal, deep learning, PPG noise detection |
| 相關次數： | 點閱：105 下載：10 |
| 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 |
充血性心臟衰竭是一種在老年人群體中常見的心臟疾病，根據症狀的嚴重程度，醫學上根據紐約心臟協會的分期標準可以將其分成四期。第一期幾乎無症狀，但是如果沒有藥物干預的話，患者會在完全不知情的情況下使心臟衰竭發展到第二期或者第三期，并且心臟衰有著較高（發病第一年3.5%）的死亡率。
現有的充血性心臟衰竭分期方式，都需要到醫院才能進行，并且這些方法的費用都很高。我們會提出一種使用深度學習技術的方法，這個方法使用容易收集到的光體積描述訊號（Photoplethysmogram，PPG）與穴道位置的皮膚阻抗（skin Impedance at acupoints，GSR），利用這些收集來的資料訓練一個深度學習模型來進行心臟衰竭的分期。此方法可以使心臟衰竭患者可以在不用去醫院與醫生問診的情況下，隨時掌握自己的病情變化情況。根據現有病患的光體積描述訊號與穴道位置的皮膚阻抗資料進行測試，我們的心臟衰竭深度學習模型使用樣本資料可以獲得93%的分期正確率。以受測者爲單位統計分類結果可以獲得100%的分期正確率。
同時爲了保證用於分期的光體積描述訊號不會受到襍訊干擾，我們也有使用現有的光體積描述訊號訓練一個深度學習模型幫助我們自動分類正常的光體積描述訊號與收到襍訊干擾的光體積描述訊號，實現光體積描述訊號襍訊檢測功能。經過實驗發現我們目前的光體積描述訊號襍訊檢測深度學習模型有96%的檢測正確率。
Congestive heart failure is a common heart disease in the elderly. According to the severity of the symptoms, it can be divided into four stages in medicine according to the staging standards of the New York Heart Association. The first stage is almost asymptomatic, but if there is no drug intervention, the patient will develop heart failure to the second or third stage without knowing it, and heart failure is relatively high (a 3.5% death rate in the first year of onset).
The existing staging methods for CHF require hospital visits and are expensive. In this work, a staging method using deep learning technology is proposed. This method uses easily-collected photoplethysmograms (PPGs) and skin impedance at acupoints using a galvanic skin response (GSR) sensor, and the collected data is used to train a deep learning model to stage heart failure. This method allows patients with heart failure to keep track of changes in their condition without having to go to the hospital for a consultation with a doctor. According to the existing patient's PPG signal and the skin impedance data of the acupoint location, the proposed heart failure deep learning model can obtain a 93% correct rate of staging base on a sample. The statistical classification results based on a subject obtains a 100% correct CHF staging rate.
At the same time, in order to ensure that the PPG signal used for CHF staging will not be interfered with by noise, we also use the existing PPG signal to train a deep learning model to help automatically classify the normal PPG signal and the noise PPG signal and achieve automatic noise detection in the PPG signal. Through experiments, it is found that the PPG noise detection has a classification accuracy of 96%.
1. Arti Patel, Darshna Patel, Congestive heart failure model representing aortic banding induced hypertrophy: A study to analyse extent of pressure overload and alteration in myocardial structure and function,IJC Heart & Vasculature, Volume 34,2021,100755,ISSN 2352-9067,
2. Heart failure in Dowland's Medical Dictionary
3. Heart failure. Health Information. Mayo Clinic. 23 December 2009 [2014-11-07]. DS00061. (Archived from the original on 2010-01-13).
4. Definition of Heart failure. Medical Dictionary. MedicineNet. 27 April 2011 [2014-11-07]. (Archived from the original on 2011-12-08).
5. https://en.wikipedia.org/wiki/New_York_Heart_Association_Functional_Classification
6. MILTON PACKER, M.D Sudden unexpected death in patients with congestive heart failure: a second frontier. 1 Oct 1985 https://doi.org/10.1161/01.CIR.72.4.681Circulation. 1985;72:681–685
7. Patrick D. Evers, Dora K. Farkas, Cathrine F. Hjorth, Michael Khoury, Morten Olsen, Nicolas L. Madsen, Return to work following adverse cardiovascular events in adults with congenital heart disease, International Journal of Cardiology Congenital Heart Disease, Volume 4, 2021, 100160, ISSN 2666-6685, https://doi.org/10.1016/j.ijcchd.2021.100160.
8.https://zh.wikipedia.org/wiki/%E5%BF%83%E8%87%9F%E8%A1%B0%E7%AB%AD
9. G. Angius and L. Raffo, "Cardiovascular disease and sleep apnoea: A wearable device for PPG acquisition and research aims," 2012 Computing in Cardiology, 2012, pp. 513-516.
10. M. Fora, S. Al-Hammouri and A. Al-Zaben, "ECG Abnormality Detection from PPG Signal," 2019 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT), 2019, pp. 103-106, doi: 10.1109/JEEIT.2019.8717512.
11. H. Hsiu, C. Hsu and Tsung-Lin Wu, "A preliminary study on the correlation of frequency components between finger PPG and radial arterial BP waveforms," 2009 International Conference on Biomedical and Pharmaceutical Engineering, 20
12. J. I. Rodriguez-Labra, C. J. Kosik, D. Maddipatla, B. B. Narakathu and M. Z. Atashbar, "Development of a PPG Sensor Array as a Wearable Device to Monitor Cardiovascular Metrics," 2020 IEEE International Conference on Flexible and Printable Sensors and Systems (FLEPS), 2020, pp. 1-4, doi: 10.1109/FLEPS49123.2020.9239440.
13. S. Ghosh, A. Banerjee, N. Ray, P. W. Wood, P. Boulanger and R. Padwal, "Continuous blood pressure prediction from pulse transit time using ECG and PPG signals," 2016 IEEE Healthcare Innovation Point-Of-Care Technologies Conference (HI-POCT), 2016, pp. 188-191, doi: 10.1109/HIC.2016.7797728.
14. Kamat, D.K. & Chavan, A.P. & Patil, P.M.. (2014). Bio-Impedance Measurement System for Analysis of Skin Diseases. IJAIEM. 3. 92-96.
15. Shirley P.C. Ngai, Alice Y.M. Jones, Eric K.W. Cheng, Lung meridian acupuncture point skin impedance in asthma and description of a mathematical relationship with FEV1, Respiratory Physiology & Neurobiology, Volume 179, Issues 2–3, 2011, Pages 187-191, ISSN 1569-9048, https://doi.org/10.1016/j.resp.2011.08.004.
16. Gupta, S.N., Ries, M., Murray, G.J. et al. Skin-impedance in Fabry Disease: A prospective, controlled, non-randomized clinical study. BMC Neurol 8, 41 (2008). https://doi.org/10.1186/1471-2377-8-41
17. S. Ahdi Rezaeieh, K. S. Bialkowski and A. M. Abbosh, "Three-Dimensional Open-Ended Slot Antenna for Heart Failure Detection System Employing Differential Technique," in IEEE Antennas and Wireless Propagation Letters, vol. 13, pp. 1753-1756, 2014, doi: 10.1109/LAWP.2014.2354042.
18. S. Ahdi Rezaeieh, A. Zamani, K. S. Bialkowski and A. M. Abbosh, "Unidirectional Slot-Loaded Loop Antenna With Wideband Performance and Compact Size for Congestive Heart Failure Detection," in IEEE Transactions on Antennas and Propagation, vol. 63, no. 10, pp. 4557-4562, Oct. 2015, doi: 10.1109/TAP.2015.2457935.
19. J. Chen et al., "Blue scale: Early detection of impending congestive heart failure events via wireless daily self-monitoring," 2014 IEEE Healthcare Innovation Conference (HIC), 2014, pp. 63-66, doi: 10.1109/HIC.2014.7038875.
20. Annisa Darmawahyuni, Siti Nurmaini, Meiryka Yuwandini, Muhammad Naufal Rachmatullah, Firdaus Firdaus,Bambang Tutuko,Congestive heart failure waveform classification based on short time-step analysis with recurrent network,Informatics in Medicine Unlocked,Volume 21,2020,100441,ISSN 2352-9148,
21. M. Gharib, M. Beizai and N. R. Saber, "Experimental and computational studies of negative near-wall shear stress in the human aorta and its correlation with various stages of CHF," Proceedings of the Second Joint 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society] [Engineering in Medicine and Biology, 2002, pp. 1254-1255 vol.2, doi: 10.1109/IEMBS.2002.1106374.
22. Giannitsi S, Bougiakli M, Bechlioulis A, Kotsia A, Michalis LK, Naka KK. 6-minute walking test: a useful tool in the management of heart failure patients. Ther Adv Cardiovasc Dis. 2019;13:1753944719870084. doi:10.1177/1753944719870084
23. Andrea Passantino, Rocco Lagioia, Filippo Mastropasqua, Domenico Scrutinio, Short-Term Change in Distance Walked in 6 Min Is an Indicator of Outcome in Patients With Chronic Heart Failure in Clinical Practice,Journal of the American College of Cardiology,Volume 48, Issue 1,2006,Pages 99-105,ISSN 0735-1097
24. G. Angius and L. Raffo, "Cardiovascular disease and sleep apnoea: A wearable device for PPG acquisition and research aims," 2012 Computing in Cardiology, 2012, pp. 513-516.
25. S. K. Prabhakar, H. Rajaguru and S. Lee, "Metaheuristic-Based Dimensionality Reduction and Classification Analysis of PPG Signals for Interpreting Cardiovascular Disease," in IEEE Access, vol. 7, pp. 165181-165206, 2019, doi: 10.1109/ACCESS.2019.2950220.
26. M. Fora, S. Al-Hammouri and A. Al-Zaben, "ECG Abnormality Detection from PPG Signal," 2019 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT), 2019, pp. 103-106, doi: 10.1109/JEEIT.2019.8717512.
27. S. Ghosh, A. Banerjee, N. Ray, P. W. Wood, P. Boulanger and R. Padwal, "Continuous blood pressure prediction from pulse transit time using ECG and PPG signals," 2016 IEEE Healthcare Innovation Point-Of-Care Technologies Conference (HI-POCT), 2016, pp. 188-191, doi: 10.1109/HIC.2016.7797728.
28. D. Yang, J. Zhu and P. Zhu, "SpO2 and heart rate measurement with wearable watch based on PPG," 2015 IET International Conference on Biomedical Image and Signal Processing (ICBISP 2015), 2015, pp. 1-5, doi: 10.1049/cp.2015.0784.
29. Gerosa M, Zimlichman E, Ventura D, Fanelli V, Riboldi P, Meroni P. Measurement of Electrical Skin Impedance of Dermal-Visceral Zones as a Diagnostic Tool for Disorders of the Immune System. Lupus. 2006;15(7):457-461. doi:10.1191/0961203306lu2333oa
30. Weitzen R, Epstein N, Shoenfeld Y, Zimlichman E. Diagnosing diseases by measurement of electrical skin impedance: a novel technique. Ann N Y Acad Sci. 2007 Aug;1109:185-92. doi: 10.1196/annals.1398.022. PMID: 17785305.
31. Gupta, S.N., Ries, M., Murray, G.J. et al. Skin-impedance in Fabry Disease: A prospective, controlled, non-randomized clinical study. BMC Neurol 8, 41 (2008). https://doi.org/10.1186/1471-2377-8-41
32. Walter-Kroker, A., Kroker, A., Mattiucci-Guehlke, M. et al. A practical guide to bioelectrical impedance analysis using the example of chronic obstructive pulmonary disease. Nutr J 10, 35 (2011). https://doi.org/10.1186/1475-2891-10-35
33. Shirley P.C. Ngai, Alice Y.M. Jones, Eric K.W. Cheng, Lung meridian acupuncture point skin impedance in asthma and description of a mathematical relationship with FEV1, Respiratory Physiology & Neurobiology, Volume 179, Issues 2–3, 2011, Pages 187-191, ISSN 1569-9048, https://doi.org/10.1016/j.resp.2011.08.004.
34. Shirley P.C. Ngai and Alice Y.M. Jones.The Journal of Alternative and Complementary Medicine.Jun 2013.558-563.http://doi.org/10.1089/acm.2012.0097
35. Nakatani Y. Skin electric resistance and ryodoraku. J Autonom Nerv Syst. 1956;6:52
36. D. Wulsin, J. Blanco, R. Mani and B. Litt, "Semi-Supervised Anomaly Detection for EEG Waveforms Using Deep Belief Nets," 2010 Ninth International Conference on Machine Learning and Applications, 2010, pp. 436-441, doi: 10.1109/ICMLA.2010.71.
37. M. Munir, S. A. Siddiqui, A. Dengel and S. Ahmed, "DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series," in IEEE Access, vol. 7, pp. 1991-2005, 2019, doi: 10.1109/ACCESS.2018.2886457.
38. E. Haselsteiner and G. Pfurtscheller, "Using time-dependent neural networks for EEG classification," in IEEE Transactions on Rehabilitation Engineering, vol. 8, no. 4, pp. 457-463, Dec. 2000, doi: 10.1109/86.895948.
39. F. Cheng et al., "Research on Satellite Power Anomaly Detection Method Based on LSTM," 2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA), 2021, pp. 706-710, doi: 10.1109/ICPECA51329.2021.9362601.
40. P. Cheng, Z. Chen, Q. Li, Q. Gong, J. Zhu and Y. Liang, "Atrial Fibrillation Identification With PPG Signals Using a Combination of Time-Frequency Analysis and Deep Learning," in IEEE Access, vol. 8, pp. 172692-172706, 2020.
41. G. Cámbara, J. Luque and M. Farrús, "Detection of Speech Events and Speaker Characteristics through Photo-Plethysmographic Signal Neural Processing," ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2020.
42. J. Van Zaen et al., "Atrial Fibrillation Detection from PPG Interbeat Intervals via a Recurrent Neural Network," 2019 Computing in Cardiology (CinC), Singapore, Singapore, 2019.
43.KirstinAschbacher,DefneYilmaz,YanivKerem,StuartCrawford,DavidBenaron,JiaqiLiu,MeghanEaton,Geoffrey H.Tison,JeffreyE.OlginMDYihanLiDPhil,Gregory M.MarcusMD, "Atrial fibrillation detection from raw photoplethysmography waveforms: A deep learning application"，2666-5018/© 2020 Heart Rhythm Society. Published by Elsevier Inc.
44. J. Zhou et al., "Cohesive Multi-modality Feature Learning and Fusion for COVID-19 Patient Severity Prediction," in IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2021.3063952.
45. Kuan Liu, Yanen Li, Ning Xu, Prem Natarajan,“Learn to Combine Modalities in Multimodal Deep Learning”, Subjects: Machine Learning (stat.ML); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)Cite as:arXiv:1805.11730 [stat.ML]
46. S. Nawaz, A. Calefati, M. Caraffini, N. Landro and I. Gallo, “Are These Birds Similar: Learning Branched Networks for Fine-grained Representations,” 2019 International Conference on Image and Vision Computing New Zealand (IVCNZ), Dunedin, New Zealand, 2019, pp. 1-5, doi: 10.1109/IVCNZ48456.2019.8960960.
47. ShuhuiBu, LeiWang, PengchengHan, ZhenbaoLiu, KeLi, “3D shape recognition and retrieval based on multi-modality deep learning”, Neurocomputing Volume 259, 11 October 2017, Pages 183-193
48. N. Arya and S. Saha, "Multi-modal classification for human breast cancer prognosis prediction: Proposal of deep-learning based stacked ensemble model," in IEEE/ACM Transactions on Computational Biology and Bioinformatics, doi: 10.1109/TCBB.2020.3018467.
49. Bingxin Gu, Mingyuan Meng, Lei Bi, Jinman Kim, David Dagan Feng, Shaoli Song, “Prediction of 5-year Progression-Free Survival in Advanced Nasopharyngeal Carcinoma with Pretreatment PET/CT using Multi-Modality Deep Learning-based Radiomics”, Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Applications (stat.AP), Cite as:arXiv:2103.05220 [eess.IV]
50. LinDu, XiongYou, KeLi, LiqiuMeng, GongCheng, LiyangXiong, GuangxiaWang, “Multi-modal deep learning for landform recognition”, ISPRS Journal of Photogrammetry and Remote Sensing Volume 158, December 2019, Pages 63-75
51. G. Zeng and G. Zheng, "Multi-stream 3D FCN with multi-scale deep supervision for multi-modality isointense infant brain MR image segmentation," 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, DC, USA, 2018, pp. 136-140, doi: 10.1109/ISBI.2018.8363540.
52. S. Ardianto and H. Hang, "Multi-View and Multi-Modal Action Recognition with Learned Fusion," 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Honolulu, HI, USA, 2018, pp. 1601-1604, doi: 10.23919/APSIPA.2018.8659539.
53. Ozturk TC, Unluer E, Denizbasi A, Guneysel O, Onur O. Can NT-proBNP be used as a criterion for heart failure hospitalization in emergency room?. J Res Med Sci. 2011;16(12):1564-1571.
54. "N-terminal pro-BNP". Archived from the original on 2008-10-11.
55. John Zhang,Effect of Age and Sex on Heart Rate Variability in Healthy Subjects, Journal of Manipulative and Physiological Therapeutics,Volume 30, Issue 5,2007,Pages 374-379,ISSN 0161-4754,https://doi.org/10.1016/j.jmpt.2007.04.001.
56. ARGUELLO-PRADA, Erick Javier. The mountaineer’s method for peak detection in photoplethysmographic signals. Rev.fac.ing.univ. Antioquia [online]. 2019, n.90 [cited 2021-05-25], pp.42-50.
57. Pankaj Malhotra, Lovekesh Vig, Gautam Shroff, Puneet Agarwal, Long Short Term Memory Networks for Anomaly Detection in Time Serieshttp://www.i6doc.com/en/.
58. Wilson S Colucci, MD Horng H Chen, MD Natriuretic peptide measurement in heart failure
59. Lam, Carolyn S.P.a,b,c; Li, Yi-Hengd,*; Bayes-Genis, Antonie; Ariyachaipanich, Aekarachf; Huan, Do Quangg; Sato, Naokih; Kahale, Pravini; Cuong, Ta Manhj; Dong, Yugangk; Li, Xinlil; Zhou, Yanlil The role of N-terminal pro-B-type natriuretic peptide in prognostic evaluation of heart failure Journal of the Chinese Medical Association: June 2019 - Volume 82 - Issue 6 - p 447-451 doi: 10.1097/JCMA.0000000000000102
60. Ozturk TC, Unluer E, Denizbasi A, Guneysel O, Onur O. Can NT-proBNP be used as a criterion for heart failure hospitalization in emergency room?. J Res Med Sci. 2011;16(12):1564-1571.
61. S. Palacios, I. Cygankiewicz, A. Bayés-de-Luna, J. P. Martínez and E. Pueyo, "Sudden Cardiac Death Prediction in Chronic Heart Failure Patients by Periodic Repolarization Dynamics," 2020 Computing in Cardiology, 2020, pp. 1-4, doi: 10.22489/CinC.2020.209.
62. J. Ramírez, M. Orini, E. Pueyo and P. Laguna, "Comparison of ECG T-wave duration and morphology restitution markers for sudden cardiac death prediction in chronic heart failure," 2017 Computing in Cardiology (CinC), 2017, pp. 1-4, doi: 10.22489/CinC.2017.224-267.
63. A. Alqahtani, R. Alshmmari, M. Alzunitan, A. Ahmed, A. Mukhtar and N. Alqahtani, "Predicting Congestive Heart Failure Risk Factors in King Abdulaziz Medical City A Machine Learning Approach," 2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA), 2021, pp. 278-280, doi: 10.1109/CAIDA51941.2021.9425233.
64. Mohammadzadeh N, Safdari R, Baraani A, Mohammadzadeh F. Intelligent data analysis: the best approach for chronic heart failure (CHF) follow up management. Acta Inform Med. 2014;22(4):263-267. doi:10.5455/aim.2014.22.263-267
校內：立即公開校外：2022-09-01公開