臺灣博碩士論文加值系統

研究⽬的
⾎糖與⾎中鉀離⼦濃度異常皆為醫療上常⾒的緊急狀況，嚴重時容易誘發⼼律不整，是病患猝死的重要鑑別診斷之⼀。⼼電圖是懷疑⾼⾎鉀時除了抽⾎檢驗外的必要檢查，然⽽，鉀離⼦異常時的⼼電圖表現變化多端，過去研究顯⽰臨床醫師依照⼼電圖變化來診斷⾼⾎鉀的敏感性僅約三成，這常導致治療處理的延宕，影響病患預後。近年因為電腦計算能⼒的⼤幅進步，⼈⼯智慧應⽤於⼼電圖分析已經有了不錯的成績。近年數個研究利⽤深度學習模型，分析⼼電圖資訊來預測鉀離⼦異常，但在使⽤少數導程的資訊下，多數表現不佳。因此直到今⽇，這些演算法的模型應⽤在單⼀導程⼼電圖監視器的即時偵測上仍相當有限。
本研究欲利⽤深度學習模型結合遷移學習演算法，即時判讀病患⽣理監測系統上單⼀導程⼼電圖之變化，早期偵測⾼⾎鉀的發⽣。

研究⽅法
本研究使⽤⿇省理⼯加護病房⽣理訊號資料庫（MIMIC-III）之⾧時間第⼆導程⼼電圖紀錄，配合資料庫⾎鉀之紀錄，透過演算法給予⼼電圖資料標註與前處理，再利⽤卷積神經網路訓練⾼⾎鉀辨識模型，之後透過輸⼊個⼈化⼼電圖資料進⾏遷移學習，分析個⼈化深度學習模型⽤於辨識⾼⾎鉀之改善程度。

結果
研究結果顯⽰，僅加⼊少量個⼈⼼電圖遷移學習後，對於⾼⾎鉀預測的準確度⾃0.604 ⼤幅提升⾄0.980。操作者特徵曲線下⾯積也⾃0.729上升⾄0.945。

結論
使⽤少量個⼈資料，結合深度神經網路模型與遷移學習演算法後，在單⼀導程⼼電圖上模型能⼤幅改善預測⾼⾎鉀的準確度。這樣的成果未來能進⼀步應⽤於智慧穿戴裝置上，提供⾧時間⾮侵⼊性的⾎鉀變化追蹤。

Introduction
Hyperkalemia, as one of the most common metabolic abnormalities seen in critical
patients will causes cardiotoxic effects and has been associated with a series of
Electrocardiogram (ECG) abnormalities that eventually lead to arrythmia and cardiac
arrest. In clinical practice, the sensitivity of physician readers in the ECG diagnosis of
hyperkalemia has been estimated to be as low as 34% to 43% due to its various
appearance. This condition often resulted in misdiagnosis, delayed medical treatment,
and increased mortality risk of critical ill patients.
Deep learning algorithm allows computer to learn directly from data and has achieved
great progress on assisting diagnosis of cardiac arrythmia, myocardial infarction on ECG.
Several studies had focused on developing deep learning model to recognize dyskalemia
from ECG but none of them demonstrated satisfactory prediction accuracy on single lead
ECG, which was used as continuous monitoring in intensive care unit (ICU). Managing
critical ill patients is a race against time. Early detection of ECG change on hyperkalemia
is crucial to enhance differential diagnosis process. With the assistance from AI, we
believe physicians are able to diagnose early, to provide treatment more efficiently, and
reduce unnecessary blood test on daily practice.
The purpose of this study is to develop and validate a deep learning model to recognize
hyperkalemia from ambulatory ECG monitor in ICU.

Method
Data for this study was generated from Medical Information Mart from Intensive Care
(MIMIC-III), an openly available database developed by Massachusetts Institute of
Technology. We included patients admitted to ICU with multiple serum potassium test
results, and matched ECG data from MIMIC-III database. Lead II ECG from ambulatory
monitor were collected and labeled as hyperkalemia and normal regarding their
corresponding potassium level. We matched and segmented ECG data based on the
timestamp of serum potassium test.
A one-dimensional convolution neural network based deep learning model is first
developed to predict hyperkalemia in a generic population from MIMIC-III database.
Once the model achieved a state-of-art performance, it was then utilized in an active
transfer learning process to perform patient adaptive heartbeat classification tasks.

Result
The results show that by acquiring a few data from each new patient, the personalized
model can improve the accuracy of hyperkalemia detection significantly from an average
of 0.604 ± 0.211 to 0.980 ± 0.078 when compared with the generic model. The Area
Under the receiver operating characteristic Curve level also improved from 0.729 ± 0.240
to 0.945 ± 0.094.

Conclusion
By utilizing deep transfer learning method, we were able to build a clinical standard
model for hyperkalemia detection from ambulatory ECG monitor. These findings could
potentially be extended to applications that continuously monitor one''s

論文審定書…………………………………………………………… i
誌謝…………………………………………………………………… ii
中文摘要……………………………………………………………… iii
英文摘要……………………………………………………………… iv
第 一 章 緒論………………………………………………………… 1
1.1 研究緣起……………………………………………………… 1
1.2 研究重要性…………………………………………………… 3
1.3 研究假說與目標……………………………………………… 4
1.4 論文架構概述………………………………………………… 5
第 二 章 文獻回顧………………………………………………… 7
2.1 心電圖的工作原理與醫療應用……………………………… 7
2.2 鉀離子血中濃度與心電圖變化……………………………… 9
2.3 重症病患血鉀與心電圖變化………………………………… 14
2.4 機器學習原理………………………………………………… 15
2.5 心電圖判讀之機器學習應用………………………………… 19
第 三 章 研究方法………………………………………………… 21
3.1 資料蒐集 ………………………………………………………22
3.2 資料前處理 ……………………………………………………23
3.3 訓練深度學習模型 ……………………………………………26
3.4 個人化遷移學習 ………………………………………………27
3.5 分析模型表現 …………………………………………………29
3.6 模型可解釋性與視覺化 ………………………………………30
3.6 研究工具 ………………………………………………………35
第 四 章 研究結果 …………………………………………………37
4.1 病患流行病學特徵………………………………………………38
4.2 一般化模型（Generic Model）訓練評估 ………………………40
4.3 個人化模型（Personal Model）訓練評估 ……………………43
4.4 模型可解釋性與視覺化 ………………………………………45
第 五 章 討論 …………………………………………………………47
5.1 心電圖技術的發展………………………………………………47
5.2 電腦輔助診斷系統的沿革 ……………………………………50
5.3 電腦輔助診斷於心電圖的應用 ………………………………53
5.4 本研究與過往研究比較 ………………………………………54
5.5 研究限制………………………………………………………59
第 六 章 結論與未來展望 ……………………………………………60
參考文獻……………………………………………………………… 61
附錄……………………………………………………………………… 69

[1] K. J. Evans and A. Greenberg, "Hyperkalemia: A Review," Journal of Intensive Care
Medicine, vol. 20, no. 5, pp. 272-290, 2005/09/01 2005, doi:
10.1177/0885066605278969.
[2] C. D. Galloway et al., "Development and validation of a deep-learning model to
screen for hyperkalemia from the electrocardiogram," JAMA cardiology, vol. 4, no.
5, pp. 428-436, 2019.
[3] C.-S. Lin et al., "A deep-learning algorithm (ECG12Net) for detecting hypokalemia
and hyperkalemia by electrocardiography: algorithm development," JMIR medical
informatics, vol. 8, no. 3, p. e15931, 2020.
[4] C. Tan, F. Sun, T. Kong, W. Zhang, C. Yang, and C. Liu, "A survey on deep
transfer learning," in International conference on artificial neural networks, 2018:
Springer, pp. 270-279.
[5] L. Torrey and J. Shavlik, "Transfer learning," in Handbook of research on machine
learning applications and trends: algorithms, methods, and techniques: IGI global,
2010, pp. 242-264.
[6] K. Weimann and T. O. F. Conrad, "Transfer learning for ECG classification,"
Scientific Reports, vol. 11, no. 1, p. 5251, 2021/03/04 2021, doi: 10.1038/s41598-
021-84374-8.
[7] J. K. Cooper, "Electrocardiography 100 years ago. Origins, pioneers, and
contributors," (in eng), N Engl J Med, vol. 315, no. 7, pp. 461-4, Aug 14 1986, doi:
10.1056/nejm198608143150721.
[8] A. Atkielski. "Schematic diagram of normal sinus rhythm for a human heart as seen
on ECG (with English labels)."
https://en.wikipedia.org/wiki/Electrocardiography#/media/File:SinusRhythmLabels.s
vg (accessed.
[9] J. K. Lau et al., "iPhone ECG application for community screening to detect silent
atrial fibrillation: a novel technology to prevent stroke," (in eng), Int J Cardiol, vol.
165, no. 1, pp. 193-4, Apr 30 2013, doi: 10.1016/j.ijcard.2013.01.220.
[10] M. V. Perez et al., "Large-Scale Assessment of a Smartwatch to Identify Atrial
Fibrillation," (in eng), N Engl J Med, vol. 381, no. 20, pp. 1909-1917, Nov 14 2019,
doi: 10.1056/NEJMoa1901183.
[11] Z. Yuan, T. Cai, J. Tian, A. V. Ivanov, D. R. Giovannucci, and Z. Xie, "Na/KATPase
tethers phospholipase C and IP3 receptor into a calcium-regulatory
complex," (in eng), Mol Biol Cell, vol. 16, no. 9, pp. 4034-45, Sep 2005, doi:
10.1091/mbc.e05-04-0295.
[12] M. Zacchia, M. L. Abategiovanni, S. Stratigis, and G. Capasso, "Potassium: From
Physiology to Clinical Implications," (in eng), Kidney Dis (Basel), vol. 2, no. 2, pp.
72-9, Jun 2016, doi: 10.1159/000446268.
[13] S. O. Thier, "Potassium physiology," (in eng), Am J Med, vol. 80, no. 4a, pp. 3-7,
Apr 25 1986, doi: 10.1016/0002-9343(86)90334-7.
[14] L. Bouadma et al., "Influence of dyskalemia at admission and early dyskalemia
correction on survival and cardiac events of critically ill patients," (in eng), Crit
Care, vol. 23, no. 1, p. 415, Dec 19 2019, doi: 10.1186/s13054-019-2679-z.
[15] C. W. Callaway et al., "Part 4: Advanced Life Support: 2015 International Consensus
on Cardiopulmonary Resuscitation and Emergency Cardiovascular Care Science
With Treatment Recommendations," (in eng), Circulation, vol. 132, no. 16 Suppl 1,
pp. S84-145, Oct 20 2015, doi: 10.1161/cir.0000000000000273.
[16] J. L. L. III. "ECG patterns in hyperkalemia."
https://www.msdmanuals.com/professional/endocrine-and-metabolicdisorders/
electrolyte-disorders/hyperkalemia (accessed.
[17] D. B. Diercks, G. M. Shumaik, R. A. Harrigan, W. J. Brady, and T. C. Chan,
"Electrocardiographic manifestations: electrolyte abnormalities," (in eng), J Emerg
Med, vol. 27, no. 2, pp. 153-60, Aug 2004, doi: 10.1016/j.jemermed.2004.04.006.
[18] B. T. Montague, J. R. Ouellette, and G. K. Buller, "Retrospective review of the
frequency of ECG changes in hyperkalemia," (in eng), Clin J Am Soc Nephrol, vol.
3, no. 2, pp. 324-30, Mar 2008, doi: 10.2215/cjn.04611007.
[19] A. Truhlář et al., "European Resuscitation Council Guidelines for Resuscitation
2015: Section 4. Cardiac arrest in special circumstances," (in eng), Resuscitation,
vol. 95, pp. 148-201, Oct 2015, doi: 10.1016/j.resuscitation.2015.07.017.
[20] "5 ECG Changes of Hyperkalemia you Need to Know."
https://acadoodle.com/articles/5-ecg-changes-of-hyperkalemia-you-need-to-know
(accessed.
[21] B. Surawicz, R. Childers, B. J. Deal, and L. S. Gettes, "AHA/ACCF/HRS
Recommendations for the Standardization and Interpretation of the
Electrocardiogram: Part III: Intraventricular Conduction Disturbances A Scientific
Statement From the American Heart Association Electrocardiography and
Arrhythmias Committee, Council on Clinical Cardiology; the American College of
Cardiology Foundation; and the Heart Rhythm Society Endorsed by the International
Society for Computerized Electrocardiology," Journal of the American College of Cardiology, vol. 53, no. 11, pp. 976-981, 2009/03/17/ 2009, doi: https://doi.org/10.1016/j.jacc.2008.12.013.
[22] M. Schulman and R. G. Narins, "Hypokalemia and cardiovascular disease," (in eng),
Am J Cardiol, vol. 65, no. 10, pp. 4E-9E; discussion 22E-23E, Mar 6 1990, doi:
10.1016/0002-9149(90)90244-u.
[23] F. Weber and F. Lehmann-Horn, "Hypokalemic periodic paralysis," 2018.
[24] A. Pezhouman et al., "Molecular basis of hypokalemia-induced ventricular
fibrillation," Circulation, vol. 132, no. 16, pp. 1528-1537, 2015.
[25] J. N. Weiss, Z. Qu, and K. Shivkumar, "Electrophysiology of Hypokalemia and
Hyperkalemia," (in eng), Circ Arrhythm Electrophysiol, vol. 10, no. 3, Mar 2017,
doi: 10.1161/circep.116.004667.
[26] K. D. Wrenn, C. M. Slovis, and B. S. Slovis, "The ability of physicians to predict
hyperkalemia from the ECG," Annals of emergency medicine, vol. 20, no. 11, pp.
1229-1232, 1991.
[27] Z. Rafique, J. Aceves, I. Espina, F. Peacock, D. Sheikh-Hamad, and D. Kuo, "Can
physicians detect hyperkalemia based on the electrocardiogram?," The American
journal of emergency medicine, vol. 38, no. 1, pp. 105-108, 2020.
[28] E. Nemati and S. Taheri, "Electrocardiographic manifestations of hyperkalemia in
hemodialysis patients," Saudi Journal of Kidney Diseases and Transplantation, vol.
21, no. 3, p. 471, 2010.
[29] O. Ifudu, M. S. Markell, and E. A. Friedman, "Unrecognized pseudohyperkalemia as
a cause of elevated potassium in patients with renal disease," American journal of
nephrology, vol. 12, no. 1-2, pp. 102-104, 1992.
[30] A. Vraets, Y. Lin, and J. L. Callum, "Transfusion-associated hyperkalemia,"
Transfusion medicine reviews, vol. 25, no. 3, pp. 184-196, 2011.
[31] L. Zhang, J. Hou, J. Li, S.-S. Su, and S. Xue, "Roxadustat for the treatment of
anemia in patients with chronic kidney diseases: a meta-analysis," Aging (Albany
NY), vol. 13, no. 13, p. 17914, 2021.
[32] M. A. Raebel, "Hyperkalemia associated with use of angiotensinconverting
enzyme
inhibitors and angiotensin receptor blockers," Cardiovascular therapeutics, vol. 30,
no. 3, pp. e156-e166, 2012.
[33] C.-L. Huang and E. Kuo, "Mechanism of hypokalemia in magnesium deficiency,"
Journal of the American Society of Nephrology, vol. 18, no. 10, pp. 2649-2652,
2007.
[34] A. N. Harris et al., "Mechanism of hyperkalemia-induced metabolic acidosis,"
Journal of the American Society of Nephrology, vol. 29, no. 5, pp. 1411-1425, 2018.
[35] E. E. Cook et al., "Prevalence of Metabolic Acidosis Among Patients with Chronic
Kidney Disease and Hyperkalemia," Advances in therapy, vol. 38, no. 10, pp. 5238-
5252, 2021.
[36] T. M. Mitchell and T. M. Mitchell, Machine learning (no. 9). McGraw-hill New
York, 1997.
[37] P. P. Shinde and S. Shah, "A review of machine learning and deep learning
applications," in 2018 Fourth international conference on computing communication
control and automation (ICCUBEA), 2018: IEEE, pp. 1-6.
[38] M. E. Celebi and K. Aydin, Unsupervised learning algorithms. Springer, 2016.
[39] J. E. Van Engelen and H. H. Hoos, "A survey on semi-supervised learning," Machine
Learning, vol. 109, no. 2, pp. 373-440, 2020.
[40] Y. Li, "Deep reinforcement learning: An overview," arXiv preprint
arXiv:1701.07274, 2017.
[41] Y. LeCun and Y. Bengio, "Convolutional networks for images, speech, and time
series," The handbook of brain theory and neural networks, vol. 3361, no. 10, p.
1995, 1995.
[42] Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to
document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324,
1998, doi: 10.1109/5.726791.
[43] Y. LeCun, "LeNet-5, convolutional neural networks," URL: http://yann. lecun.
com/exdb/lenet, vol. 20, no. 5, p. 14, 2015.
[44] C. Szegedy, S. Ioffe, V. Vanhoucke, and A. A. Alemi, "Inception-v4, inceptionresnet
and the impact of residual connections on learning," in Thirty-first AAAI
conference on artificial intelligence, 2017.
[45] K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image
recognition," in Proceedings of the IEEE conference on computer vision and pattern
recognition, 2016, pp. 770-778.
[46] K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale
image recognition," arXiv preprint arXiv:1409.1556, 2014.
[47] C. Zywietz, H. Atorf, P. Friedrichs, and E. Greiser, "Development of a computerassisted
electrocardiogram evaluation system at the Hannover Medical School,"
Verhandlungen der Deutschen Gesellschaft fur Kreislaufforschung, vol. 37, pp. 450-
455, 1971.
[48] A. LeBlanc and F. Roberge, "Canadian Colloquium on Computer-Assisted
Interpretation of electrocardiograms. 3. Present state of arrhythmia analysis by
computer," Canadian Medical Association Journal, vol. 108, no. 10, p. 1239, 1973.
[49] V. Velagapudi et al., "Computer-assisted image processing 12 lead ECG model to
diagnose hyperkalemia," Journal of Electrocardiology, vol. 50, no. 1, pp. 131-138,
2017/01/01/ 2017, doi: https://doi.org/10.1016/j.jelectrocard.2016.09.001.
[50] A. Y. Hannun et al., "Cardiologist-level arrhythmia detection and classification in
ambulatory electrocardiograms using a deep neural network," Nature medicine, vol.
25, no. 1, pp. 65-69, 2019.
[51] M. Porumb, S. Stranges, A. Pescapè, and L. Pecchia, "Precision medicine and
artificial intelligence: a pilot study on deep learning for hypoglycemic events
detection based on ECG," Scientific reports, vol. 10, no. 1, pp. 1-16, 2020.
[52] Z. I. Attia et al., "Screening for cardiac contractile dysfunction using an artificial
intelligence–enabled electrocardiogram," Nature medicine, vol. 25, no. 1, pp. 70-74,
2019.
[53] M. Lown et al., "Machine learning detection of Atrial Fibrillation using wearable
technology," PLoS One, vol. 15, no. 1, p. e0227401, 2020.
[54] S. Parvaneh, J. Rubin, S. Babaeizadeh, and M. Xu-Wilson, "Cardiac arrhythmia
detection using deep learning: A review," Journal of electrocardiology, vol. 57, pp.
S70-S74, 2019.
[55] I. M. Chiu et al., "Using Deep Transfer Learning to Detect Hyperkalemia From
Ambulatory Electrocardiogram Monitors in Intensive Care Units: Personalized
Medicine Approach," (in eng), J Med Internet Res, vol. 24, no. 12, p. e41163, Dec 5
2022, doi: 10.2196/41163.
[56] R. Mark, "The Story of MIMIC," in Secondary Analysis of Electronic Health
Records, M. I. T. C. Data Ed. Cham: Springer International Publishing, 2016, pp. 43-
49.
[57] Z. Dai, S. Liu, J. Wu, M. Li, J. Liu, and K. Li, "Analysis of adult disease
characteristics and mortality on MIMIC-III," PloS one, vol. 15, no. 4, p. e0232176,
2020.
[58] T. Chen et al., "Prediction of extubation failure for intensive care unit patients using
light gradient boosting machine," IEEE Access, vol. 7, pp. 150960-150968, 2019.
[59] T. Gentimis, A. Ala''J, A. Durante, K. Cook, and R. Steele, "Predicting hospital
length of stay using neural networks on mimic iii data," in 2017 IEEE 15th intl conf
on dependable, autonomic and secure computing, 15th intl conf on pervasive
intelligence and computing, 3rd intl conf on big data intelligence and computing and
cyber science and technology congress (DASC/PiCom/DataCom/CyberSciTech),
2017: IEEE, pp. 1194-1201.
[60] Chire. "Illustration of en:DBSCAN cluster analysis (minPts=3)."
https://zh.wikipedia.org/wiki/DBSCAN#/media/File:DBSCAN-Illustration.svg
(accessed.
[61] M. Ester, H.-P. Kriegel, J. Sander, and X. Xu, "A density-based algorithm for
discovering clusters in large spatial databases with noise," in kdd, 1996, vol. 96, no.
34, pp. 226-231.
[62] A. Milchevski and M. Gusev, "Performance evaluation of FIR and IIR filtering of
ECG signals," in International Conference on ICT Innovations, 2016: Springer, pp.
103-112.
[63] d. lopez, "RNN, LSTM & GRU," vol. 2023, ed, 2020.
[64] S. Singh, S. K. Pandey, U. Pawar, and R. R. Janghel, "Classification of ECG
arrhythmia using recurrent neural networks," Procedia computer science, vol. 132,
pp. 1290-1297, 2018.
[65] M. Cherti, "Deep generative neural networks for novelty generation: a foundational
framework, metrics and experiments," Université Paris-Saclay, 2018.
[66] S. Narkhede, "Understanding AUC - ROC Curve," in Understanding AUC - ROC
Curve vol. 2023, ed. Medium, 2018.
[67] A. P. Bradley, "The use of the area under the ROC curve in the evaluation of
machine learning algorithms," Pattern Recognition, vol. 30, no. 7, pp. 1145-1159,
1997/07/01/ 1997, doi: https://doi.org/10.1016/S0031-3203(96)00142-2.
[68] B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba, "Learning deep
features for discriminative localization," in Proceedings of the IEEE conference on
computer vision and pattern recognition, 2016, pp. 2921-2929.
[69] R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra,
"Grad-cam: Visual explanations from deep networks via gradient-based localization,"
in Proceedings of the IEEE international conference on computer vision, 2017, pp.
618-626.
[70] M. Sheeny, A. Wallace, and S. Wang, "300 GHz radar object recognition based on
deep neural networks and transfer learning," IET Radar, Sonar & Navigation, vol.
14, no. 10, pp. 1483-1493, 2020.
[71] S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural computation,
vol. 9, no. 8, pp. 1735-1780, 1997.
[72] M. AlGhatrif and J. Lindsay, "A brief review: history to understand fundamentals of
electrocardiography," (in eng), J Community Hosp Intern Med Perspect, vol. 2, no.
1, 2012, doi: 10.3402/jchimp.v2i1.14383.
[73] M. Barton. "WILLEM EINTHOVEN AND THE ELECTROCARDIOGRAM."
https://www.pastmedicalhistory.co.uk/willem-einthoven-and-the-electrocardiogram/
(accessed.
[74] A. Mubarik and A. M. Iqbal, "Holter Monitor," in StatPearls. Treasure Island (FL):
StatPearls Publishing
Copyright © 2022, StatPearls Publishing LLC., 2022.
[75] K. Ioannou, M. Ignaszewski, and I. Macdonald, "Ambulatory electrocardiography:
the contribution of Norman Jefferis Holter," BC Med. J, vol. 56, no. 2, pp. 86-89,
2014.
[76] K.-P. Adlassnig, "A fuzzy logical model of computer-assisted medical diagnosis,"
Methods of Information in Medicine, vol. 19, no. 03, pp. 141-148, 1980.
[77] H.-P. Chan, K. Doi, C. J. Vyborny, K.-L. Lam, and R. A. Schmidt, "Computer-aided
detection of microcalcifications in mammograms methodology and preliminary
clinical study," Investigative Radiology, vol. 23, no. 9, pp. 664-671, 1988.
[78] K. Doi, "Computer-aided diagnosis in medical imaging: historical review, current
status and future potential," (in eng), Comput Med Imaging Graph, vol. 31, no. 4-5,
pp. 198-211, Jun-Jul 2007, doi: 10.1016/j.compmedimag.2007.02.002.
[79] V. Jahmunah et al., "Computer-aided diagnosis of congestive heart failure using
ECG signals - A review," (in eng), Phys Med, vol. 62, pp. 95-104, Jun 2019, doi:
10.1016/j.ejmp.2019.05.004.
[80] J. Schläpfer and J. Wellens Hein, "Computer-Interpreted Electrocardiograms,"
Journal of the American College of Cardiology, vol. 70, no. 9, pp. 1183-1192,
2017/08/29 2017, doi: 10.1016/j.jacc.2017.07.723.
[81] W. C. Tzeng, Y. Z. Chan, and J. C. Hsieh, "Predicting hyperkalemia by the use of a
12-lead temporal-spatial electrocardiograph: clinical evaluations and model
simulations," in Computers in Cardiology, 2005, 25-28 Sept. 2005 2005, pp. 215-
218, doi: 10.1109/CIC.2005.1588075.
[82] C.-X. Wang et al., "Development and validation of a deep learning model to screen
hypokalemia from electrocardiogram in emergency patients," Chinese medical
journal, vol. 134, no. 19, pp. 2333-2339, 2021.
[83] E. Urtnasan, J. H. Lee, B. Moon, H. Y. Lee, K. Lee, and H. Youk, "Noninvasive
Screening Tool for Hyperkalemia Using a Single-Lead Electrocardiogram and Deep
Learning: Development and Usability Study," JMIR Medical Informatics, vol. 10,
no. 6, p. e34724, 2022.
[84] M.-H. Wu, E. J. Chang, and T.-H. Chu, "Personalizing a generic ECG heartbeat
classification for arrhythmia detection: a deep learning approach," in 2018 IEEE
Conference on Multimedia Information Processing and Retrieval (MIPR), 2018:
IEEE, pp. 92-99.
[85] M. S. Milivojević, A. Gavrovska, and I. Reljin, "Biometric Clustering of ECG
using Wave Peaks," in 2018 14th Symposium on Neural Networks and Applications
(NEUREL), 2018: IEEE, pp. 1-4.
[86] T.-W. Shen, "Applied ECG biometric technology for disability population
personalization," in Proceedings of the 2nd International Convention on
Rehabilitation Engineering & Assistive Technology, 2008, pp. 103-107.
[87] Y. Zhang, Z. Xiao, Z. Guo, and Z. Wang, "ECG-based personal recognition using a
convolutional neural network," Pattern Recognition Letters, vol. 125, pp. 668-676,
2019/07/01/ 2019, doi: https://doi.org/10.1016/j.patrec.2019.07.009.
[88] A. Lourenço, H. Silva, and C. Carreiras, "Outlier detection in non-intrusive ECG
biometric system," in International Conference Image Analysis and Recognition,
2013: Springer, pp. 43-52.
[89] M. Ahmed, A. N. Mahmood, and M. R. Islam, "A survey of anomaly detection
techniques in financial domain," Future Generation Computer Systems, vol. 55, pp.
278-288, 2016.
[90] R. Röhrig, "Semantic Anomaly Detection in Medical Time Series," in German
Medical Data Sciences: Bringing Data to Life: Proceedings of the Joint Annual
Meeting of the German Association of Medical Informatics, Biometry and
Epidemiology (gmds EV) and the Central European Network-International Biometric
Society (CEN-IBS) 2020 in Berlin, Germany, 2021, vol. 278: IOS Press, p. 118.
[91] R. Domingues, M. Filippone, P. Michiardi, and J. Zouaoui, "A comparative
evaluation of outlier detection algorithms: Experiments and analyses," Pattern
recognition, vol. 74, pp. 406-421, 2018.
[92] S. L. Joshi, R. A. Vatti, and R. V. Tornekar, "A survey on ECG signal denoising
techniques," in 2013 International Conference on Communication Systems and
Network Technologies, 2013: IEEE, pp. 60-64.
[93] C. Haritha, M. Ganesan, and E. Sumesh, "A survey on modern trends in ECG noise
removal techniques," in 2016 International Conference on Circuit, Power and
Computing Technologies (ICCPCT), 2016: IEEE, pp. 1-7.
[94] S. Nurmaini, A. Darmawahyuni, A. N. Sakti Mukti, M. N. Rachmatullah, F. Firdaus,
and B. Tutuko, "Deep learning-based stacked denoising and autoencoder for ECG
heartbeat classification," Electronics, vol. 9, no. 1, p. 135, 2020.
[95] K. Antczak, "Deep recurrent neural networks for ECG signal denoising," arXiv
preprint arXiv:1807.11551, 2018.