An Innovative algorithm framework for cardiovascular risk assessment based on ECG data

Authors

  • Denghong Zhang Faculty of Health and Medical Sciences, Taylor’s University Lakeside Campus, No. 1, Jalan Taylor’s, 47500 Subang Jaya, Selangor Darul Ehsan, Malaysia Author https://orcid.org/0000-0002-9342-9978
  • Benjamin Samraj Prakash Earnest Faculty of Health and Medical Sciences, Taylor’s University Lakeside Campus, No. 1, Jalan Taylor’s, 47500 Subang Jaya, Selangor Darul Ehsan, Malaysia Author https://orcid.org/0009-0000-8342-4332
  • Ihab Elsayed Mohamed Ali Abdou Faculty of Health and Medical Sciences, Taylor’s University Lakeside Campus, No. 1, Jalan Taylor’s, 47500 Subang Jaya, Selangor Darul Ehsan, Malaysia Author https://orcid.org/0000-0002-4749-3282

DOI:

https://doi.org/10.56294/dm2025457

Keywords:

Cardiovascular disease (CVD), Risk Assessment, Dynamic Owl Search algorithm-driven Adaptive Long Short-Term Memory (DOS-ALSTM), ECG Data

Abstract

Background:Cardiovascular disease (CVD) is a primary universal physical problem, with conventional prediction systems frequently being persistent and expensive. Modern advancements in machine learning (ML)offer a hopeful option for accurate CVD risk assessment by leveraging multifaceted relations among diverse risk factors.
Aim:Their search proposes a novel deep learning (DL) system, Dynamic Owl Search algorithm-driven Adaptive Long Short-Term Memory (DOS-ALSTM), to enhance cardiovascular risk prediction utilizing electrocardiogram (ECG) data.
Method:The study utilizes ECG data from a diverse population group to train and assess the proposed model. Data is cleaned and normalized employing standard techniques to handle lost values and ensure reliability. Relevant features are extracted using statistical and signal processing technique to detain crucial features from the ECG data. The DOS-ALSTM system integrates a DOS optimization algorithm for optimized parameter regulation and ALSTM networks to detain sequential dependencies in ECG data for accurate risk prediction. The recognized method is evaluated using Python software.
Result:The DOS-ALSTM system demonstrates superior performance with superioraccuracy of 99%, recall of 98%, F1-Score of 97.9% and Precision of 98.8% in CVD risk assessment compared to traditional methods

References

[1] Gooding HC, Gidding SS, Moran AE, Redmond N, Allen NB, Bacha F, Burns TL, Catov JM, Grandner MA, Harris KM, Johnson HM. Challenges and opportunities for the prevention and treatment of cardiovascular disease among young adults: report from a National Heart, Lung, and Blood Institute Working Group. Journal of the American Heart Association. 2020 Oct 6;9(19):e016115.

[2] Kobat H, Elkonaissi I, Foreman E, Davidson M, Idaikkadar P, O'Brien M, Nabhani-Gebara S. Smoking, diabetes mellitus, and previous cardiovascular disease as predictors of anticancer treatment-induced cardiotoxicity in non–small-cell lung cancer: a real-world study. Clinical Lung Cancer. 2024 Jan 1;25(1):e35-42.

[3] Yagi R, Mori Y, Goto S, Iwami T, Inoue K. Routine electrocardiogram screening and cardiovascular disease events in adults. JAMA Internal Medicine. 2024 Sep 1;184(9):1035-44.

[4] Polcwiartek C, Atwater BD, Kragholm K, Friedman DJ, Barcella CA, Attar R, Graff C, Nielsen JB, Pietersen A, Søgaard P, Torp‐Pedersen C. Association between ECG abnormalities and fatal cardiovascular disease among patients with and without severe mental illness. Journal of the American Heart Association. 2021 Jan 19;10(2):e019416.

[5] Xie L, Li Z, Zhou Y, He Y, Zhu J. Computational diagnostic techniques for electrocardiogram signal analysis. Sensors. 2020 Nov 5;20(21):6318.

[6] Rashed-Al-Mahfuz M, Moni MA, Lio’ P, Islam SM, Berkovsky S, Khushi M, Quinn JM. Deep convolutional neural networks based ECG beats classification to diagnose cardiovascular conditions. Biomedical engineering letters. 2021 May;11:147-62.

[7] Karthik S, Santhosh M, Kavitha MS, Paul AC. Automated Deep Learning Based Cardiovascular Disease Diagnosis Using ECG Signals. Computer Systems Science & Engineering. 2022 Jul 1;42(1).

[8] Liu J, Li Z, Fan X, Hu X, Yan J, Li B, Xia Q, Zhu J, Wu Y. CRT-Net: A generalized and scalable framework for the computer-aided diagnosis of Electrocardiogram signals. Applied Soft Computing. 2022 Oct 1;128:109481.

[9] Golande AL, Pavankumar T. Optical electrocardiogram based heart disease prediction using hybrid deep learning. Journal of Big Data. 2023 Sep 9;10(1):139.

[10] Khanna A, Selvaraj P, Gupta D, Sheikh TH, Pareek PK, Shankar V. Internet of things and deep learning enabled healthcare disease diagnosis using biomedical electrocardiogram signals. Expert Systems. 2023 May;40(4):e12864.

[11] Mewada H. 2D-wavelet encoded deep CNN for image-based ECG classification. Multimedia Tools and Applications. 2023 May;82(13):20553-69.

[12] Wasimuddin M, Elleithy K, Abuzneid A, Faezipour M, Abuzaghleh O. Multiclass ECG signal analysis using global average-based 2-D convolutional neural network modeling. Electronics. 2021 Jan 14;10(2):170.

[13] Madan P, Singh V, Singh DP, Diwakar M, Pant B, Kishor A. A hybrid deep learning approach for ECG-based arrhythmia classification. Bioengineering. 2022 Apr 2;9(4):152.

[14] Ahmed AA, Ali W, Abdullah TA, Malebary SJ. Classifying cardiac arrhythmia from ECG signal using 1D CNN deep learning model. Mathematics. 2023 Jan 20;11(3):562.

[15] Abdullah LA, Al-Ani MS. CNN-LSTM based model for ECG arrhythmias and myocardial infarction classification. Adv. Sci. Technol. Eng. Syst. 2020;5(5):601-6.

[16] Chen CY, Lin YT, Lee SJ, Tsai WC, Huang TC, Liu YH, Cheng MC, Dai CY. Automated ECG classification based on 1D deep learning network. Methods. 2022 Jun 1;202:127-35.

[17] Rath A, Mishra D, Panda G, Satapathy SC, Xia K. Improved heart disease detection from ECG signal using deep learning based ensemble model. Sustainable Computing: Informatics and Systems. 2022 Sep 1;35:100732.

[18] Parveen N, Gupta M, Kasireddy S, Ansari MS, Ahmed MN. ECG based one-dimensional residual deep convolutional auto-encoder model for heart disease classification. Multimedia Tools and Applications. 2024 Jan 22:1-27.

[19] Sekhar JC, Roy TL, Sridharan K, Saravanan KA, Taloba AI. Explainable Artificial Intelligence Method for Identifying Cardiovascular Disease with a Combination CNN-XG-Boost Framework. International Journal of Advanced Computer Science & Applications. 2024 May 1;15(5).

[20] Alqahtani A, Alsubai S, Sha M, Vilcekova L, Javed T. Cardiovascular disease detection using ensemble learning. Computational Intelligence and Neuroscience. 2022;2022(1):5267498.

Downloads

Published

2025-01-01

Issue

Section

Original

How to Cite

1.
Zhang denghong, Prakash Earnest BS, Mohamed Ali Abdou IE. An Innovative algorithm framework for cardiovascular risk assessment based on ECG data. Data and Metadata [Internet]. 2025 Jan. 1 [cited 2024 Dec. 9];4:457. Available from: https://dm.ageditor.ar/index.php/dm/article/view/457