Pre-Processing techniques and artificial intelligence algorithms for electrocardiogram (ECG) signals analysis: A comprehensive review
Electrocardiogram (ECG) are the physiological signals and a standard test to measure the heart’s electrical activity that depicts the movement of cardiac muscles. A review study has been conducted on ECG signals analysis with the help of artificial intelligence (AI) methods over the last ten years i...
Gespeichert in:
Veröffentlicht in: | Computers in biology and medicine 2024-03, Vol.170, p.107908-107908, Article 107908 |
---|---|
Hauptverfasser: | , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 107908 |
---|---|
container_issue | |
container_start_page | 107908 |
container_title | Computers in biology and medicine |
container_volume | 170 |
creator | Safdar, Muhammad Farhan Nowak, Robert Marek Pałka, Piotr |
description | Electrocardiogram (ECG) are the physiological signals and a standard test to measure the heart’s electrical activity that depicts the movement of cardiac muscles. A review study has been conducted on ECG signals analysis with the help of artificial intelligence (AI) methods over the last ten years i.e., 2012–22. Primarily, the method of ECG analysis by software systems was divided into classical signal processing (e.g. spectrograms or filters), machine learning (ML) and deep learning (DL), including recursive models, transformers and hybrid. Secondly, the data sources and benchmark datasets were depicted. Authors grouped resources by ECG acquisition methods into hospital-based portable machines and wearable devices. Authors also included new trends like advanced pre-processing, data augmentation, simulations and agent-based modeling.
The study found improvement in ECG examination perfection made each year through ML, DL, hybrid models, and transformers. Convolutional neural networks and hybrid models were more targeted and proved efficient. The transformer model extended the accuracy from 90% to 98%. The Physio-Net library helps acquire ECG signals, including the popular benchmark databases such as MIT-BIH, PTB, and challenging datasets. Similarly, wearable devices have been established as a appropriate option for monitoring patient health without the time and place limitations and are also helpful for AI model calibration with so far accuracy of 82%–83% on Samsung smartwatch. In the pre-processing signals, spectrogram generation through Fourier and wavelet transformations are erected leading approaches promoting on average accuracy of 90%–95%. Likewise, data enhancement using geometrical techniques is well-considered; however, extraction and concatenation-based methods need attention. As the what-if analysis in healthcare or cardiac issues can be performed using a complex simulation, the study reviews agent-based modeling and simulation approaches for cardiovascular risk event assessment.
•Improvement comes from advanced algorithms, replacing classical ML with deep learning: hybrid models, transformers.•Convolutional neural networks and hybrid models were more targeted and found productive.•In signal pre-processing, Fourier and wavelet transformations dominate for spectrogram generation.•Enhancing signals via extraction, concatenation methods, and single-channel ECG reliability from wearables needs further exploration.•Exploring PPG signals in addition to |
doi_str_mv | 10.1016/j.compbiomed.2023.107908 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2929032999</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0010482523013732</els_id><sourcerecordid>2928852450</sourcerecordid><originalsourceid>FETCH-LOGICAL-c347t-b7349ec3d748bc85367e233ebca05bf17be90c8c59917617b18ddef243e9b5223</originalsourceid><addsrcrecordid>eNqFkc1u1DAUhS0EokPhFZAlNmWRwT_J2GZXRm1BqkQXsLYc5yZzR0k82JmiPgDvXVvTCokNK8v2d3_OOYRQztac8c2n_dqH6dBimKBbCyZkflaG6RdkxbUyFWtk_ZKsGOOsqrVozsiblPaMsZpJ9pqcSS24MkquyJ-7CNVdDB5SwnmgC_jdjL-OkKibO-rigj16dCPFeYFxxAFmD9SNQ4i47KZE-xApjOCX3MTFDsMQ3UQvrrY3H2nCYXZjaeXGh4TpM72kZfMIO5gT3gONcI_w-y151WcO3j2d5-Tn9dWP7dfq9vvNt-3lbeVlrZaqVbI24GWnat163ciNAiEltN6xpu25asEwr31jDFebfOW666AXtQTTNkLIc3Jx6nuIoWhc7ITJZ1luhnBMVhhhmBTGmIx--Afdh2MsagqldSPqhmVKnygfQ0oRenuIOLn4YDmzJSq7t3-jsiUqe4oql75_GnBsy99z4XM2GfhyAiA7kl2KNnks7ncYs922C_j_KY-4d6v5</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2928852450</pqid></control><display><type>article</type><title>Pre-Processing techniques and artificial intelligence algorithms for electrocardiogram (ECG) signals analysis: A comprehensive review</title><source>MEDLINE</source><source>Elsevier ScienceDirect Journals Complete</source><creator>Safdar, Muhammad Farhan ; Nowak, Robert Marek ; Pałka, Piotr</creator><creatorcontrib>Safdar, Muhammad Farhan ; Nowak, Robert Marek ; Pałka, Piotr</creatorcontrib><description>Electrocardiogram (ECG) are the physiological signals and a standard test to measure the heart’s electrical activity that depicts the movement of cardiac muscles. A review study has been conducted on ECG signals analysis with the help of artificial intelligence (AI) methods over the last ten years i.e., 2012–22. Primarily, the method of ECG analysis by software systems was divided into classical signal processing (e.g. spectrograms or filters), machine learning (ML) and deep learning (DL), including recursive models, transformers and hybrid. Secondly, the data sources and benchmark datasets were depicted. Authors grouped resources by ECG acquisition methods into hospital-based portable machines and wearable devices. Authors also included new trends like advanced pre-processing, data augmentation, simulations and agent-based modeling.
The study found improvement in ECG examination perfection made each year through ML, DL, hybrid models, and transformers. Convolutional neural networks and hybrid models were more targeted and proved efficient. The transformer model extended the accuracy from 90% to 98%. The Physio-Net library helps acquire ECG signals, including the popular benchmark databases such as MIT-BIH, PTB, and challenging datasets. Similarly, wearable devices have been established as a appropriate option for monitoring patient health without the time and place limitations and are also helpful for AI model calibration with so far accuracy of 82%–83% on Samsung smartwatch. In the pre-processing signals, spectrogram generation through Fourier and wavelet transformations are erected leading approaches promoting on average accuracy of 90%–95%. Likewise, data enhancement using geometrical techniques is well-considered; however, extraction and concatenation-based methods need attention. As the what-if analysis in healthcare or cardiac issues can be performed using a complex simulation, the study reviews agent-based modeling and simulation approaches for cardiovascular risk event assessment.
•Improvement comes from advanced algorithms, replacing classical ML with deep learning: hybrid models, transformers.•Convolutional neural networks and hybrid models were more targeted and found productive.•In signal pre-processing, Fourier and wavelet transformations dominate for spectrogram generation.•Enhancing signals via extraction, concatenation methods, and single-channel ECG reliability from wearables needs further exploration.•Exploring PPG signals in addition to ECG for cardiac disease detection is a promising research direction.</description><identifier>ISSN: 0010-4825</identifier><identifier>EISSN: 1879-0534</identifier><identifier>DOI: 10.1016/j.compbiomed.2023.107908</identifier><identifier>PMID: 38217973</identifier><language>eng</language><publisher>United States: Elsevier Ltd</publisher><subject>Accuracy ; Agent based modeling ; Agent-based models ; Algorithms ; Artificial Intelligence ; Artificial neural networks ; Benchmarks ; Cardiac muscle ; Cardiovascular diseases ; Computer simulation ; Data augmentation ; Data processing ; Datasets ; Deep learning ; EKG ; Electrocardiograms ; Electrocardiography ; Electrocardiography - methods ; Health risks ; Humans ; Machine learning ; Model accuracy ; Modelling ; Muscles ; Neural networks ; Neural Networks, Computer ; Portable equipment ; Signal generation ; Signal processing ; Signal Processing, Computer-Assisted ; Software ; Spectrograms ; Transformers ; Wavelet transforms ; Wearable computers ; Wearable devices ; Wearable technology</subject><ispartof>Computers in biology and medicine, 2024-03, Vol.170, p.107908-107908, Article 107908</ispartof><rights>2024 The Authors</rights><rights>Copyright © 2024 The Authors. Published by Elsevier Ltd.. All rights reserved.</rights><rights>2024. The Authors</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c347t-b7349ec3d748bc85367e233ebca05bf17be90c8c59917617b18ddef243e9b5223</cites><orcidid>0000-0001-7248-6888 ; 0000-0001-7818-4805 ; 0000-0002-0006-363X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.compbiomed.2023.107908$$EHTML$$P50$$Gelsevier$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38217973$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Safdar, Muhammad Farhan</creatorcontrib><creatorcontrib>Nowak, Robert Marek</creatorcontrib><creatorcontrib>Pałka, Piotr</creatorcontrib><title>Pre-Processing techniques and artificial intelligence algorithms for electrocardiogram (ECG) signals analysis: A comprehensive review</title><title>Computers in biology and medicine</title><addtitle>Comput Biol Med</addtitle><description>Electrocardiogram (ECG) are the physiological signals and a standard test to measure the heart’s electrical activity that depicts the movement of cardiac muscles. A review study has been conducted on ECG signals analysis with the help of artificial intelligence (AI) methods over the last ten years i.e., 2012–22. Primarily, the method of ECG analysis by software systems was divided into classical signal processing (e.g. spectrograms or filters), machine learning (ML) and deep learning (DL), including recursive models, transformers and hybrid. Secondly, the data sources and benchmark datasets were depicted. Authors grouped resources by ECG acquisition methods into hospital-based portable machines and wearable devices. Authors also included new trends like advanced pre-processing, data augmentation, simulations and agent-based modeling.
The study found improvement in ECG examination perfection made each year through ML, DL, hybrid models, and transformers. Convolutional neural networks and hybrid models were more targeted and proved efficient. The transformer model extended the accuracy from 90% to 98%. The Physio-Net library helps acquire ECG signals, including the popular benchmark databases such as MIT-BIH, PTB, and challenging datasets. Similarly, wearable devices have been established as a appropriate option for monitoring patient health without the time and place limitations and are also helpful for AI model calibration with so far accuracy of 82%–83% on Samsung smartwatch. In the pre-processing signals, spectrogram generation through Fourier and wavelet transformations are erected leading approaches promoting on average accuracy of 90%–95%. Likewise, data enhancement using geometrical techniques is well-considered; however, extraction and concatenation-based methods need attention. As the what-if analysis in healthcare or cardiac issues can be performed using a complex simulation, the study reviews agent-based modeling and simulation approaches for cardiovascular risk event assessment.
•Improvement comes from advanced algorithms, replacing classical ML with deep learning: hybrid models, transformers.•Convolutional neural networks and hybrid models were more targeted and found productive.•In signal pre-processing, Fourier and wavelet transformations dominate for spectrogram generation.•Enhancing signals via extraction, concatenation methods, and single-channel ECG reliability from wearables needs further exploration.•Exploring PPG signals in addition to ECG for cardiac disease detection is a promising research direction.</description><subject>Accuracy</subject><subject>Agent based modeling</subject><subject>Agent-based models</subject><subject>Algorithms</subject><subject>Artificial Intelligence</subject><subject>Artificial neural networks</subject><subject>Benchmarks</subject><subject>Cardiac muscle</subject><subject>Cardiovascular diseases</subject><subject>Computer simulation</subject><subject>Data augmentation</subject><subject>Data processing</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>EKG</subject><subject>Electrocardiograms</subject><subject>Electrocardiography</subject><subject>Electrocardiography - methods</subject><subject>Health risks</subject><subject>Humans</subject><subject>Machine learning</subject><subject>Model accuracy</subject><subject>Modelling</subject><subject>Muscles</subject><subject>Neural networks</subject><subject>Neural Networks, Computer</subject><subject>Portable equipment</subject><subject>Signal generation</subject><subject>Signal processing</subject><subject>Signal Processing, Computer-Assisted</subject><subject>Software</subject><subject>Spectrograms</subject><subject>Transformers</subject><subject>Wavelet transforms</subject><subject>Wearable computers</subject><subject>Wearable devices</subject><subject>Wearable technology</subject><issn>0010-4825</issn><issn>1879-0534</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNqFkc1u1DAUhS0EokPhFZAlNmWRwT_J2GZXRm1BqkQXsLYc5yZzR0k82JmiPgDvXVvTCokNK8v2d3_OOYRQztac8c2n_dqH6dBimKBbCyZkflaG6RdkxbUyFWtk_ZKsGOOsqrVozsiblPaMsZpJ9pqcSS24MkquyJ-7CNVdDB5SwnmgC_jdjL-OkKibO-rigj16dCPFeYFxxAFmD9SNQ4i47KZE-xApjOCX3MTFDsMQ3UQvrrY3H2nCYXZjaeXGh4TpM72kZfMIO5gT3gONcI_w-y151WcO3j2d5-Tn9dWP7dfq9vvNt-3lbeVlrZaqVbI24GWnat163ciNAiEltN6xpu25asEwr31jDFebfOW666AXtQTTNkLIc3Jx6nuIoWhc7ITJZ1luhnBMVhhhmBTGmIx--Afdh2MsagqldSPqhmVKnygfQ0oRenuIOLn4YDmzJSq7t3-jsiUqe4oql75_GnBsy99z4XM2GfhyAiA7kl2KNnks7ncYs922C_j_KY-4d6v5</recordid><startdate>202403</startdate><enddate>202403</enddate><creator>Safdar, Muhammad Farhan</creator><creator>Nowak, Robert Marek</creator><creator>Pałka, Piotr</creator><general>Elsevier Ltd</general><general>Elsevier Limited</general><scope>6I.</scope><scope>AAFTH</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>K9.</scope><scope>M7Z</scope><scope>NAPCQ</scope><scope>P64</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0001-7248-6888</orcidid><orcidid>https://orcid.org/0000-0001-7818-4805</orcidid><orcidid>https://orcid.org/0000-0002-0006-363X</orcidid></search><sort><creationdate>202403</creationdate><title>Pre-Processing techniques and artificial intelligence algorithms for electrocardiogram (ECG) signals analysis: A comprehensive review</title><author>Safdar, Muhammad Farhan ; Nowak, Robert Marek ; Pałka, Piotr</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c347t-b7349ec3d748bc85367e233ebca05bf17be90c8c59917617b18ddef243e9b5223</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accuracy</topic><topic>Agent based modeling</topic><topic>Agent-based models</topic><topic>Algorithms</topic><topic>Artificial Intelligence</topic><topic>Artificial neural networks</topic><topic>Benchmarks</topic><topic>Cardiac muscle</topic><topic>Cardiovascular diseases</topic><topic>Computer simulation</topic><topic>Data augmentation</topic><topic>Data processing</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>EKG</topic><topic>Electrocardiograms</topic><topic>Electrocardiography</topic><topic>Electrocardiography - methods</topic><topic>Health risks</topic><topic>Humans</topic><topic>Machine learning</topic><topic>Model accuracy</topic><topic>Modelling</topic><topic>Muscles</topic><topic>Neural networks</topic><topic>Neural Networks, Computer</topic><topic>Portable equipment</topic><topic>Signal generation</topic><topic>Signal processing</topic><topic>Signal Processing, Computer-Assisted</topic><topic>Software</topic><topic>Spectrograms</topic><topic>Transformers</topic><topic>Wavelet transforms</topic><topic>Wearable computers</topic><topic>Wearable devices</topic><topic>Wearable technology</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Safdar, Muhammad Farhan</creatorcontrib><creatorcontrib>Nowak, Robert Marek</creatorcontrib><creatorcontrib>Pałka, Piotr</creatorcontrib><collection>ScienceDirect Open Access Titles</collection><collection>Elsevier:ScienceDirect:Open Access</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Biochemistry Abstracts 1</collection><collection>Nursing & Allied Health Premium</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>MEDLINE - Academic</collection><jtitle>Computers in biology and medicine</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Safdar, Muhammad Farhan</au><au>Nowak, Robert Marek</au><au>Pałka, Piotr</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Pre-Processing techniques and artificial intelligence algorithms for electrocardiogram (ECG) signals analysis: A comprehensive review</atitle><jtitle>Computers in biology and medicine</jtitle><addtitle>Comput Biol Med</addtitle><date>2024-03</date><risdate>2024</risdate><volume>170</volume><spage>107908</spage><epage>107908</epage><pages>107908-107908</pages><artnum>107908</artnum><issn>0010-4825</issn><eissn>1879-0534</eissn><abstract>Electrocardiogram (ECG) are the physiological signals and a standard test to measure the heart’s electrical activity that depicts the movement of cardiac muscles. A review study has been conducted on ECG signals analysis with the help of artificial intelligence (AI) methods over the last ten years i.e., 2012–22. Primarily, the method of ECG analysis by software systems was divided into classical signal processing (e.g. spectrograms or filters), machine learning (ML) and deep learning (DL), including recursive models, transformers and hybrid. Secondly, the data sources and benchmark datasets were depicted. Authors grouped resources by ECG acquisition methods into hospital-based portable machines and wearable devices. Authors also included new trends like advanced pre-processing, data augmentation, simulations and agent-based modeling.
The study found improvement in ECG examination perfection made each year through ML, DL, hybrid models, and transformers. Convolutional neural networks and hybrid models were more targeted and proved efficient. The transformer model extended the accuracy from 90% to 98%. The Physio-Net library helps acquire ECG signals, including the popular benchmark databases such as MIT-BIH, PTB, and challenging datasets. Similarly, wearable devices have been established as a appropriate option for monitoring patient health without the time and place limitations and are also helpful for AI model calibration with so far accuracy of 82%–83% on Samsung smartwatch. In the pre-processing signals, spectrogram generation through Fourier and wavelet transformations are erected leading approaches promoting on average accuracy of 90%–95%. Likewise, data enhancement using geometrical techniques is well-considered; however, extraction and concatenation-based methods need attention. As the what-if analysis in healthcare or cardiac issues can be performed using a complex simulation, the study reviews agent-based modeling and simulation approaches for cardiovascular risk event assessment.
•Improvement comes from advanced algorithms, replacing classical ML with deep learning: hybrid models, transformers.•Convolutional neural networks and hybrid models were more targeted and found productive.•In signal pre-processing, Fourier and wavelet transformations dominate for spectrogram generation.•Enhancing signals via extraction, concatenation methods, and single-channel ECG reliability from wearables needs further exploration.•Exploring PPG signals in addition to ECG for cardiac disease detection is a promising research direction.</abstract><cop>United States</cop><pub>Elsevier Ltd</pub><pmid>38217973</pmid><doi>10.1016/j.compbiomed.2023.107908</doi><tpages>1</tpages><orcidid>https://orcid.org/0000-0001-7248-6888</orcidid><orcidid>https://orcid.org/0000-0001-7818-4805</orcidid><orcidid>https://orcid.org/0000-0002-0006-363X</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0010-4825 |
ispartof | Computers in biology and medicine, 2024-03, Vol.170, p.107908-107908, Article 107908 |
issn | 0010-4825 1879-0534 |
language | eng |
recordid | cdi_proquest_miscellaneous_2929032999 |
source | MEDLINE; Elsevier ScienceDirect Journals Complete |
subjects | Accuracy Agent based modeling Agent-based models Algorithms Artificial Intelligence Artificial neural networks Benchmarks Cardiac muscle Cardiovascular diseases Computer simulation Data augmentation Data processing Datasets Deep learning EKG Electrocardiograms Electrocardiography Electrocardiography - methods Health risks Humans Machine learning Model accuracy Modelling Muscles Neural networks Neural Networks, Computer Portable equipment Signal generation Signal processing Signal Processing, Computer-Assisted Software Spectrograms Transformers Wavelet transforms Wearable computers Wearable devices Wearable technology |
title | Pre-Processing techniques and artificial intelligence algorithms for electrocardiogram (ECG) signals analysis: A comprehensive review |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T14%3A35%3A28IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Pre-Processing%20techniques%20and%20artificial%20intelligence%20algorithms%20for%20electrocardiogram%20(ECG)%20signals%20analysis:%20A%20comprehensive%20review&rft.jtitle=Computers%20in%20biology%20and%20medicine&rft.au=Safdar,%20Muhammad%20Farhan&rft.date=2024-03&rft.volume=170&rft.spage=107908&rft.epage=107908&rft.pages=107908-107908&rft.artnum=107908&rft.issn=0010-4825&rft.eissn=1879-0534&rft_id=info:doi/10.1016/j.compbiomed.2023.107908&rft_dat=%3Cproquest_cross%3E2928852450%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2928852450&rft_id=info:pmid/38217973&rft_els_id=S0010482523013732&rfr_iscdi=true |