Artificial Intelligence-Driven Screening System for Rapid Image-Based Classification of 12-Lead ECG Exams: A Promising Solution for Emergency Room Prioritization

Página do item simplificado
dc.contributorSistema FMUSP-HC: Faculdade de Medicina da Universidade de São Paulo (FMUSP) e Hospital das Clínicas da FMUSP
dc.contributor.authorDIAS, Felipe Meneguitti
dc.contributor.authorRIBEIRO, Estela
dc.contributor.authorMORENO, Ramon Alfredo
dc.contributor.authorRIBEIRO, Adele Helena
dc.contributor.authorSAMESIMA, Nelson
dc.contributor.authorPASTORE, Carlos Alberto
dc.contributor.authorKRIEGER, Jose Eduardo
dc.contributor.authorGUTIERREZ, Marco Antonio
dc.date.accessioned2023-12-15T18:45:24Z
dc.date.available2023-12-15T18:45:24Z
dc.date.issued2023
dc.description.abstractThe electrocardiogram (ECG) serves as a valuable diagnostic tool, providing crucial information about life-threatening cardiac conditions such as atrial fibrillation and myocardial infarction. A prompt and efficient assessment of ECG exams in environments such as Emergency Rooms (ERs) can significantly enhance the chances of survival for high-risk patients. Despite the presence of numerous works on ECG classification, most of these studies have concentrated on one-dimensional ECG signals, which are commonly found in publicly available ECG datasets. Nevertheless, the practical relevance of such methods is limited in hospital settings, where ECG exams are usually stored as images. In this study, we have developed an artificial intelligence-driven screening system specifically designed to analyze 12-lead ECG images. Our proposed method has been trained on an extensive dataset comprising 99,746 12-lead ECG exams collected from the ambulatory section of a tertiary hospital. The primary goal was to precisely classify the exams into three classes: Normal (N), Atrial Fibrillation (AFib), and Other (O). The evaluation of our approach yielded AUROC scores of 93.2%, 99.2%, and 93.1% for N, AFib, and O, respectively. To further validate our approach, we conducted evaluations using the 2018 China Physiological Signal Challenge (CPSC) database. In this evaluation, we achieved AUROC scores of 91.8%, 97.5%, and 70.4% for the classes N, AFib, and O, respectively. Additionally, we assessed our method using 1,074 exams acquired in the ER and obtained AUROC values of 98.3%, 98.0%, and 97.7% for the classes N, AFib, and O, respectively. Furthermore, we developed and deployed a system with a trained model within the ER of a tertiary hospital for research purposes. This system automatically retrieves newly captured ECG chart images from the Picture Archiving and Communication System (PACS) within the ER. These images undergo necessary preprocessing steps and serve as input for our proposed classification method. This comprehensive approach established an efficient and versatile end-to-end framework for ECG classification. The results of our study highlight the potential of leveraging artificial intelligence in the screening of ECG exams, offering a promising solution for the rapid assessment and prioritization of patients in the ER.eng
dc.description.indexPubMed
dc.description.indexWoS
dc.description.indexScopus
dc.description.sponsorshipSao Paulo Research Foundation (FAPESP) [2021/12935-0, 2014/50889-7]
dc.description.sponsorshipFoxconn Brazil
dc.description.sponsorshipZerbini Foundation
dc.identifier.citationIEEE ACCESS, v.11, p.121739-121752, 2023
dc.identifier.doi10.1109/ACCESS.2023.3328538
dc.identifier.issn2169-3536
dc.identifier.urihttps://observatorio.fm.usp.br/handle/OPI/57369
dc.language.isoeng
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INCeng
dc.relation.ispartofIeee Access
dc.rightsrestrictedAccesseng
dc.rights.holderCopyright IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INCeng
dc.subjectElectrocardiographyeng
dc.subjectHospitalseng
dc.subjectPicture archiving and communication systemseng
dc.subjectFeature extractioneng
dc.subjectClassification algorithmseng
dc.subjectAtrial fibrillationeng
dc.subjectTrainingeng
dc.subjectArtificial intelligenceeng
dc.subjectMedical serviceseng
dc.subjectEmergency serviceseng
dc.subjectatrial fibrillationeng
dc.subjectECGeng
dc.subjectECG imageeng
dc.subject12-lead electrocardiogrameng
dc.subjectemergency roomeng
dc.subject.otherarrhythmia detectioneng
dc.subject.otheratrial-fibrillationeng
dc.subject.otherextractioneng
dc.subject.otherimpacteng
dc.subject.wosComputer Science, Information Systemseng
dc.subject.wosEngineering, Electrical & Electroniceng
dc.subject.wosTelecommunicationseng
dc.titleArtificial Intelligence-Driven Screening System for Rapid Image-Based Classification of 12-Lead ECG Exams: A Promising Solution for Emergency Room Prioritizationeng
dc.typearticleeng
dc.type.categoryoriginal articleeng
dc.type.versionpublishedVersioneng
dspace.entity.typePublication
hcfmusp.author.externalRIBEIRO, Adele Helena:Clin Hosp Univ Sao Paulo Med Sch HCFMUSP, Heart Inst InCor, BR-05403000 Sao Paulo, Brazil
hcfmusp.citation.scopus0
hcfmusp.contributor.author-fmusphcFELIPE MENEGUITTI DIAS
hcfmusp.contributor.author-fmusphcESTELA RIBEIRO
hcfmusp.contributor.author-fmusphcRAMON ALFREDO MORENO
hcfmusp.contributor.author-fmusphcNELSON SAMESIMA
hcfmusp.contributor.author-fmusphcCARLOS ALBERTO PASTORE
hcfmusp.contributor.author-fmusphcJOSE EDUARDO KRIEGER
hcfmusp.contributor.author-fmusphcMARCO ANTONIO GUTIERREZ
hcfmusp.description.beginpage121739
hcfmusp.description.endpage121752
hcfmusp.description.volume11
hcfmusp.origemWOS
hcfmusp.origem.scopus2-s2.0-85176782839
hcfmusp.origem.wosWOS:001102185600001
hcfmusp.publisher.cityPISCATAWAYeng
hcfmusp.publisher.countryUSAeng
hcfmusp.relation.referenceAndersen RS, 2019, EXPERT SYST APPL, V115, P465, DOI 10.1016/j.eswa.2018.08.011eng
hcfmusp.relation.reference[Anonymous], 2014, Global status report on noncommunicable diseaseseng
hcfmusp.relation.referenceAtienza F., 2014, Cardiac Electrophysiology: From Cell to Bedside, P419eng
hcfmusp.relation.referenceBrundel BJJM, 2022, NAT REV DIS PRIMERS, V8, DOI 10.1038/s41572-022-00347-9eng
hcfmusp.relation.referenceButkuviene M, 2021, IEEE T BIO-MED ENG, V68, P3250, DOI 10.1109/TBME.2021.3067698eng
hcfmusp.relation.referenceCACERES CA, 1962, CIRCULATION, V25, P356, DOI 10.1161/01.CIR.25.2.356eng
hcfmusp.relation.referenceChe C, 2021, BMC MED INFORM DECIS, V21, DOI 10.1186/s12911-021-01546-2eng
hcfmusp.relation.referenceDias F. M., 2021, P COMPUT CARDIOL, V48, P1eng
hcfmusp.relation.referenceDong YF, 2023, MICROMACHINES-BASEL, V14, DOI 10.3390/mi14061155eng
hcfmusp.relation.referenceSiqueira ADE, 2017, ARQ BRAS CARDIOL, V109, P39, DOI 10.5935/abc.20170068eng
hcfmusp.relation.referenceGliner V, 2020, SCI REP-UK, V10, DOI 10.1038/s41598-020-73060-weng
hcfmusp.relation.referenceHahne K, 2016, VASC HEALTH RISK MAN, V12, P65, DOI 10.2147/VHRM.S81807eng
hcfmusp.relation.referenceHannun AY, 2019, NAT MED, V25, P65, DOI 10.1038/s41591-018-0268-3eng
hcfmusp.relation.referenceHao PY, 2020, COMPUT METH PROG BIO, V184, DOI 10.1016/j.cmpb.2019.105286eng
hcfmusp.relation.referenceHarris K, 2012, J R Coll Physicians Edinb, V42 Suppl 18, P5, DOI 10.4997/JRCPE.2012.S02eng
hcfmusp.relation.referenceHindricks G, 2021, REV ESP CARDIOL, V74, DOI 10.1016/j.recesp.2020.10.022eng
hcfmusp.relation.referenceHoussein EH, 2021, EXPERT SYST APPL, V181, DOI 10.1016/j.eswa.2021.115131eng
hcfmusp.relation.referenceKingma D.P., 2015, arXiveng
hcfmusp.relation.referenceKirchhoff P., ESC GUIDELINES MANAGeng
hcfmusp.relation.referenceKról-Józaga B, 2022, BIOMED SIGNAL PROCES, V74, DOI 10.1016/j.bspc.2021.103470eng
hcfmusp.relation.referenceKundu S, 2021, NAT MED, V27, P1328, DOI 10.1038/s41591-021-01461-zeng
hcfmusp.relation.referenceLiu FF, 2018, J MED IMAG HEALTH IN, V8, P1368, DOI 10.1166/jmihi.2018.2442eng
hcfmusp.relation.referenceLuz EJD, 2016, COMPUT METH PROG BIO, V127, P144, DOI 10.1016/j.cmpb.2015.12.008eng
hcfmusp.relation.referenceMacfarlane PW, 2014, J ELECTROCARDIOL, V47, P809, DOI 10.1016/j.jelectrocard.2014.08.003eng
hcfmusp.relation.referenceMacfarlane P. W., 2021, Hearts, V2, P433eng
hcfmusp.relation.referenceMarinho LB, 2019, FUTURE GENER COMP SY, V97, P564, DOI 10.1016/j.future.2019.03.025eng
hcfmusp.relation.referenceMoody GA, 2001, IEEE ENG MED BIOL, V20, P45, DOI 10.1109/51.932724eng
hcfmusp.relation.referenceRibeiro A. H., Nature Commun., V11eng
hcfmusp.relation.referenceRudin C, 2019, NAT MACH INTELL, V1, P206, DOI 10.1038/s42256-019-0048-xeng
hcfmusp.relation.referenceSangha V, 2022, NAT COMMUN, V13, DOI 10.1038/s41467-022-29153-3eng
hcfmusp.relation.referenceSassi R, 2017, J ELECTROCARDIOL, V50, P776, DOI 10.1016/j.jelectrocard.2017.08.001eng
hcfmusp.relation.referenceSchläpfer J, 2017, J AM COLL CARDIOL, V70, P1183, DOI 10.1016/j.jacc.2017.07.723eng
hcfmusp.relation.referenceSeki A., 2016, Cardiovascular Pathology, P57eng
hcfmusp.relation.referenceSelvaraju RR, 2017, IEEE I CONF COMP VIS, P618, DOI 10.1109/ICCV.2017.74eng
hcfmusp.relation.referenceSevakula RK, 2020, J AM HEART ASSOC, V9, DOI 10.1161/JAHA.119.013924eng
hcfmusp.relation.referenceSiontis KC, 2021, NAT REV CARDIOL, V18, P465, DOI 10.1038/s41569-020-00503-2eng
hcfmusp.relation.referenceSmulyan H, 2019, AM J MED, V132, P153, DOI 10.1016/j.amjmed.2018.08.025eng
hcfmusp.relation.referenceSvennberg E, 2015, CIRCULATION, V131, P2176, DOI 10.1161/CIRCULATIONAHA.114.014343eng
hcfmusp.relation.referenceZhang DD, 2021, ISCIENCE, V24, DOI 10.1016/j.isci.2021.102373eng
hcfmusp.scopus.lastupdate2024-04-12
relation.isAuthorOfPublicationeafa51a8-ab2d-42f1-8113-2a02866fddbf
relation.isAuthorOfPublicationfa93d264-5e13-42e4-a319-f5f04f1b4b76
relation.isAuthorOfPublicationeb09a742-3715-41e4-94e8-f3991b996db3
relation.isAuthorOfPublication2f7b6fba-e78d-43c1-828f-06b15cdd5f2f
relation.isAuthorOfPublication0380bae3-f797-4979-bfa0-021526ecbf43
relation.isAuthorOfPublicationa970d450-bcd4-4662-94d6-ad1c6d043b3c
relation.isAuthorOfPublication23ec3b55-50df-4630-902e-bedbb470fecb
relation.isAuthorOfPublication.latestForDiscoveryeafa51a8-ab2d-42f1-8113-2a02866fddbf
Arquivos
Pacote Original
Agora exibindo 1 - 1 de 1
Nenhuma Miniatura disponível
Nome:
art_DIAS_Artificial_IntelligenceDriven_Screening_System_for_Rapid_ImageBased_Classification_2023.PDF
Tamanho:
2.46 MB
Formato:
Adobe Portable Document Format
Descrição:
publishedVersion (English)
Baixar
Coleções
Artigos e Materiais de Revistas Científicas - FM/MCP
Artigos e Materiais de Revistas Científicas - HC/InCor
Artigos e Materiais de Revistas Científicas - LIM/13
Artigos e Materiais de Revistas Científicas - LIM/65