Artificial Intelligence-Driven Screening System for Rapid Image-Based Classification of 12-Lead ECG Exams: A Promising Solution for Emergency Room Prioritization
Carregando...
Citações na Scopus
0
Tipo de produção
article
Data de publicação
2023
Título da Revista
ISSN da Revista
Título do Volume
Editora
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Autores
Citação
IEEE ACCESS, v.11, p.121739-121752, 2023
Resumo
The 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.
Palavras-chave
Electrocardiography, Hospitals, Picture archiving and communication systems, Feature extraction, Classification algorithms, Atrial fibrillation, Training, Artificial intelligence, Medical services, Emergency services, atrial fibrillation, ECG, ECG image, 12-lead electrocardiogram, emergency room
Referências
- Andersen RS, 2019, EXPERT SYST APPL, V115, P465, DOI 10.1016/j.eswa.2018.08.011
- [Anonymous], 2014, Global status report on noncommunicable diseases
- Atienza F., 2014, Cardiac Electrophysiology: From Cell to Bedside, P419
- Brundel BJJM, 2022, NAT REV DIS PRIMERS, V8, DOI 10.1038/s41572-022-00347-9
- Butkuviene M, 2021, IEEE T BIO-MED ENG, V68, P3250, DOI 10.1109/TBME.2021.3067698
- CACERES CA, 1962, CIRCULATION, V25, P356, DOI 10.1161/01.CIR.25.2.356
- Che C, 2021, BMC MED INFORM DECIS, V21, DOI 10.1186/s12911-021-01546-2
- Dias F. M., 2021, P COMPUT CARDIOL, V48, P1
- Dong YF, 2023, MICROMACHINES-BASEL, V14, DOI 10.3390/mi14061155
- Siqueira ADE, 2017, ARQ BRAS CARDIOL, V109, P39, DOI 10.5935/abc.20170068
- Gliner V, 2020, SCI REP-UK, V10, DOI 10.1038/s41598-020-73060-w
- Hahne K, 2016, VASC HEALTH RISK MAN, V12, P65, DOI 10.2147/VHRM.S81807
- Hannun AY, 2019, NAT MED, V25, P65, DOI 10.1038/s41591-018-0268-3
- Hao PY, 2020, COMPUT METH PROG BIO, V184, DOI 10.1016/j.cmpb.2019.105286
- Harris K, 2012, J R Coll Physicians Edinb, V42 Suppl 18, P5, DOI 10.4997/JRCPE.2012.S02
- Hindricks G, 2021, REV ESP CARDIOL, V74, DOI 10.1016/j.recesp.2020.10.022
- Houssein EH, 2021, EXPERT SYST APPL, V181, DOI 10.1016/j.eswa.2021.115131
- Kingma D.P., 2015, arXiv
- Kirchhoff P., ESC GUIDELINES MANAG
- Król-Józaga B, 2022, BIOMED SIGNAL PROCES, V74, DOI 10.1016/j.bspc.2021.103470
- Kundu S, 2021, NAT MED, V27, P1328, DOI 10.1038/s41591-021-01461-z
- Liu FF, 2018, J MED IMAG HEALTH IN, V8, P1368, DOI 10.1166/jmihi.2018.2442
- Luz EJD, 2016, COMPUT METH PROG BIO, V127, P144, DOI 10.1016/j.cmpb.2015.12.008
- Macfarlane PW, 2014, J ELECTROCARDIOL, V47, P809, DOI 10.1016/j.jelectrocard.2014.08.003
- Macfarlane P. W., 2021, Hearts, V2, P433
- Marinho LB, 2019, FUTURE GENER COMP SY, V97, P564, DOI 10.1016/j.future.2019.03.025
- Moody GA, 2001, IEEE ENG MED BIOL, V20, P45, DOI 10.1109/51.932724
- Ribeiro A. H., Nature Commun., V11
- Rudin C, 2019, NAT MACH INTELL, V1, P206, DOI 10.1038/s42256-019-0048-x
- Sangha V, 2022, NAT COMMUN, V13, DOI 10.1038/s41467-022-29153-3
- Sassi R, 2017, J ELECTROCARDIOL, V50, P776, DOI 10.1016/j.jelectrocard.2017.08.001
- Schläpfer J, 2017, J AM COLL CARDIOL, V70, P1183, DOI 10.1016/j.jacc.2017.07.723
- Seki A., 2016, Cardiovascular Pathology, P57
- Selvaraju RR, 2017, IEEE I CONF COMP VIS, P618, DOI 10.1109/ICCV.2017.74
- Sevakula RK, 2020, J AM HEART ASSOC, V9, DOI 10.1161/JAHA.119.013924
- Siontis KC, 2021, NAT REV CARDIOL, V18, P465, DOI 10.1038/s41569-020-00503-2
- Smulyan H, 2019, AM J MED, V132, P153, DOI 10.1016/j.amjmed.2018.08.025
- Svennberg E, 2015, CIRCULATION, V131, P2176, DOI 10.1161/CIRCULATIONAHA.114.014343
- Zhang DD, 2021, ISCIENCE, V24, DOI 10.1016/j.isci.2021.102373