Standardized Database of 12-Lead Electrocardiograms with a Common Standard for the Promotion of Cardiovascular Research: KURIAS-ECG
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Objectives: Electrocardiography (ECG)-based diagnosis by experts cannot maintain uniform quality because individual differencesmay occur. Previous public databases can be used for clinical studies, but there is no common standard that wouldallow databases to be combined. For this reason, it is difficult to conduct research that derives results by combining databases. Recent commercial ECG machines offer diagnoses similar to those of a physician. Therefore, the purpose of this study was toconstruct a standardized ECG database using computerized diagnoses. Methods: The constructed database was standardizedusing Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT) and Observational Medical Outcomes Partnership–common data model (OMOP-CDM), and data were then categorized into 10 groups based on the Minnesota classification. In addition, to extract high-quality waveforms, poor-quality ECGs were removed, and database bias was minimizedby extracting at least 2,000 cases for each group. To check database quality, the difference in baseline displacement accordingto whether poor ECGs were removed was analyzed, and the usefulness of the database was verified with seven classificationmodels using waveforms. Results: The standardized KURIAS-ECG database consists of high-quality ECGs from 13,862 patients,with about 20,000 data points, making it possible to obtain more than 2,000 for each Minnesota classification. An artificialintelligence classification model using the data extracted through SNOMED-CT showed an average accuracy of 88.03%. Conclusions: The KURIAS-ECG database contains standardized ECG data extracted from various machines. The proposedprotocol should promote cardiovascular disease research using big data and artificial intelligence.
Abstract
Objectives: Electrocardiography (ECG)-based diagnosis by experts cannot maintain uniform quality because individual differencesmay occur. Previous public databases can be used for clinical studies, but there is no common standard that wouldallow databases to be combined. For this reason, it is difficult to conduct research that derives results by combining databases. Recent commercial ECG machines offer diagnoses similar to those of a physician. Therefore, the purpose of this study was toconstruct a standardized ECG database using computerized diagnoses. Methods: The constructed database was standardizedusing Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT) and Observational Medical Outcomes Partnership–common data model (OMOP-CDM), and data were then categorized into 10 groups based on the Minnesota classification. In addition, to extract high-quality waveforms, poor-quality ECGs were removed, and database bias was minimizedby extracting at least 2,000 cases for each group. To check database quality, the difference in baseline displacement accordingto whether poor ECGs were removed was analyzed, and the usefulness of the database was verified with seven classificationmodels using waveforms. Results: The standardized KURIAS-ECG database consists of high-quality ECGs from 13,862 patients,with about 20,000 data points, making it possible to obtain more than 2,000 for each Minnesota classification. An artificialintelligence classification model using the data extracted through SNOMED-CT showed an average accuracy of 88.03%. Conclusions: The KURIAS-ECG database contains standardized ECG data extracted from various machines. The proposedprotocol should promote cardiovascular disease research using big data and artificial intelligence.
참고문헌 (30)
- Maron BJ, "Assessment of the 12-lead ECG as a screening test for detection of cardiovascular disease in healthy general populations of young people(12-25years of age) : a scientific statement from the American Heart Association and the American College of Cardiology", Circulation, 130(15), pp.1303~1334 (2014)[DOI]
- Hao P, "Multi-branch fusion network for Myocardial infarction screening from 12-lead ECG images", Comput Methods Programs Biomed, 184, pp.105286~ (2020)[DOI]
- Rajkumar A, "Arrhythmia classification on ECG using deep learning", Proceedings of 2019 5th International Conference on advanced Computing & Communication Systems (ICACCS), pp.365~369 (2019)
- Liu X, "Deep learning in ECG diagnosis : a review", Knowl Based Syst, 227, pp.107187~ (2021)[DOI]
- Hong S, "Opportunities and challenges of deep learning methods for electrocardiogram data : a systematic review", Comput Biol Med, 122, pp.103801~ (2020)[DOI]
- Goldberger AL, "PhysioBank, PhysioToolkit, and PhysioNet : components of a new research resource for complex physiologic signals", Circulation, 101, pp.e215~e220 (2000)[DOI]
- Taddei A, "The European ST-T database : standard for evaluating systems for the analysis of ST-T changes in ambulatory electrocardiography", Eur Heart J, 13(9), pp.1164~1172 (1992)[DOI]
- Jager F, "Long-term ST database : a reference for the development and evaluation of automated ischaemia detectors and for the study of the dynamics of myocardial ischaemia", Med Biol Eng Comput, 41(2), pp.172~182 (2003)[DOI]
- Moody GB, "The impact of the MIT-BIH arrhythmia database", IEEE Eng Med Biol Mag, 20(3), pp.45~50 (2001)[DOI]
- Moody GB, "A noise stress test for arrhythmia detectors", Comput Cardiol, 11(3), pp.381~384 (1984)
- Laguna P, "The STAFF III ECG database and its significance for methodological development and evaluation", J Electrocardiol, 47(4), pp.408~417 (2014)[DOI]
- Kreiseler D, "Automatisierte EKG-Auswertung mit Hilfe der EKG-Signaldatenbank CARDIODAT der PTB", Biomed Tech(Berl), 40(s1), pp.319~320 (1995)[DOI]
- "St Petersburg INCART 12-lead Arrhythmia Database" (2008)[URL]
- Moody GB, "The PhysioNet", Computers in Cardiology challenge 2008: T-wave alternans, 2008, 505~508
- Kalyakulina AI, "LUDB : a new open-access validation tool for electrocardiogram delineation algorithms", IEEE Access, 8, pp.186181~186190 (2020)[DOI]
- Zheng J, "A 12-lead electrocardiogram database for arrhythmia research covering more than 10, 000 patients", Sci Data, 7(1), pp.48~ (2020)[DOI]
- Wagner P, "PTB-XL, a large publicly available electrocardiography dataset", Sci Data, 7(1), pp.154~ (2020)[DOI]
- Donnelly K, "SNOMED-CT : the advanced terminology and coding system for eHealth", Stud Health Technol Inform, 121, pp.279~290 (2006)
- Lee D, "Literature review of SNOMED CT use", J Am Med Inform Assoc, 21(e1), pp.e11~e19 (2014)[DOI]
- Prineas RJ, "Minnesota code manual of electrocardiographic findings" (2009), Springer Science & Business Media
- Willems JL, "The diagnostic performance of computer programs for the interpretation of electrocardiograms", N Engl J Med, 325(25), pp.1767~1773 (1991)[DOI]
- Smulyan H, "The computerized ECG : friend and foe", Am J Med, 132(2), pp.153~160 (2019)[DOI]
- Makadia R, "Transforming the premier perspective hospital database into the Observational Medical Outcomes Partnership(OMOP)common data model", EGEMS(Wash DC), 2(1), pp.1110~ (2014)[DOI]
- Altay Y, "The effect of filter parameters on the accuracy of ECG signal measurement", Biomed Eng, 53(3), pp.176~180 (2019)[DOI]
- Sohn J, "Reconstruction of 12-lead electrocardiogram from a three-lead patch-type device using a LSTM network", Sensors(Basel), 20(11), pp.3278~ (2020)[DOI]
- Gan F, "Baseline correction by improved iterative polynomial fitting with automatic threshold", Chemometr Intell Lab Syst, 82(1-2), pp.59~65 (2006)[DOI]
- Baek SJ, "Baseline correction using asymmetrically reweighted penalized least squares smoothing", Analyst, 140(1), pp.250~257 (2015)[DOI]
- Meek S, "ABC of clinical electrocardiography. Introduction. I-Leads, rate, rhythm, and cardiac axis", BMJ, 324(7334), pp.415~418 (2002)[DOI]
- Ebrahimi Z, "A review on deep learning methods for ECG arrhythmia classification", Exp Syst Appl, 7, pp.100033~ (2020)[DOI]
- Yoo H, "Deep Learning Algorithm of 12-Lead Electrocardiogram for Parkinson Disease Screening", J Parkinsons Dis, pp.1~12 (2023)[DOI]