An artificial intelligence-enabled ECG algorithm for identifying ventricular premature contraction during sinus rhythm
Abstract Background Ventricular premature complex (VPC) is a common arrhythmia in clinical practice. VPC could trigger ventricular tachycardia/fibrillation or VPC-induced cardiomyopathy in susceptible patients. Existing screening methods require prolonged monitoring and are limited by cost and low y...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-12-01
|
| Series: | European Journal of Medical Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40001-022-00929-z |
| _version_ | 1811292140742901760 |
|---|---|
| author | Sheng-Nan Chang Yu-Heng Tseng Jien-Jiun Chen Fu-Chun Chiu Chin-Feng Tsai Juey-Jen Hwang Yi-Chih Wang Chia-Ti Tsai |
| author_facet | Sheng-Nan Chang Yu-Heng Tseng Jien-Jiun Chen Fu-Chun Chiu Chin-Feng Tsai Juey-Jen Hwang Yi-Chih Wang Chia-Ti Tsai |
| author_sort | Sheng-Nan Chang |
| collection | DOAJ |
| description | Abstract Background Ventricular premature complex (VPC) is a common arrhythmia in clinical practice. VPC could trigger ventricular tachycardia/fibrillation or VPC-induced cardiomyopathy in susceptible patients. Existing screening methods require prolonged monitoring and are limited by cost and low yield when the frequency of VPC is low. Twelve-lead electrocardiogram (ECG) is low cost and widely used. We aimed to identify patients with VPC during normal sinus rhythm (NSR) using artificial intelligence (AI) and machine learning-based ECG reading. Methods We developed AI-enabled ECG algorithm using a convolutional neural network (CNN) to detect the ECG signature of VPC presented during NSR using standard 12-lead ECGs. A total of 2515 ECG records from 398 patients with VPC were collected. Among them, only ECG records of NSR without VPC (1617 ECG records) were parsed. Results A total of 753 normal ECG records from 387 patients under NSR were used for comparison. Both image and time-series datasets were parsed for the training process by the CNN models. The computer architectures were optimized to select the best model for the training process. Both the single-input image model (InceptionV3, accuracy: 0.895, 95% confidence interval [CI] 0.683–0.937) and multi-input time-series model (ResNet50V2, accuracy: 0.880, 95% CI 0.646–0.943) yielded satisfactory results for VPC prediction, both of which were better than the single-input time-series model (ResNet50V2, accuracy: 0.840, 95% CI 0.629–0.952). Conclusions AI-enabled ECG acquired during NSR permits rapid identification at point of care of individuals with VPC and has the potential to predict VPC episodes automatically rather than traditional long-time monitoring. |
| first_indexed | 2024-04-13T04:40:51Z |
| format | Article |
| id | doaj.art-d77ee8dfdd7143548a3fb808f516d85f |
| institution | Directory Open Access Journal |
| issn | 2047-783X |
| language | English |
| last_indexed | 2024-04-13T04:40:51Z |
| publishDate | 2022-12-01 |
| publisher | BMC |
| record_format | Article |
| series | European Journal of Medical Research |
| spelling | doaj.art-d77ee8dfdd7143548a3fb808f516d85f2022-12-22T03:02:01ZengBMCEuropean Journal of Medical Research2047-783X2022-12-012711910.1186/s40001-022-00929-zAn artificial intelligence-enabled ECG algorithm for identifying ventricular premature contraction during sinus rhythmSheng-Nan Chang0Yu-Heng Tseng1Jien-Jiun Chen2Fu-Chun Chiu3Chin-Feng Tsai4Juey-Jen Hwang5Yi-Chih Wang6Chia-Ti Tsai7Division of Cardiology, Department of Internal Medicine, National Taiwan University College of Medicine and Hospital Yun-Lin BranchGraduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan UniversityDivision of Cardiology, Department of Internal Medicine, National Taiwan University College of Medicine and Hospital Yun-Lin BranchDivision of Cardiology, Department of Internal Medicine, National Taiwan University College of Medicine and Hospital Yun-Lin BranchDivision of Cardiology, Department of Internal Medicine, Chung Shan Medical University HospitalDivision of Cardiology, Department of Internal Medicine, National Taiwan University College of Medicine and HospitalDivision of Cardiology, Department of Internal Medicine, National Taiwan University College of Medicine and HospitalDivision of Cardiology, Department of Internal Medicine, National Taiwan University College of Medicine and HospitalAbstract Background Ventricular premature complex (VPC) is a common arrhythmia in clinical practice. VPC could trigger ventricular tachycardia/fibrillation or VPC-induced cardiomyopathy in susceptible patients. Existing screening methods require prolonged monitoring and are limited by cost and low yield when the frequency of VPC is low. Twelve-lead electrocardiogram (ECG) is low cost and widely used. We aimed to identify patients with VPC during normal sinus rhythm (NSR) using artificial intelligence (AI) and machine learning-based ECG reading. Methods We developed AI-enabled ECG algorithm using a convolutional neural network (CNN) to detect the ECG signature of VPC presented during NSR using standard 12-lead ECGs. A total of 2515 ECG records from 398 patients with VPC were collected. Among them, only ECG records of NSR without VPC (1617 ECG records) were parsed. Results A total of 753 normal ECG records from 387 patients under NSR were used for comparison. Both image and time-series datasets were parsed for the training process by the CNN models. The computer architectures were optimized to select the best model for the training process. Both the single-input image model (InceptionV3, accuracy: 0.895, 95% confidence interval [CI] 0.683–0.937) and multi-input time-series model (ResNet50V2, accuracy: 0.880, 95% CI 0.646–0.943) yielded satisfactory results for VPC prediction, both of which were better than the single-input time-series model (ResNet50V2, accuracy: 0.840, 95% CI 0.629–0.952). Conclusions AI-enabled ECG acquired during NSR permits rapid identification at point of care of individuals with VPC and has the potential to predict VPC episodes automatically rather than traditional long-time monitoring.https://doi.org/10.1186/s40001-022-00929-zArtificial intelligenceConvolutional neural network12-Lead electrocardiogramVentricular premature complex |
| spellingShingle | Sheng-Nan Chang Yu-Heng Tseng Jien-Jiun Chen Fu-Chun Chiu Chin-Feng Tsai Juey-Jen Hwang Yi-Chih Wang Chia-Ti Tsai An artificial intelligence-enabled ECG algorithm for identifying ventricular premature contraction during sinus rhythm European Journal of Medical Research Artificial intelligence Convolutional neural network 12-Lead electrocardiogram Ventricular premature complex |
| title | An artificial intelligence-enabled ECG algorithm for identifying ventricular premature contraction during sinus rhythm |
| title_full | An artificial intelligence-enabled ECG algorithm for identifying ventricular premature contraction during sinus rhythm |
| title_fullStr | An artificial intelligence-enabled ECG algorithm for identifying ventricular premature contraction during sinus rhythm |
| title_full_unstemmed | An artificial intelligence-enabled ECG algorithm for identifying ventricular premature contraction during sinus rhythm |
| title_short | An artificial intelligence-enabled ECG algorithm for identifying ventricular premature contraction during sinus rhythm |
| title_sort | artificial intelligence enabled ecg algorithm for identifying ventricular premature contraction during sinus rhythm |
| topic | Artificial intelligence Convolutional neural network 12-Lead electrocardiogram Ventricular premature complex |
| url | https://doi.org/10.1186/s40001-022-00929-z |
| work_keys_str_mv | AT shengnanchang anartificialintelligenceenabledecgalgorithmforidentifyingventricularprematurecontractionduringsinusrhythm AT yuhengtseng anartificialintelligenceenabledecgalgorithmforidentifyingventricularprematurecontractionduringsinusrhythm AT jienjiunchen anartificialintelligenceenabledecgalgorithmforidentifyingventricularprematurecontractionduringsinusrhythm AT fuchunchiu anartificialintelligenceenabledecgalgorithmforidentifyingventricularprematurecontractionduringsinusrhythm AT chinfengtsai anartificialintelligenceenabledecgalgorithmforidentifyingventricularprematurecontractionduringsinusrhythm AT jueyjenhwang anartificialintelligenceenabledecgalgorithmforidentifyingventricularprematurecontractionduringsinusrhythm AT yichihwang anartificialintelligenceenabledecgalgorithmforidentifyingventricularprematurecontractionduringsinusrhythm AT chiatitsai anartificialintelligenceenabledecgalgorithmforidentifyingventricularprematurecontractionduringsinusrhythm AT shengnanchang artificialintelligenceenabledecgalgorithmforidentifyingventricularprematurecontractionduringsinusrhythm AT yuhengtseng artificialintelligenceenabledecgalgorithmforidentifyingventricularprematurecontractionduringsinusrhythm AT jienjiunchen artificialintelligenceenabledecgalgorithmforidentifyingventricularprematurecontractionduringsinusrhythm AT fuchunchiu artificialintelligenceenabledecgalgorithmforidentifyingventricularprematurecontractionduringsinusrhythm AT chinfengtsai artificialintelligenceenabledecgalgorithmforidentifyingventricularprematurecontractionduringsinusrhythm AT jueyjenhwang artificialintelligenceenabledecgalgorithmforidentifyingventricularprematurecontractionduringsinusrhythm AT yichihwang artificialintelligenceenabledecgalgorithmforidentifyingventricularprematurecontractionduringsinusrhythm AT chiatitsai artificialintelligenceenabledecgalgorithmforidentifyingventricularprematurecontractionduringsinusrhythm |