| Autor: |
Qiushi Luo, Hongling Zhu, Jiabing Zhu, Yi Li, Yang Yu, Lei Lei, Fan Lin, Minghe Zhou, Longyan Cui, Tao Zhu, Xuefei Li, Huakun Zuo, Xiaoyun Yang |
| Jazyk: |
angličtina |
| Rok vydání: |
2023 |
| Předmět: |
|
| Zdroj: |
Frontiers in Cardiovascular Medicine, Vol 10 (2023) |
| Druh dokumentu: |
article |
| ISSN: |
2297-055X |
| DOI: |
10.3389/fcvm.2023.1279324 |
| Popis: |
BackgroundPatients with atrial septal defect (ASD) exhibit distinctive electrocardiogram (ECG) patterns. However, ASD cannot be diagnosed solely based on these differences. Artificial intelligence (AI) has been widely used for specifically diagnosing cardiovascular diseases other than arrhythmia. Our study aimed to develop an artificial intelligence-enabled 8-lead ECG to detect ASD among adults.MethodIn this study, our AI model was trained and validated using 526 ECGs from patients with ASD and 2,124 ECGs from a control group with a normal cardiac structure in our hospital. External testing was conducted at Wuhan Central Hospital, involving 50 ECGs from the ASD group and 46 ECGs from the normal group. The model was based on a convolutional neural network (CNN) with a residual network to classify 8-lead ECG data into either the ASD or normal group. We employed a 10-fold cross-validation approach.ResultsStatistically significant differences (p |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
