通过使用卷积神经网络从单线心电图自动检测正常,心房和心室早跳
1MedTec & Science GmbH, Maria-Merian-Straße 6, 85521 Ottobrunn, Germany.
Sensors (Basel, Switzerland)
|January 28, 2026
概括
一个新的U-Net模型准确地检测到来自心电图的过早心房和心室收缩,而无需R峰检测. 这一进步有助于早期识别严重心脏病的风险.
科学领域:
- 心脏病学 心脏病学
- 生物医学工程 生物医学工程
- 医疗保健中的人工智能
背景情况:
- 从单导电心电图 (ECG) 准确检测早收缩 (PAC) 和早收缩 (PVC),对于识别患有心房动和心肌病风险的患者至关重要.
- 目前的方法可能依赖于R峰检测或手工制作的特征,这限制了它们在杂或复杂的心电图信号中的适用性.
研究的目的:
- 呈现一个完全卷积的单维U-Net模型,用于从原始单导电心电图信号中直接检测正常节拍,PAC和PVC.
- 评估模型在各种数据集上的性能,包括挑战噪音记录,并评估其概括能力.
主要方法:
- 采用了U-Net架构,使用了ConvNeXt V2编码器和简单的解码器块,将节拍分类重新定义为细分任务.
- 该模型在Icentia11k和内部ECG数据集上进行了训练,并在CPSC2020上得到了验证,在多个基准数据集上进行了概括测试.
- 没有使用明确的R峰检测,手工制作的功能或固定长度输入窗口.
主要成果:
- 该模型实现了近乎完美的QRS检测 (灵敏度和精度高达0.999).
- 观察到具有竞争力的PVC检测性能,在数据集中灵敏度高达0.986和精度高达0.993.
- PAC检测显示出变化,但在SVDB数据集上获得了0.72的F1得分,超过了以前的方法. 层GradCAM证实了生理学上可信的注意力机制.
结论:
- 拟议的U-Net框架提供了一个强大,可解释和硬件效率高的解决方案,用于在杂的单导电心电图中联合检测PAC和PVC.
- 该方法适合集成到连续监控系统,如霍尔特显示器和可穿戴设备.
- 这种方法推进了自动心律失常检测,潜在地改善了早期诊断和患者的结果.
相关概念视频
01:25ECG Interpretation of Arrhythmias II: Atrial, Junctional and Ventricular Arrhythmias
533
Arrhythmia is a condition characterized by an irregular heart rhythm, with ECG changes that differ based on its origin and nature. The types of arrhythmias discussed below include atrial, junctional, and ventricular arrhythmias.Atrial ArrhythmiasPremature Atrial Complexes (PACs): PACs are early atrial beats caused by stress, caffeine, alcohol, electrolyte imbalances, hypoxia, hyperthyroidism, or certain medications (e.g., bronchodilators and decongestants). The ECG shows early P waves with an...
533
01:09Beats
1.4K
The study of music provides many examples of the superposition of waves and the constructive and destructive interference that occurs. Very few examples of music being performed consist of a single source playing a single frequency for an extended period of time. A single frequency of sound for an extended period might be monotonous to the point of irritation, similar to the unwanted drone of an aircraft engine or a loud fan. Music is pleasant and exciting due to mixing the changing frequencies...
1.4K
01:17Convolution Properties II
583
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
583
02:26Protein Networks
4.5K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.5K
01:20Convolution Properties I
584
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
584
02:18Network Covalent Solids
16.1K
Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
16.1K