Automatic ECG signal quality assessment using convolutional neural networks and derivative ECG signal for false alarm reduction in wearable vital signs monitoring devices

Abstract

The electrocardiogram (ECG) signals are often analyzed to detect cardiovascular diseases and monitor vital signs. However, analysis of noisy ECG signals leads to misdiagnosis of diseases and generates false alarms. To prevent false alarms, we present a derivative ECG (dECG) signal-based lightweight convolutional neural network (CNN) for automatic ECG signal quality assessment (ECG-SQA). The proposed CNN detects clean (“acceptable”) and noisy (“unacceptable”) ECG signals which ensures only clean ECG signals are analyzed for disease detection and monitoring vital signs with reduced false alarms in health monitoring devices. Here, we evaluated the performance, total parameters, testing time for ECG-SQA, and model size of 60 dECG-based CNNs to determine the optimal ECG-SQA method. The performance of the dECG-based CNNs are analyzed with three activation functions, five kernel sizes, different numbers of convolutional layers, and dense layers. The CNNs are trained using ECG signals from one channel and fifteen channels of standard ECG databases. On a standard unseen ECG database, the proposed CNN model has achieved accuracy, sensitivity, and specificity of 97.59%, 98.78%, and 89.23%, respectively. The optimal CNN (model size: 2,989 kB) implemented on the Raspberry Pi computing platform has testing time of 130.44±46.24 ms for quality assessment of 5 s ECG signal which confirms the real-time feasibility of the proposed method. The dECG-based ECG-SQA method is essential during continuous monitoring of vital signs and diagnosis of cardiovascular disease to reduce false alarms and improve reliability of wearable devices having limited computing capacity and onboard memory.