Structural Anomalies Detection from Electrocardiogram (ECG) with Spectrogram and Handcrafted Features

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 7; p. 2467
• Main Authors: Li, Hongzu, Boulanger, Pierre
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 23.03.2022; MDPI
• Subjects: Algorithms; Anomalies; anomaly detection; Cardiovascular diseases; Classification; Deep learning; Discriminant analysis; Electrocardiogram; Electrocardiography; Electrocardiography - methods; False alarms; Fourier transforms; Heart; Heart Defects, Congenital; Heart Rate; Humans; Low income groups; Machine learning; Monitoring, Physiologic; Morphology; Neural networks; Neural Networks, Computer; Noise; Rhythm; Sensitivity; Signal processing; Signal Processing, Computer-Assisted; Wavelet transforms; deep learning; electrocardiogram; anomaly detection; machine learning; signal processing
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22072467

Cardiovascular diseases are the leading cause of death globally, causing nearly 17.9 million deaths per year. Therefore, early detection and treatment are critical to help improve this situation. Many manufacturers have developed products to monitor patients' heart conditions as they perform their daily activities. However, very few can diagnose complex heart anomalies beyond detecting rhythm fluctuation. This paper proposes a new method that combines a Short-Time Fourier Transform (STFT) spectrogram of the ECG signal with handcrafted features to detect heart anomalies beyond commercial product capabilities. Using the proposed Convolutional Neural Network, the algorithm can detect 16 different rhythm anomalies with an accuracy of 99.79% with 0.15% false-alarm rate and 99.74% sensitivity. Additionally, the same algorithm can also detect 13 heartbeat anomalies with 99.18% accuracy with 0.45% false-alarm rate and 98.80% sensitivity.