Evaluation of the QRS detector using the Medicom-combi complex for daily monitoring of ECG and blood pressure using the MIT-BIH ECG signal test database

Purpose. To evaluate the accuracy of the QRS complex detectorof the Medicom-combi complex for daily monitoring of ECG and blood pressure using the MIT-BIH ECG signal test database in accordance with the requirements of GOST R IEC60601–2–47–2017, 30324.2.47–2012.

Materials and methods. During the tests, the operation of the detector was evaluated using the MIT-BIH Arrhythmia Database, containing 48 records of 30 minutes each. Each selected QRS complex was assigned one of the following types: N (supraventricular complex, normal QRS complex, including bundle branch block), V (ventricular complex), U (complex that experts find difficult to determine) and A (artifact). Rates of sensitivity (Sen), specificity or positive predictive rate (PPR), and overdiagnosis (FPR) were determined.

Results. The sensitivity of the QRS complex detector of the Medicom-combi complex for daily monitoring of ECG and blood pressure was 99,98%, and the specificity was 99,87%. The sensitivity of determining ventricular complexes was 99,97%, the specificity of determining ventricular complexes was 99,64%. Overdiagnosis of ventricular complexes does not exceed 0,03%.

Conclusion. The Medicom-combi complex for daily monitoring of ECG and blood pressure, designed for long-term ECG monitoring, has sufficient sensitivity and specificity for analyzing Holter ECG recordings, as well as identifying ventricular ectopic complexes.

1. Boytsov S. A., Drapkina O. M. Modern content and improvement of high cardiovascular risk strategy in reducing mortality from cardiovascular diseases. Terapevticheskii arkhiv. 2021; 93 (1): 4-6.

2. Jun T. J., Nguyen H.M., Kang D. et al. ECG arrhythmia classification using a 2-D convolutional neural network.ariv preprint arXiv,1804.06812, Apr. 2018.

3. Abrishami H., Han C., Zhou X. et al. Supervised ECG Interval Segmentation Using LSTM Neural Network. Proc. BIOCOMP Conf., 2018. Pp. 71-77.

4. Yildirim O. A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification. Computers in biology and medicine. May 2018; 96: 189-202.

5. Saadatnejad S., Oveisi M., Hashemi M. LSTM-Based ECG Classification for Continuous Monitoring on Personal Wearable Devices. IEEE Journal of Biomedical and Health Informatics, 2019.

6. Epifanov S.N. Experience of ROKHMeNE test bases usage for automatic ECG analysis evaluation. Polyclinic. 2020; 3: 110-114.