Key result
CNN-based contactless ballistocardiography lowers heart rate estimation error to ~2 bpm over conventional algorithms.
Why the study?
Continuous heart rate monitoring is needed for early detection of heart disease, but current ECG devices are expensive and less accessible, motivating development of a non-contact BCG-based system.
Observational (n=14)
No
Absolute Event Rate: 2.07% vs 10.12%
Chair BCG system tracks HR/HRV with high accuracy even in arrhythmia; leaves open larger prospective validation before clinical use.
Cardiovascular disease is the number one cause of death in the world and is a serious problem. In the case of cardiopulmonary arrest due to myocardial infarction, the survival rate is as low as 13.3% one month after resuscitation, which birthed the need for continuous heart monitoring. In this study, we develop a Ballistocardiogram (BCG) measurement system using a load cell installed on a chair and a heart rate estimation algorithm that is robust to waveform changes, with the aim of constructing a non-contact heart rate acquisition system. The proposed system was evaluated by utilizing data obtained from 13 healthy subjects and 1 subject with abnormal ECG who were simultaneously measured with ECG. The output of the BCG system was confirmed to change with the same period as the ECG data obtained as the correct answer, and the synchronization of the R-peak positions was confirmed for all cases. As a result of comparing the heart rate intervals estimated from BCG and those obtained from ECG, it was confirmed that the same heart rate variability (HRV) features could be obtained even for abnormal ECG subject.
No takes yet. Share an insight, caveat, or question.
Sumali et al. (2022) conducted an observational in Healthy and abnormal ECG (n=14). Chair-based ballistocardiogram (BCG) with CNN peak detection vs. Standard Electrocardiography (ECG) and conventional BCG algorithms was evaluated on Heart rate estimation error rate. A contactless ballistocardiography system using chair-based load cells and a CNN algorithm estimated R-peaks with 95.9% accuracy and achieved a mean heart rate estimation error of 2.07 bpm, outperforming the conventional algorithm's 10.12 bpm error.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: