A Multi-Pathology Ballistocardiogram Dataset for Cardiac Function Monitoring and Arrhythmia Assessment

Area of Science:

• Cardiology
• Biomedical Engineering
• Signal Processing

Background:

• Cardiac dysfunction necessitates advanced diagnostic and treatment strategies.
• Current monitoring methods like echocardiography have limitations, driving the need for noninvasive, continuous solutions.
• Ballistocardiography (BCG) offers a promising noninvasive approach by detecting cardiac mechanical activity through body vibrations.

Purpose of the Study:

• To present a comprehensive, multi-pathology Ballistocardiography (BCG) dataset.
• To facilitate the development of advanced algorithms for noninvasive cardiovascular monitoring.
• To support the clinical validation of BCG for diagnosing and managing heart conditions.

Main Methods:

• Collected synchronized Ballistocardiography (BCG), electrocardiogram (ECG), and M-mode echocardiography data.
• Included recordings from healthy individuals and patients with heart failure (HF), atrial fibrillation (AF), premature ventricular contractions (PVCs), and premature atrial contractions (PACs).
• Ensured data diversity to cover various physiological and pathological cardiac states.

Main Results:

• A novel, multi-pathology BCG dataset is now available.
• The dataset provides synchronized multi-modal physiological recordings.
• It encompasses a range of cardiovascular conditions, from healthy to complex arrhythmias and heart failure.

Conclusions:

• The presented BCG dataset is a valuable resource for advancing noninvasive cardiovascular monitoring.
• It will aid in developing and validating algorithms for remote detection of cardiac dysfunction.
• This work promotes the clinical utility of BCG in diagnostics and patient management.