Preliminary results on quantification of Seismocardiogram morphological changes, using principal component analysis.

Area of Science:

• Biomedical Engineering
• Cardiology
• Signal Processing

Background:

• Seismocardiogram (SCG) signals reflect cardiac mechanical activity.
• Quantifying beat-to-beat SCG variations is crucial for understanding cardiac health.
• Existing methods may not fully capture subtle changes indicative of heart disease.

Purpose of the Study:

• To propose and validate a novel methodology for quantifying beat-to-beat Seismocardiogram changes.
• To assess the potential of this method in differentiating between healthy subjects and patients with ischemic heart disease.
• To explore the utility of the developed index in patient monitoring and classification of myocardial abnormalities.

Main Methods:

• Principal Component Analysis (PCA) applied to Seismocardiogram (SCG) data.
• Analysis of beat-to-beat SCG variations.
• Testing the methodology on a cohort of 94 subjects, including 35 with ischemic heart disease.

Main Results:

• The PCA-based method demonstrated an insignificant overlap between healthy and diseased populations based on the number of principal components (NPC).
• The number of principal components (NPC) showed potential as a discriminator for myocardial abnormalities.
• The findings suggest the method's feasibility for classifying cardiac conditions.

Conclusions:

• The proposed PCA-based methodology offers a quantitative approach to analyze Seismocardiogram (SCG) signals.
• The method shows potential for developing a classification index for myocardial abnormalities.
• This approach could be valuable for non-invasive patient monitoring in cardiology.