Interpretation and Classification of Phonocardiogram Using Principal Component Analysis

Abstract

Background: Large datasets are logically common yet frequently difficult to interpret. Principal Component Analysis (PCA) is a technique to reduce the dimensionality of a dataset. Objective: The main objective of this work is to use principal component analysis to interpret and classify phonocardiogram signals. Methods: Finding new factors aids in the reduction of important components of an eigenvalue/ eigenvector problem, thus enabling the new factors to be represented by the current dataset and making PCA a flexible data analysis tool. PCA is adaptable to a variety of systems created to update different data types and technology advancements. Results: Signals acquired from a patient, i.e., bio-signals, are used to investigate the patient's strength. One such bio-signal of central significance is the phonocardiogram (PCG), which addresses the working of the heart. Any change in the PCG signal is a characteristic proportion of heart failure, an arrhythmia condition. Conclusion: Long-term observation is difficult due to the many complexities, such as the lack of human competence and the high chance of misdiagnosis.