Carlos Alvarez Picaza*, Alberto Daniel Valdéz, Paola Luciana Schlesinger and Juan Ángel Chiozza

Universidad Nacional del Nordeste, Argentina

*Corresponding Author: Carlos Alvarez Picaza, Universidad Nacional del Nordeste, Argentina.

Received: April 01, 2025; Published: May 20, 2025

Abstract

Bioengineering is a branch of engineering that studies, among other things, the quantification of biological phenomena, such as the conductivity of blood and tissues, the mechanical response to an electrical stimulus, or the study of bioelectrical phenomena. Among these, the analysis of the cardiac signal, the electrocardiogram (ECG), is included. The electrocardiographic signal is the most studied biological signal in the world; despite this, there is no automated method that allows for the classification of the wave or signal to identify a normal heartbeat from an abnormal one. In order to identify and classify anomalous patterns, the routine analysis of the clinical ECG almost exclusively depends on visual inspection. Currently, efforts are being made to find a methodology that brings precision in determining normal beats from aberrant ones. The use of tools provided by biostatistics will allow this work to address the analog-digital processing of biopotentials. The optimization in information processing is fundamental for obtaining relevant conclusions. Using digital techniques, the conditioning of signals will be sought for the identification and classification of patterns. The current paper will aim at the treatment and analysis of electrical potentials from biosignals for their subsequent processing through biostatistics, using data compression tools such as Principal Component Analysis (PCA). In order to identify and classify anomalous patterns in various cardiac pathologies, an attempt is made to find a methodology that brings precision when determining more accurate diagnoses.

 Keywords: PCA; Correlation; Variance

References

1. Camargo A. “PCA test: testing the statistical significance of Principal Component Analysis in R”. Peer Journal 10 (2022): e12967.
2. M Sudharsan and G Thailambal. “Alzheimer's disease prediction using machine learning techniques and principal component analysis (PCA)”. Proceedings of IVCSM 2K20 (International Virtual Conference on Sustainable Materials) 2 (2023): 87-1176.
3. Tusongjiang K and Wensheng G. “Power transformer fault diagnosis using FCM and improved PCA”. The Journal of Engineering. IET Electrical Engineering Academic Forum (2017).
4. Yalin W., et al. “A Novel Sliding Window PCA-IPF Based Steady-State Detection Framework and Its Industrial App”. IEEE Access. Magazine. Digital Object Identifier.
5. Alvarez Picaza C., et al. “Compresión de Datos aplicado a Sistemas de Energías Renovables”. Enfoque asociado a Bio-Información. Proceedings del II Congreso Latinoamericano de Ingeniería. Cartagena, Colombia (2019).
6. Alvarez Picaza C., et al. “Análisis de Componentes Principales desarrollado en Energías Renovables”. Aplicación a Sistemas Dinámicos y Biomédicos. Proceedings del III Congreso Argentino de Ingeniería – Chaco – Argentina (2016).
7. González AJ., et al. “Energy efficiency improvement in the cement industry through energy management”. IEEE-IAS/PCA 54^th Cement Industry Technical Conference (2023).

Citation

Citation: Carlos Alvarez Picaza., et al. “Biostatistical Analysis of Heart Diseases: Compression of Bio-Data using Principal Component Analysis”.Acta Scientific Medical Sciences 9.5 (2025): 79-83.

Copyright

Copyright: © 2025 Carlos Alvarez Picaza., et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.