A Prototype Framework Design for Assisting the Detection of Atrial Fibrillation Using a Generic Low-Cost Biomedical...

Area of Science:

• Biomedical Engineering
• Cardiovascular Health
• Signal Processing

Background:

• Cardiovascular diseases are a leading global cause of death.
• Low-cost biomedical sensors offer portability and low power consumption but lack clinical accuracy.
• Accurate data acquisition remains a challenge for widespread clinical use of these sensors.

Purpose of the Study:

• To present a methodology for building a prototype framework using a low-cost commercial sensor.
• To develop a classification algorithm for distinguishing normal sinus rhythms from atrial fibrillation.
• To demonstrate the applicability of the proposed algorithm across various low-cost biomedical sensors.

Main Methods:

• Developed a four-module application: digitalization, signal processing/filtering, data calibration, and classification.
• Input signals include electrocardiograph (ECG) data in PDF or JPEG formats.
• Utilized the Symbolic Recurrence Quantification Analysis (SRQA) algorithm on RR interval time series for classification.

Main Results:

• The developed framework successfully processes and analyzes biomedical signals from low-cost sensors.
• The SRQA algorithm effectively classifies individuals with normal sinus rhythms versus atrial fibrillation.
• The methodology achieves good results without requiring complex or expensive equipment.

Conclusions:

• The proposed framework enhances the clinical utility of low-cost biomedical sensors.
• The SRQA algorithm offers a robust and versatile method for analyzing cardiovascular data.
• This approach facilitates more accessible and accurate cardiovascular disease monitoring.