Exploring Gender-Related Variations in Photoplethysmography

Area of Science:

• Biomedical Engineering
• Physiological Signal Analysis

Background:

• Photoplethysmographic signal (PPG) analysis is a noninvasive, cost-effective healthcare tool.
• PPG signals are known to be influenced by various factors, including subject gender.

Purpose of the Study:

• To determine which PPG signal parameters exhibit gender-related variations.
• To apply machine learning for gender classification using PPG mathematical models.

Main Methods:

• Utilized a machine learning approach to analyze PPG signals.
• Developed a mathematical model of the PPG signal for gender classification.
• Employed a cross-validation procedure for performance evaluation.

Main Results:

• Achieved 78% accuracy in classifying gender from PPG signals (90 out of 115 subjects).
• Identified heart cycle duration, systolic phase duration, and reflected wave variables as significant gender-related parameters.

Conclusions:

• PPG signal analysis reveals distinct gender-related variability.
• These findings contribute to understanding PPG signal characteristics for improved cardiovascular monitoring.