Age and Gender Impact on Heart Rate Variability towards Noninvasive Glucose Measurement

Area of Science:

• Biomedical Engineering
• Physiology
• Machine Learning

Background:

• Heart rate variability (HRV) reflects autonomic nervous system function and can be used for noninvasive blood glucose estimation.
• Existing research often focuses on healthy individuals and limited HRV measurement durations.
• A comprehensive understanding of factors influencing HRV is needed to enhance diagnostic tools.

Purpose of the Study:

• To investigate the influence of patient age and gender on heart rate variability (HRV) parameters.
• To refine a noninvasive blood glucose estimator by accounting for age and gender-related HRV variations.
• To explore HRV in both healthy individuals and those with arrhythmia across various measurement lengths.

Main Methods:

• Analysis of electrocardiogram (ECG) data from 284 subjects across four datasets.
• Application of statistical correlation methods: point biserial, Pearson, and Spearman rank correlations.
• Development of mathematical models, machine learning, and deep learning algorithms for classification and estimation.

Main Results:

• A moderate correlation (0.58) was found between age, gender, and HRV parameters.
• The study successfully identified the influence of individual input parameters on HRV.
• Developed models demonstrated the capability to detect these influences.

Conclusions:

• Age and gender are significant confounding factors in HRV analysis.
• Accounting for age and gender can improve the accuracy of noninvasive glucose estimators.
• This holistic approach provides a more nuanced understanding of HRV compared to previous studies.