Multivariable relationships between autonomic nervous system related indices in hyperbaric environments

Area of Science:

• Physiology
• Biomedical Engineering
• Data Science

Background:

• Autonomic Nervous System (ANS) responses are altered by hyperbaric conditions.
• Heart Rate Variability (HRV) analysis reflects ANS activity.
• Simulated hyperbaric environments provide controlled conditions for studying physiological responses.

Purpose of the Study:

• To model relationships between HRV parameters and simulated diving depths.
• To investigate linear and nonlinear dependencies within HRV signals.
• To develop predictive models for diver safety using ECG data.

Main Methods:

• Collected electrocardiogram (ECG) data from 17 subjects at simulated depths (0-40m).
• Analyzed HRV parameters using linear regression and Mutual Information.
• Employed artificial neural networks, including Self-Organizing Maps (SOM), for data modeling and clustering.

Main Results:

• Characterized linear and nonlinear relationships between HRV parameters, biophysical variables, and pressure.
• Successfully modeled and clustered complex physiological data using SOM.
• Established a foundation for predicting HRV changes under hyperbaric stress.

Conclusions:

• The developed models can predict HRV parameters at high depths.
• These predictive models offer potential for enhancing diver safety by providing early warnings.
• ECG signal processing at sea level could preemptively identify potential risks before immersion.