Development and Pilot Test of a Virtual Reality Respiratory Biofeedback Approach

Abstract

Breathing exercises with biofeedback have benefits over breathing exercises without biofeedback. However, the traditional measurement of respiratory signals that is required as part of feeding back the breath incurs high cost and effort. We propose a novel virtual reality (VR) based approach to respiratory biofeedback that utilizes the positionally tracked hand controllers integrated into modern VR systems to capture and feedback the respiration-induced abdominal movements. In a randomized controlled laboratory study, we investigated the feasibility and efficacy of the developed biofeedback algorithm. In total, 72 participants performed a short breathing exercise in VR with or without respiratory biofeedback. The feedback integration resulted in a satisfactory user experience, a heightened breath awareness, a greater focus on slow diaphragmatic breathing and an increased respiratory sinus arrhythmia. This evidences that the novel biofeedback approach is low-cost, unobtrusive, usable and effective in increasing breath awareness and promoting slow diaphragmatic breathing in the context of VR-based breathing exercises. Future studies need to investigate the broader applicability and long-term effects.

Keywords: Abdominal breathing; Biofeedback; Diaphragmatic breathing; Respiratory biofeedback; Respiratory sinus arrhythmia; Virtual reality.

Fig. 1

Screenshot of the virtual environment in its default state (a) and while exhaling (b)

Fig. 2

Mean subjective focus on the breath by condition. Error bars represent 95% confidence intervals (CI)

Fig. 3

Relative duration of inhalation movement, exhalation movement, movement artifacts and no movement by condition

Fig. 4

Mean duration (sec) of inhalation and exhalation movements by condition. Error bars represent 95% CI

Fig. 5

Approximated respiratory rate (breaths per minute) by condition. Error bars represent 95% CI

Fig. 6

RMSSD (ms) by condition. Error bars represent 95% CI

Fig. 7

High frequency band power (HF) and low frequency band power (LF) by condition. Error bars represent 95% CI