Key result
An LSTM model using blood volume pulse signals achieves ~98% accuracy for recognizing anxiety levels.
Why the study?
Increased psychological pressure from the COVID-19 pandemic highlighted the need for an unbiased measure to aid in the preliminary diagnosis of anxiety disorders and serve as initial treatment in cognitive-behavioral therapy.
Does a long short-term memory architecture using BVP signals accurately recognize three levels of anxiety during virtual reality exposure?
Does a long short-term memory architecture using BVP signals accurately recognize three levels of anxiety during virtual reality exposure?
An LSTM architecture using BVP-derived parameters achieved 98% accuracy in recognizing three levels of anxiety during virtual reality exposure.
May support VR-based anxiety biofeedback tools; leaves open validation in larger clinical cohorts.
BACKGROUND: The COVID-19 pandemic has resulted in increased psychological pressure on mental health since 2019. The resulting anxiety and stress have permeated every aspect of life during confinement. OBJECTIVE: To provide psychologists with an unbiased measure that can aid in the preliminary diagnosis of anxiety disorders and be used as an initial treatment in cognitive-behavioral therapy, this article introduces automated recognition of three levels of anxiety. METHODS: Anxiety was elicited by exposing participants to virtual environments inspired by social situations in reference to the Liebowitz social anxiety scale. Relevant parameters, such as heart rate variability and vasoconstriction were derived from the measurement of the blood volume pulse (BVP) signal. RESULTS: A long short-term memory architecture achieved an accuracy of approximately 98% on the training and test set. CONCLUSION: The generated model allowed for careful study of the state of seven phobic participants during virtual reality exposure (VRE).
No takes yet. Share an insight, caveat, or question.
Handouzi et al. (2023) studied Anxiety disorders (n=7). Virtual reality exposure (VRE) aided-diagnosis system using long short-term memory architecture was evaluated on Accuracy of anxiety recognition on training and test set. A long short-term memory architecture using blood volume pulse signals during virtual reality exposure achieved approximately 98% accuracy in recognizing three levels of anxiety.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: