Key result
A novel multimodal deep fusion model utilizing spectrogram and 1D ECG outperformed classical HRV-based machine learning models by 9% and baseline deep learning models by 2.5% in predicting multi-level stress.
Why the study?
Existing machine learning models for ECG-based stress assessment perform poorly, focus only on binary stress, and classify entire experiences rather than enabling real-time, multi-level evaluation.
Does a multimodal deep fusion model utilizing spectrogram and 1D ECG improve stress prediction accuracy in healthy users experiencing a VR environment?
Does a multimodal deep fusion model utilizing spectrogram and 1D ECG improve stress prediction accuracy in healthy users experiencing a VR environment?
Absolute Event Rate: 66.6% vs 57.1%
A novel multimodal deep fusion model utilizing 1D ECG and spectrograms improves multi-level stress assessment accuracy in a VR environment compared to classical machine learning models.
Hypothesis-generating for multimodal ECG stress prediction; prospective validation required before clinical consideration.
ECG is an attractive option to assess stress in serious Virtual Reality (VR) applications due to its non-invasive nature. However, the existing Machine Learning (ML) models perform poorly. Moreover, existing studies only perform a binary stress assessment, while to develop a more engaging biofeedback-based application, multi-level assessment is necessary. Existing studies annotate and classify a single experience (e.g. watching a VR video) to a single stress level, which again prevents design of dynamic experiences where real-time in-game stress assessment can be utilized. In this paper, we report our findings on a new study on VR stress assessment, where three stress levels are assessed. ECG data was collected from 9 users experiencing a VR roller coaster. The VR experience was then manually labeled in 10-seconds segments to three stress levels by three raters. We then propose a novel multimodal deep fusion model utilizing spectrogram and 1D ECG that can provide a stress prediction from just a 1-second window. Experimental results demonstrate that the proposed model outperforms the classical HRV-based ML models (9% increase in accuracy) and baseline deep learning models (2.5% increase in accuracy). We also report results on the benchmark WESAD dataset to show the supremacy of the model.
No takes yet. Share an insight, caveat, or question.
Ahmad et al. (2021) studied Stress (n=9). Multimodal deep fusion model (spectrogram and 1D ECG) vs. Classical HRV-based ML models and baseline deep learning models was evaluated on Accuracy of 3-level stress prediction. A novel multimodal deep fusion model utilizing spectrogram and 1D ECG outperformed classical HRV-based machine learning models by 9% and baseline deep learning models by 2.5% in predicting multi-level stress.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: