Respiratory Markers Significantly Enhance Anxiety Detection Using Multimodal Physiological Sensing

Gazi, Asim H.; Lis, Patrick; Mohseni, Arshawn; Ompi, Christopher; Giuste, Felipe; Shi, Wenqi; Inan, Omer T.; Wang, May D.

doi:10.1109/bhi50953.2021.9508589

Cited by 4 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The best performance for RF was achieved with EEG, then with a combination of ECG and EDA, and, finally, with a combination of ECG, EDA, and RSP. However, this result contradicts the results of Gazi et al [ 29 ], who found an accuracy of 78% with a combination of ECG and EDA and 85% with a combination of ECG, EDA, and RSP. A combination of skin temperature (ST), EDA, RSP, and HR led to the best performance using SVM, followed by a study [ 28 ] using only EEG and a study [ 23 ] that combined ECG and EEG.…”

Section: Modelscontrasting

confidence: 91%

“…Ihmig et al [ 15 ], Gazi et al [ 29 ], and Selzler et al [ 30 ] belong to this second category and focused only on phobic participants. Specific phobia is a common mental disorder that affects about 7.4% of the population at least once in their lives.…”

Section: Methodsmentioning

confidence: 99%

“…The state section measures state anxiety (i.e., how an individual feels right now), and the trait section measures trait anxiety (i.e., how an individual feels generally). Another method used by Gazi et al [ 29 ] and Miranda et al [ 31 ] consisted of labeling the time-series data according to the video clips stimulating anxiety and no-anxiety events.…”

Section: Methodsmentioning

confidence: 99%

“…Thus, the sequential function stops adding new features when there is no further improvement in accuracy. In another study, Gazi et al [ 29 ] employed a permutation approach to quantify feature importance. Specifically, this consisted of randomly permuting feature j ∈ 1, 2, …, J of the testing set K = 30 different times and averaging the resulting accuracy decreases across all iterations of k ∈ 1, 2, …, K .…”

Section: Featuresmentioning

confidence: 99%

“…SVM [ 27 , 29 , 31 ] and RF [ 29 , 30 , 34 ] were the predominant algorithms used in the remaining studies. The RF consists of many individual decision trees that work as ensembles.…”

Section: Modelsmentioning

confidence: 99%

See 4 more Smart Citations

Machine Learning for Anxiety Detection Using Biosignals: A Review

2022

View full text Add to dashboard Cite

Anxiety disorder (AD) is a major mental health illness. However, due to the many symptoms and confounding factors associated with AD, it is difficult to diagnose, and patients remain untreated for a long time. Therefore, researchers have become increasingly interested in non-invasive biosignals, such as electroencephalography (EEG), electrocardiogram (ECG), electrodermal response (EDA), and respiration (RSP). Applying machine learning to these signals enables clinicians to recognize patterns of anxiety and differentiate a sick patient from a healthy one. Further, models with multiple and diverse biosignals have been developed to improve accuracy and convenience. This paper reviews and summarizes studies published from 2012 to 2022 that applied different machine learning algorithms with various biosignals. In doing so, it offers perspectives on the strengths and weaknesses of current developments to guide future advancements in anxiety detection. Specifically, this literature review reveals promising measurement accuracies ranging from 55% to 98% for studies with sample sizes of 10 to 102 participants. On average, studies using only EEG seemed to obtain the best performance, but the most accurate results were obtained with EDA, RSP, and heart rate. Random forest and support vector machines were found to be widely used machine learning methods, and they lead to good results as long as feature selection has been performed. Neural networks are also extensively used and provide good accuracy, with the benefit that no feature selection is needed. This review also comments on the effective combinations of modalities and the success of different models for detecting anxiety.

show abstract

Section: Modelscontrasting

confidence: 91%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Featuresmentioning

confidence: 99%

“…SVM [ 27 , 29 , 31 ] and RF [ 29 , 30 , 34 ] were the predominant algorithms used in the remaining studies. The RF consists of many individual decision trees that work as ensembles.…”

Section: Modelsmentioning

confidence: 99%

See 3 more Smart Citations