On-line anxiety level detection from biosignals: Machine learning based on a randomized controlled trial with spider-fearful individuals

Ihmig, Frank R.; Gogeascoechea, H Antonio; Neurohr-Parakenings, Frank; Schäfer, Sarah; Lass‐Hennemann, Johanna; Michael, Tanja

doi:10.1371/journal.pone.0231517

Cited by 65 publications

(59 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the users watched the films, skin conductance was measured and recorded using electrodes on the index and middle finger of the left hand of the participant. The study reported that skin conductance response was not related to changes in anxiety levels, which is contradictory to the findings of other studies in which skin conductance was used as an indicator of anxiety [38,39]. Yet this contradiction might be specific to the group targeted by the intervention.…”

Section: Interventions For Adultscontrasting

confidence: 72%

Biofeedback-Based Connected Mental Health Interventions for Anxiety: Systematic Literature Review

Alneyadi¹,

Drissi²,

Almeqbaali³

et al. 2021

JMIR Mhealth Uhealth

View full text Add to dashboard Cite

Background: Connected mental health, which refers to the use of technology for mental health care and technology-based therapeutic solutions, has become an established field of research. Biofeedback is one of the approaches used in connected mental health solutions, which is mainly based on the analysis of physiological indicators for the assessment and management of the psychological state. Biofeedback is recommended by many therapists and has been used for conditions including depression, insomnia, and anxiety. Anxiety is associated with several physiological symptoms, including muscle tension and breathing issues, which makes the inclusion of biofeedback useful for anxiety detection and management.Objective: The aim of this study was to identify interventions using biofeedback as a part of their process for anxiety management and investigate their perceived effectiveness. Methods:A systematic literature review of publications presenting empirically evaluated biofeedback-based interventions for anxiety was conducted. The systematic literature review was based on publications retrieved from IEEE Digital Library, PubMed, ScienceDirect, and Scopus. A preliminary selection of papers was identified, examined, and filtered to include only relevant publications. Studies in the final selection were classified and analyzed to extract the modalities of use of biofeedback in the identified interventions, the types of physiological data that were collected and analyzed and the sensors used to collect them. Processes and outcomes of the empirical evaluations were also extracted.Results: After final selection, 13 publications presenting different interventions were investigated. The interventions addressed either primarily anxiety disorders or anxiety associated with health issues such as migraine, Parkinson disease, and rheumatology. Solutions combined biofeedback with other techniques including virtual reality, music therapy, games, and relaxation practices and used different sensors including cardiovascular belts, wrist sensors, or stretch sensors to collect physiological data such as heart rate, respiration indicators, and movement information. The interventions targeted different cohorts including children, students, and patients. Overall, outcomes from the empirical evaluations yielded positive results and emphasized the effectiveness of connected mental health solutions using biofeedback for anxiety; however, certain unfavorable outcomes, such as interventions not having an effect on anxiety and patients' preferring traditional therapy, were reported in studies addressing patients with specific physical health issues. Conclusions:The use of biofeedback in connected mental health interventions for the treatment and management of anxiety allows better screening and understanding of both psychological and physiological patient information, as well as of the association between the two. The inclusion of biofeedback could improve the outcome of interventions and boost their effectiveness; however, when used with patients s...

show abstract

Section: Interventions For Adultscontrasting

confidence: 72%

Biofeedback-Based Connected Mental Health Interventions for Anxiety: Systematic Literature Review

Alneyadi¹,

Drissi²,

Almeqbaali³

et al. 2021

JMIR Mhealth Uhealth

View full text Add to dashboard Cite

show abstract

“…A recent study by Ihmig et al, showed ML models can be used to detect anxiety in subjects with spider fear using ECG and respiratory signals [23]. In the current study, we tested how well the ML models can predict the ADys in anxiety disorder from ECG and respiratory signals recorded during a sleep study.…”

Section: Discussionmentioning

confidence: 94%

Predicting Autonomic Dysfunction in Anxiety Disorder from ECG and Respiratory Signals Using Machine Learning Models

et al. 2021

View full text Add to dashboard Cite

<p class="0abstract">Anxiety is a cognitive, behavioural, and biological response that prepares the individual to handle the stresses and conflicts of everyday life. The excessive appearance of this biological response is diagnosed as an anxiety disorder, which is often associated with Autonomic dysfunction (ADy). ADy is difficult to study in clinics with very few parameters available. Detection of ADy may not be possible/difficult in anxiety disorder with the existing method. In this study, we built machine learning models to identify ADy in subjects with anxiety using properties extracted from ECG and respiratory signals. For each dataset, statistical and frequency domain features were estimated from ECG and respiratory signals. Supervised machine learning (ML) algorithms were used to classify the subjects. Out of 23 features estimated, 11 were found to be statistically significant for the classification. We segmented the signals into 5, 10, and 30 minutes intervals to build generalized models. To overcome data imbalance, ensemble techniques like boosting was used. The highest accuracy was obtained in the SVM, Random forest and Gradient Boosting classifiers (cross-validation accuracy of 82.2%, 81.64% and 79.06% and; AUC of 0.81, 0.76 and 0.84) for 10 and 30 minutes segmented datasets. Our results showed that the features extracted from the ECG signal are a good marker for diagnosing ADy in patients with anxiety disorder. Further, a deep neural network-based model can be implemented that may achieve better accuracy for classification provided with the cost of a large number of datasets and computation time.</p>

show abstract

“…Among the emerging technologies that can contribute to the treatment of anxiety, depression and stress disorders, VR appears to be the most exciting and advanced [ 14 , 34 ]. Increasingly more studies confirm the efficacy of VR therapies in fields such as psychology and psychiatry [ 9 , 35 , 36 ]. Our results also confirm the efficacy of the applied VR-based therapy in reducing the symptoms of stress.…”

Section: Discussionmentioning

confidence: 99%

“…In their study, Jerdan et al concluded that VR is a promising form of relaxation [ 13 ]. However, most studies on the use of VR are related to the treatment of anxiety disorders, including arachnophobia [ 36 , 37 , 38 , 39 ] or social phobia, where Gebara et al described improvement in the area of a social anxiety disorder (SAD) across all scales used, and their study showed that exposure to VR leads to better treatment adherence and a reduction in SAD symptoms [ 40 ]. In their study, Urech et al observed an improvement in SAD symptoms as compared to pre-study and follow-up assessment and suggested that VR is a feasible and promising therapy medium [ 35 ].…”

Section: Discussionmentioning

confidence: 99%

The Use of Virtual Therapy in Cardiac Rehabilitation of Female Patients with Heart Disease

Jóźwik

Cieślik

Gajda³

et al. 2021

Medicina

View full text Add to dashboard Cite

Background and Objectives: Cardiovascular disease (CVD) has become increasingly prevalent in women, and it is also in this group that the risk of developing depression is the highest. The most commonly applied therapeutic intervention in cardiac rehabilitation is Schultz’s autogenic training, which has proven to be of little efficacy in reducing depression and anxiety disorders. At the same time, a growing number of scientific reports have been looking at the use of virtual reality (VR) to treat mental health problems. This study aimed at assessing the efficacy of virtual therapy in reducing levels of depression, anxiety, and stress in female CVD patients. Materials and Methods: The study included 43 women who were randomly divided into two groups: experimental group (N = 17), where eight-week cardiac rehabilitation was enhanced with VR-based therapeutic sessions, and control group (N = 26), where the VR therapy was replaced with Schultz’s autogenic training. Mental state parameters were measured using the Perception of Stress Questionnaire and Hospital Anxiety and Depression Scale (HADS). Results: In the experimental group, the sole parameter which failed to improve was HADS-Anxiety, which remained at the baseline level. In the control group, there was a deterioration in nearly all tested parameters except for HADS-Depression. Statistically significant differences in the efficacy of rehabilitation were recorded in relation to the level of stress in the sub-scales: emotional tension (p = 0.005), external stress (p = 0.012), intrapsychic stress (p = 0.023) and the generalized stress scale (p = 0.004). Conclusions: VR therapy is an efficient and interesting complement to cardiac rehabilitation, with proven efficacy in reducing stress levels.

show abstract

On-line anxiety level detection from biosignals: Machine learning based on a randomized controlled trial with spider-fearful individuals

Cited by 65 publications

References 44 publications

Biofeedback-Based Connected Mental Health Interventions for Anxiety: Systematic Literature Review

Biofeedback-Based Connected Mental Health Interventions for Anxiety: Systematic Literature Review

Predicting Autonomic Dysfunction in Anxiety Disorder from ECG and Respiratory Signals Using Machine Learning Models

The Use of Virtual Therapy in Cardiac Rehabilitation of Female Patients with Heart Disease

Contact Info

Product

Resources

About