On-line anxiety level detection from biosignals: ML in a spider-fear RCT (Ihmig … Michael; PLoS One 2020)

Ihmig and colleagues recorded ECG, palm EDA and chest respiration with a PLUX BITalino while 80 spider-fearful adults watched 16 one-minute spider clips, and trained classifiers on 10-60 s windows to detect anxiety level. Bagged trees reached 89.8% for two levels and 74.4% for three levels, but under 10-fold window-level CV (not subject-independent). Data released as PhysioNet ecg-spider-clip (57 participants, ODC-By).

• Form factor: chest + palm research kit (PLUX BITalino)

We present performance results concerning the validation for anxiety level detection based on trained mathematical models using supervised machine learning techniques. The model training is based on biosignals acquired in a randomized controlled trial. Wearable sensors were used to collect electrocardiogram, electrodermal activity, and respiration from spider-fearful individuals. We designed and applied ten approaches for data labeling considering individual biosignals as well as subjective ratings. Performance results revealed a selection of trained models adapted for two-level (low and high) and three-level (low, medium and high) classification of anxiety using a minimal set of six features. We obtained a remarkable accuracy of 89.8% for the two-level classification and of 74.4% for the three-level classification using a short time window length of ten seconds when applying the approach that uses subjective ratings for data labeling. Bagged Trees proved to be the most suitable classifier type among the classification models studied. The trained models will have a practical impact on the feasibility study of an augmented reality exposure therapy based on a therapeutic game for the treatment of arachnophobia.

Verbatim from Europe PMC (opens in a new tab) · Licence: cc by

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.