Automated anxiety detection using probabilistic binary pattern with ECG signals

• Published in: Computer methods and programs in biomedicine Vol. 247; p. 108076
• Main Authors: Baygin, Mehmet, Barua, Prabal Datta, Dogan, Sengul, Tuncer, Turker, Hong, Tan Jen, March, Sonja, Tan, Ru-San, Molinari, Filippo, Acharya, U. Rajendra
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.04.2024
• Subjects: Algorithms; Anxiety - diagnosis; Anxiety Disorders; combinational majority voting; ECG signal classification; ECG-based mood detection; Electrocardiography; Feature engineering; Humans; Probabilistic binary pattern; Signal Processing, Computer-Assisted; Wavelet Analysis; ECG signal classification; Probabilistic binary pattern; ECG-based mood detection; combinational majority voting; Feature engineering
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2024.108076

•We presented a self-organized feature engineering model using the presented PBP..•Our proposed model attained over 98% accuracy.•We proposed a lightweigh ECG classification model.•This study sets a new benchmark in ECG signal classification for wearable technologies, optimizing both performance and efficiency. Anxiety disorder is common; early diagnosis is crucial for management. Anxiety can induce physiological changes in the brain and heart. We aimed to develop an efficient and accurate handcrafted feature engineering model for automated anxiety detection using ECG signals. We studied open-access electrocardiography (ECG) data of 19 subjects collected via wearable sensors while they were shown videos that might induce anxiety. Using the Hamilton Anxiety Rating Scale, subjects are categorized into normal, light anxiety, moderate anxiety, and severe anxiety groups. ECGs were divided into non-overlapping 4- (Case 1), 5- (Case 2), and 6-second (Case 3) segments for analysis. We proposed a self-organized dynamic pattern-based feature extraction function―probabilistic binary pattern (PBP)―in which patterns within the function were determined by the probabilities of the input signal-dependent values. This was combined with tunable q-factor wavelet transform to facilitate multileveled generation of feature vectors in both spatial and frequency domains. Neighborhood component analysis and Chi2 functions were used to select features and reduce data dimensionality. Shallow k-nearest neighbors and support vector machine classifiers were used to calculate four (=2 × 2) classifier-wise results per input signal. From the latter, novel self-organized combinational majority voting was applied to calculate an additional five voted results. The optimal final model outcome was chosen from among the nine (classifier-wise and voted) results using a greedy algorithm. Our model achieved classification accuracies of over 98.5 % for all three cases. Ablation studies confirmed the incremental accuracy of PBP-based feature engineering over traditional local binary pattern feature extraction. The results demonstrated the feasibility and accuracy of our PBP-based feature engineering model for anxiety classification using ECG signals.