Alertness assessment by optical stimulation-induced brainwave entrainment through machine learning classification

Abstract

Background: Alertness plays a crucial role in the completion of important tasks. However, application of existing methods for evaluating alertness is limited due to issues such as high subjectivity, practice effect, susceptibility to interference, and complexity in data collection. Currently, there is an urgent need for a rapid, quantifiable, and easily implementable alertness assessment method.

Methods: Twelve optical stimulation frequencies ranged from 4 to 48 Hz were chosen to induce brainwave entrainment (BWE) for 30 s, respectively, in 40 subjects. Electroencephalogram (EEG) were recorded at the prefrontal pole electrodes Fpz, Fp1, and Fp2. Karolinska Sleepiness Scale, psychomotor vigilance test and β band power in resting EEG, were used to evaluate the alertness level before and after optical stimulation-induced BWE. The correlation between nine EEG features during the BWE and different alertness states were analyzed. Next, machine learning models including support vector machine, Naive Bayes and logistic regression were employed to conduct integrated analysis on the EEG features with significant differences.

Results: We found that BWE intensity, β band power, and γ band power exhibit significant differences across different states of alertness. The area under the receiver operating characteristic curve (AUC) of individual features for classifying alertness states was between 0.62-0.83. To further improve classification efficacy, these three features were used as input parameters in machine learning models. We found that Naive Bayes model showed the best classification efficacy in 30 Hz optical stimulation, with AUC reaching 0.90, an average accuracy of 0.90, an average sensitivity of 0.89, and an average specificity of 0.90. Meanwhile, we observed that the subjects' alertness levels did not change significantly before and after optical stimulation-induced BWE.

Conclusions: Our study demonstrated that the use of machine learning to integrate EEG features during 30 s optical stimulation-induced BWE showed promising classification capabilities for alertness states. It provided a rapid, quantifiable, and easily implementable alertness assessment option.

Keywords: Alertness; Brainwave entrainment; Electroencephalogram; Karolinska Sleepiness Scale; Machine learning; Optical stimulation; Psychomotor vigilance test.

Fig. 1

Comparison of three optical-induced stimulation entrainment features in different alertness states at twelve frequencies, respectively. a BWE. b β band power. C γ band power. *p < 0.05, **p < 0.01

Fig. 2

Area under the ROC curve for the classification of different alertness states using individual EEG features as characteristic parameters. a BWE. b β band power. C γ band power

Fig. 3

Classification of different alertness states using machine learning models that integrated three individual features, displaying a accuracy rate, b sensitivity, C specificity, d area under the ROC curve. SVM: support vector machine. NB Naive Bayes. LR logistic regression

Fig. 4

Analysis of the model fusion difference characteristics for different states of alertness under 30 Hz optical stimulation: a confusion matrix. b ROC curve

Fig. 5

Experimental protocol for alertness assessment by optical stimulation-induced brainwave entrainment through machine learning classification. PVT Psychomotor Vigilance Test. KSS Karolinska Sleepiness Scale. EEG electroencephalogram. BWE brainwave entrainment. SVM support vector machine. NB naive Bayes. LR logistic regression