Multimodal quantification of cognitive load using a printed wearable facial bio-potential system

Clinical Snapshot

Key Findings

• P Value: Not explicitly reported in abstract

• Effect Size: Mean Spearman correlation ρ = 0.792 for facial EMG model; ρ = 0.739 for EEG-only model; EOG features did not pass feature-selection threshold in seated paradigm

• Primary Outcome: Cross-subject prediction of NASA-TLX weighted workload score using facial EMG features in a leave-one-subject-out model

• Nnt Or Sensitivity: Mean absolute error = 4.3 on NASA-TLX 0–100 scale for facial EMG model; no sensitivity/specificity reported (continuous prediction task, not classification)

• Confidence Interval: 95% CI for facial EMG Spearman ρ: [0.747, 0.836]

Clinical Application

The printed wearable form factor is a genuine advance in comfort and unobtrusiveness compared to conventional EEG caps. However, clinical deployment requires: (1) validation in much larger and more diverse cohorts; (2) regulatory approval of the device; (3) standardised cognitive load task paradigms; (4) integration with clinical workflows; and (5) demonstration of clinical utility beyond research correlation metrics. This device is not TGA-approved and is not available on the Australian Register of Therapeutic Goods. There is no current PBS listing or RACGP guideline relevance. Potential future applications in Australian healthcare could include: occupational health monitoring for high-cognitive-demand workers (surgeons, pilots, emergency clinicians), neurorehabilitation monitoring post-TBI or stroke, and educational neuroscience research. The RACGP and relevant specialist colleges (RACP Neurology, RANZCP) would require substantially larger RCT-level or prospective cohort evidence before any clinical recommendation could be considered. Australian researchers interested in this technology should note that the Tel Aviv University group holds the primary intellectual property and that local replication studies would be needed. Currently applicable only to healthy young adults in controlled or semi-controlled settings as a research tool. Not yet validated for clinical populations including those with neurological conditions (TBI, dementia, ADHD), psychiatric disorders, or occupational health monitoring contexts.

Abstract

Objective.Cognitive load refers to the amount of mental effort required to process information and perform tasks. It has a strong impact on both learning and task performance and, therefore, plays a central role in cognitive neuroscience, psychology, neurology, human-machine interaction, and education research. Despite its significance, measuring cognitive load is challenging due to its complex and dynamic nature, influenced by task complexity, individual differences, and emotional states. While standard methods are based on subjective self-reports, numerous objective methods have been explored to assess cognitive load, such as electroencephalography (EEG), heart rate variability, and performance-based metrics. Despite these efforts, it remains challenging to objectively measure cognitive load in stationary and even more so in freely moving individuals.Approach.In this study, a wireless wearable system was employed to collect facial bio-potential markers and systematically compare their sensitivity to cognitive load. A dedicated task paradigm was developed and validated to induce graded cognitive load, allowing precise synchronization of physiological signals with task events. Facial muscle activity, eye movements, and brain activity were acquired simultaneously using a single facial electrode array.Main results.Across nine participants, entropy-based features tracked cognitive load more closely than conventional band-power measures. Facial EMG was the most informative modality: a cross-subject (leave-one-subject-out) model predicted the NASA-TLX weighted workload score with a mean Spearman correlation= 0.792 (95% CI [0.747, 0.836]; mean absolute error4.3, on a NASA-TLX 0-100 scale), and a single forehead-EMG entropy feature (the EMG-band entropy of forehead channel Ch14, above the right eyebrow) was selected in every cross-subject fold, generalizing across all participants without subject-specific calibration. An EEG-only model carried weaker but genuine cross-subject information (= 0.739), whereas EOG features did not pass the feature-selection threshold in this seated paradigm.Significance.Facial bio-potentials offer a practical, wearable system for objective cognitive load assessment. An outdoor pilot experiment further demonstrated electrophysiological measures under non-laboratory conditions. These findings offer insights into the suitability of different physiological indicators for assessing cognitive load, particularly the informativeness of facial EMG for seated assessment and the robustness of blink-based measures under ambulatory motion, contributing to the future development of practical measurement techniques in dynamic everyday settings.

References

1. 1.Teitelbaum, D., Ibrahim, R., Man, H., Luxembourg, N., Re, D., & Hanein, Y. (2026). Multimodal quantification of cognitive load using a printed wearable facial bio-potential system. Journal of Neural Engineering. https://doi.org/10.1088/1741-2552/ae89e9