Wearable “Stressomic” Biosensor Tracks Real-Time Hormone Levels, Predicts Anxiety with high Accuracy

In a breakthrough for personalized mental and physical health monitoring, researchers have developed a wearable microfluidic biosensor capable of continuously tracking three key stress hormones – cortisol, epinephrine, and norepinephrine – directly from sweat. Published in Science Advances, the “Stressomic” platform offers a non-invasive, real-time assessment of the body’s stress response with unprecedented sensitivity and accuracy, possibly revolutionizing how we understand and manage stress-related conditions.The device, built on a flexible printed circuit board (FPCB), measures hormone concentrations with picomolar to nanomolar sensitivity, providing data approximately every six minutes. Testing demonstrated the sensor’s ability to differentiate between physiological stress responses triggered by physical exertion and those stemming from psychological stress induced by emotionally evocative images. Researchers observed that while psychological stress didn’t significantly alter cortisol levels, it did elevate norepinephrine, mirroring increases in self-reported anxiety scores.

Importantly, the study also tracked the impact of a dietary supplement, revealing a progressive decline in cortisol levels and a slight decrease in norepinephrine without significant changes in epinephrine or subjective feelings, suggesting a baseline modulation of the neuroendocrine system.

Beyond simply measuring stress, the “Stressomic” platform can predict it. Machine learning models, trained on the initial 20 minutes of hormone data, accurately predicted negative affect (62%), positive affect (54%), and state anxiety (86%). Analysis using SHapley Additive exPlanations (SHAP) revealed that cortisol was the dominant factor in predicting negative affect, while norepinephrine and epinephrine worked together to predict anxiety, highlighting the complex interplay of thes hormones. No single hormone alone provided a complete picture.

The biosensor’s functionality was validated through rigorous testing, confirming consistent chemical reactions and stable signal performance even during rapid sweat flow, thanks to a microfluidic layout that maximizes incubation time. Data is streamed wirelessly via Bluetooth Low energy (BLE) to a custom mobile request and can also be accessed on a laptop.

Researchers acknowledge inter-individual variability in stress response – some participants exhibited rapid HPA axis suppression, while others maintained elevated sympathetic nervous system activity for longer periods.Thay recommend future iterations focus on process standardization and batch-specific calibration to address observed batch-to-batch variability.

The team envisions the “Stressomic” platform enabling personalized stress dashboards, early detection of unhealthy stress patterns, and objective evaluation of mental health interventions across diverse settings, including workplaces, clinics, athletic training, and everyday life. This technology represents a significant step towards proactive, data-driven mental and physical wellbeing.

Source: Tu,J., Yeom, J., Ulloa, J. C., Solomon, S.A., Min, J.,Heng,W., Kim, G., Dao, J., Vemu, R., Pang, M., Wang, C., kim, D.-H., & Gao, W. (2025). Stressomic: A wearable microfluidic biosensor for dynamic profiling of multiple stress hormones in sweat. Sci. Adv. 11(32). DOI:10.1126/sciadv.adx6491. https://www.science.org/doi/10.1126/sciadv.adx6491