The persistent drag of fatigue – whether from burnout, long work hours, or underlying health conditions – carries a significant economic and personal toll. Diagnosing these conditions, however, often relies on subjective self-reporting, a method prone to inconsistency and ill-suited for real-time monitoring. Now, researchers at the National University of Singapore are unveiling a modern wearable technology that promises a more objective and continuous assessment of fatigue levels, potentially revolutionizing how we understand and manage mental and physical exhaustion. This breakthrough centers on a novel “metahydrogel” platform paired with artificial intelligence, offering a significant leap forward in wearable sensor accuracy.
Current wearable devices, like smartwatches, attempt to track fatigue by monitoring cardiovascular signals – heart rate, blood pressure, and electrical activity – all linked to the autonomic nervous system. However, these readings are frequently obscured by “motion artifacts,” interference caused by everyday movements like walking or even subtle muscle twitches. Existing solutions often address only specific types of noise, leaving a gap in reliable, real-world data collection. The team in Singapore tackled this challenge by focusing on mitigating noise at the source: the interface between the sensor and the body. Their work, published in Nature Sensors on March 24, 2026, demonstrates a system capable of classifying fatigue levels with 92 percent accuracy.
A New Material for Clearer Signals
The core of the innovation lies in the metahydrogel artefact-mitigating platform (MAP). Unlike traditional sensors that rely on software to filter out noise *after* it’s captured, MAP actively suppresses interference during signal acquisition. The hydrogel itself is engineered with nanoparticles arranged in periodic bands, designed to scatter and absorb mechanical vibrations – effectively acting as a soundproofing layer for the sensor. Simultaneously, a biocompatible glycerol-water electrolyte within the gel controls the flow of ions, allowing the faint signals from the heart to pass through whereas blocking higher-frequency electrical noise from muscle activity. A final layer of machine learning further refines the signal, removing any remaining unstructured noise while preserving crucial physiological details.
According to Dr. Tian Guo, a Research Fellow at the National University of Singapore and first author of the study, the system achieves an electrocardiograph (ECG) signal-to-noise ratio of 37.36 dB and blood pressure deviation as low as 3 mmHg during movement. “Compared with current commercial devices, our metahydrogel platform demonstrates superior performance, particularly under motion conditions where artefact suppression is critical,” Dr. Tian explained. “Current smartwatches typically achieve ECG signal-to-noise ratios of 10-20 dB, which can decrease by approximately 40 per cent under motion due to artefacts and unstable contact. Our system achieves around 37 dB during daily activities.” This improved signal clarity translates to a significant increase in peak-detection accuracy, rising from 52 percent with conventional sensors to 93 percent with MAP.
Decoding Fatigue Through Cardiovascular Data
The team’s research demonstrates that fatigue leaves measurable traces in cardiovascular patterns – specifically, changes in heart rate variability, blood pressure, and the shape of the ECG waveform. However, capturing these subtle changes requires a clean, reliable signal. To validate their system, researchers developed a fully integrated wearable MAP device with wireless data transmission. Participants wore the device over multiple days, including during simulated driving tasks designed to induce fatigue. The resulting high-quality cardiovascular data was then fed into a deep-learning algorithm, which accurately identified fatigue levels 92 percent of the time – a substantial improvement over the 64 percent accuracy achieved using data from sensors without MAP. The system also met the ISO 81060-2 gold-standard requirements for blood pressure monitoring, further validating its clinical potential.
The potential applications of this technology extend beyond fatigue tracking. The researchers found that MAP effectively suppressed noise across a range of biosignals, including heart sounds, respiratory patterns, brain activity, and eye movements. This suggests the platform could be adapted for broader neurophysiological and mental health monitoring, offering new avenues for diagnosing and managing conditions like anxiety, depression, and sleep disorders. The autonomic nervous system plays a key role in regulating these conditions, and the ability to accurately monitor its signals could provide valuable insights for clinicians.
From Lab to Real-World Application
Developing the metahydrogel platform was a multi-year process, beginning with four years of foundational research into sensing technologies. The metahydrogel concept itself emerged approximately two and a half years ago, followed by a year of design and fabrication, during which the team created a library of hydrogels with varying material compositions to target different noise frequencies. Another year was dedicated to system integration and validation, including exploring its potential for mental health monitoring. Professor Ho Ghim Wei, who led the research team, emphasized the importance of collaboration with medical professionals. “We hope to work closely with mental-health physicians to better understand what types of physiological data are most relevant in real-world settings, as well as the level of accuracy required to meet clinical needs,” she stated. “Clinicians can provide valuable insights to assist us establish meaningful links between the data and pathological conditions.”
The team is now actively seeking industry partners to scale up production and improve device consistency. “Our current material synthesis and system fabrication are still largely based on laboratory processes,” Professor Ho added. “We aim to collaborate with industrial partners to optimise manufacturing strategies and advance the platform toward practical, product-level implementation.” The next step involves refining the manufacturing process and conducting larger-scale clinical trials to further validate the technology’s effectiveness and reliability.
Disclaimer: This article provides information for general knowledge and informational purposes only, and does not constitute medical advice. It’s essential to consult with a qualified healthcare professional for any health concerns or before making any decisions related to your health or treatment.
The development of this advanced wearable sensor represents a significant step towards objective, continuous mental health monitoring. As research progresses and the technology becomes more widely available, it could empower individuals to proactively manage their well-being and provide clinicians with valuable tools for personalized care. Share your thoughts on the potential impact of this technology in the comments below.
