Reviewing 40 peer-reviewed, English-language studies published between 2013 and 2024, the paper evaluates how technologies such as inertial measurement units (IMUs), electromyography (EMG) sensors, and pressure sensors are reshaping ergonomic risk assessment across high-risk industries.
Get all the details: Grab your PDF here!
WMSDs are one of the most common occupational health challenges worldwide. Caused by repetitive strain, awkward postures, and prolonged physical stress, they affect muscles, tendons, ligaments, cartilage, bones, and nerves.
Its impact is far-reaching: More than 40 million workers in the European Union and nearly one million workers in the United States are affected each year, with productivity losses in industrialized economies reaching up to 2 % of gross domestic product.
Despite ergonomic standards and workplace interventions, many traditional approaches rely on periodic assessments rather than continuous monitoring, limiting their ability to prevent injury before it occurs.
Why Wearables Matter in Industry 4.0
Industry 4.0 has introduced cyber-physical systems, artificial intelligence (AI), and the Internet of Things (IoT) into industrial environments, enabling real-time data collection and feedback.
Wearable technologies, from smart vests to sensorized insoles, extend this capability directly to workers.
According to the review, wearables currently support diagnostic and early-intervention ergonomics, providing continuous insight into posture, movement, muscle activity, and physical load.
While these systems are not yet fully predictive or prescriptive, they offer a significant step beyond observational assessments by embedding sensing and analytics into daily operations.
The Evidence Backs Wearable Sensors
Across construction, manufacturing, healthcare, and forestry, the reviewed studies demonstrate consistent gains in ergonomic risk detection:
- In construction, IMU-based systems automatically detect hazardous postures and alert workers via smartphone applications, enabling real-time self-correction.
- Insole pressure systems classify awkward postures such as squatting, stooping, and kneeling with high accuracy; one study reported posture classification rates of 99.70 % using support vector machines.
- Deep learning models, including bidirectional long short-term memory (LSTM) networks, classify physical load levels during material handling tasks with accuracies ranging from 74.6 % to 98.6 %, based on gait and lower-body motion data.
Within forestry, activity trackers measuring heart rate, steps, and reaction time revealed patterns of physical and cognitive fatigue linked to increased accident risk, while also highlighting seasonal effects and the importance of worker acceptance.
In healthcare settings, wearable inertial sensors combined with digital human modeling can be used to identify high-risk postures during patient handling, including measurable gender differences in spinal loading.
These insights inform ergonomic training and workplace redesign rather than immediate automated correction.
Limits of Automation, for Now
While machine learning significantly improves classification accuracy, the review emphasized that most systems remain human-in-the-loop.
Wearables typically provide feedback that supports worker awareness and self-adjustment, rather than enforcing corrective actions or autonomously adapting tasks.
Fully predictive or prescriptive ergonomics, where systems anticipate injury risk and automatically intervene, remain a research goal rather than an industrial reality.
The review also highlighted several persistent challenges involved in workplace protection.
In construction and forestry, sensor durability, environmental interference, scalability, and privacy concerns complicate deployment.
In healthcare, high costs, comfort issues, and acceptance barriers limit uptake, particularly for motion tracking and modeling systems that require individualized calibration and alignment with institutional safety standards.
These non-technical factors often determine whether wearable systems move beyond pilot studies into sustained use.
Privacy and Ethical Oversight
Continuous monitoring raises ethical concerns around consent, transparency, and psychological stress. Workers may perceive wearables as surveillance rather than safety tools if data practices are unclear.
The authors stress the importance of transparent governance, employee control over personal data, and compliance with privacy regulations such as the General Data Protection Regulation (GDPR).
Federated learning, where data remain on local devices while models are trained collaboratively, offers a promising privacy-preserving approach. However, its application to ergonomic risk detection has yet to be validated at scale or in safety-critical industrial environments.
Is There a Future for Wearable Sensors in the Workplace?
The review concludes that wearable sensors already provide actionable value for ergonomic risk detection, but their long-term impact depends on more than technical performance.
Future progress will require standardized evaluation protocols, long-term real-world validation, improved comfort and usability, and ethically grounded AI integration aligned with occupational safety regulations and industrial interoperability standards.
The evidence suggests that wearable sensors could become a practical tool in the ongoing effort to reduce workplace injuries in an increasingly data-driven industrial world.
Journal Reference
Alenjareghi, M. et al (2026). Wearable sensors in Industry 4.0: Preventing work-related musculoskeletal disorders. Sensors International, 7, 100343. DOI: 10.1016/j.sintl.2025.100343
Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of AZoM.com Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.