20 July 2023
Data can help to inform health and safety policy in the workplace. Graham Sharp provides an insight.
THE INTRODUCTION of artificial intelligence (AI) and wearable technologies into the UK, offers tremendous potential for cutting workplace accidents and improving workplace safety, health, and productivity. We can already see those changes happening in the United States, where the AI wearable device market for health and safety monitoring has been pioneered and where the market is more developed. One of the key benefits of these new wearable AI technology solutions, aside from improvement of employee health and wellbeing, is the detailed real time data that businesses can collect about the workplace environment, including data on task movements of specific roles.
Workplace accidents and injury, such as musculoskeletal disorder (MSDs), are one of the biggest causes of dips in productivity and one of the main reasons that workers take time off sick in the UK. In fact, according to the latest figures from the Health and Safety Executive, the total number of cases of work-related MSDs in 2021/22 in the UK, was 477,000 which equates to a total of 27% of all work-related ill health cases and 24% of all working days lost due to work-related ill health. Wearable technologies that collect and track detailed data from employees to better understand where the biggest risks to workplace safety originate, have the ability to help businesses to cut these figures dramatically.
In the UK, AI solutions such as the Modjoul SmartBelt, Ansell’s Inteliforz, that tracks hand and wrist movement and WearHealth exoskeleton scanning technology, are just starting to come onto the market bringing disruptive change. Not only this, AI data-driven solutions allow for a more advanced level of protection for workers at high risk of workplace injury and an easy way for employers to collect detailed data that can help them to track workplace activity and plan for a more rigorous health and safety training regime.
The AI algorithms can analyse historical data on manual handling tasks, workplace conditions, and injury records to identify patterns and correlations. By analysing this data, AI can help in identifying high-risk situations or tasks that are prone to injuries. The wearable technology continuously measures and tracks progress, allowing companies to access granular data analysis reports on bends, twists, stooping, crouching, and reaching, which can be then processed in detail to offer insights across a global workforce risk analysis. Using data analytics in this way can help to build a picture of where the key weaknesses lie and where accidents are most likely to happen. The result of this comprehensive analysis quantifies the impact of tasks on workers and offers potential solutions for risk reduction.
Products such as the Ansell Inteliforz hand pod and Modjoul SmartBelt will produce a haptic buzz to help workers correct their posture when bending, lifting or twisting. Each of these individual movements is recorded and analysed to help build a picture of risk and see if there are patterns emerging from the data.
For example, bends of 60 degrees or more — when a worker bends over at the waist rather than using their legs to pick up an item — is one of the riskiest movements and a leading cause of workplace injuries. The Modjoul SmartBelt closely tracks these movements, and its research has found that these types of movement decline rapidly within 10-25 hours of wearing the SmartBelt and as new muscle memories are formed. The same applies to exoskeleton technology. Wearers are not only aided by the exoskeleton when lifting heavy weights, but the wearable technology helps to retrain the muscles to lift and move more safely and with less risk of injury.
In jobs that require a lot of physical lifting and stretching in environments like warehousing and construction, it is the newer staff that are often at most at risk of injury. In fact, wearable technology statistics show us that within the first two months of employment, there is a 70% increased risk of injury and that 1 in 8 of all workplace injuries happen on an employee’s first day on the job.
We can see that AI algorithms can identify patterns and factors that contribute to the occurrence of injuries, which means that managers can ensure that they proactively intervene to minimise risks. Predictive analytics can also help optimise work schedules, how workload is distributed and task assignments to minimise the likelihood of injuries.
Results driven planning
Once weak points have been identified and a comprehensive step by step plan has been drawn up, organisations can adopt a more proactive approach to risk management using wearable technology to help bring about gradual behaviour change across an organisation. The changes can be tracked using real time data, target setting and easy ongoing assessments.
This more rigorous planning and assessment has positive knock-on effects on staff wellbeing. As levels of sickness fall, employees feel that they are being effectively trained and supported as they learn and adjust their behaviour.
Effective planning measures may include:
More comprehensive training on certain aspects of the job role looking at specific groups based on risk factors such as age, new starters, riskiest activities etc
Involving staff in targets and improvements e.g. reward based systems. In the US, they have found that if workers themselves are able to track their own progress either on their own mobile phones via a bespoke app or on supplied in house technology, they are more invested in their own health and wellbeing. So, for example, they can track their performance and see whether they are reducing their hazardous movements. This can be potentially linked to a rewards-based system where they may get a reward when they hit specific targets. This type of gamification has been shown to improve employee buy-in because individuals feel that the business is committed to improving health and wellbeing which is a great contributor towards higher staff retention levels.
Tracking progress post training to ensure that employees stay on track and act on the training they have had on risk avoidance. Where weaknesses are identified, wearable technology can be used to help to reinforce correct movement and avoid potential injury.
By using data analysis in this way, a more accurate and targeted training regime can be implemented and training budgets spent only where needed and where risk of injury is greatest.
The Enel Group example
Let’s look at an example of how data can help to inform policy. The Enel Group is a leading manufacturer and distributor of electricity and gas and is present in more than 30 countries including the UK. The company uses sustainable technologies to supply energy to people.
The company identified WearHealth exoskeleton scanning technology as a potential solution to certain physically challenging operations undertaken by its maintenance workers. Once identified, the appropriate exoskeleton had been tested in terms of usability, comfort, and support, using subjective questionnaires and objective lab data. However, it was not clear how exoskeletons could impact workers’ overall workload in a real work environment over longer periods.
To test this, a group of workers performed maintenance operations with and without an exoskeleton suit. In both cases a wearable device was used to gather heart rate, heart rate variability and movement data. The resulting data was converted to a 1-10 workload scale (physical & mental) using WearHealth's proprietary artificial intelligence algorithms based on ISO standards.
A 27% reduction in workload was identified when workers wore the exoskeleton that was recommended by the WearHealth platform, and overall findings suggested that during maintenance operations and breaks, the exoskeleton provided support during physically challenging periods and also enabled a faster recovery between demanding tasks. A step by step roll out is now planned by the Group.
Return on investment
There is no denying that wearable technology costs money to roll out across a business, but the US model has shown that this initial outlay is soon recouped as sickness and injury levels drop, injury claims are far less frequent, and health and safety budgets are spent more wisely. As the Enel Group example above shows, this technology can also improve productivity and efficiency for certain tasks while improving health and wellbeing. We would not be able to know that without access to real time data. Businesses can now have access to solid information that can be used to underpin health and safety decision making and transform staff health and wellbeing.
Graham Sharp is managing director of health and safety consultancy, Stanley. For more information, visit www.stanleyhandling.co.uk