Data project opens up new ways to prevent accidents

Discovering Safety is a project from HSE scientists who are working with industry partners to build a massive data warehouse containing information on safety.

It will store and collate data to understand how accidents can be prevented using Artificial Intelligence, which will read and anonymise the data. Work begins with over 70,000 reports sent to HSE every year under the Reporting of Incidents, Diseases and Dangerous Occurrences Regulations (RIDDOR), about 130 of which involve fatalities.

Commenting, Joseph Januszewski, an HSE data scientist coordinating the Discovering Safety team, said: “We are using the data warehouse to process the accident reports to work out the activities being undertaken and the risks they posed, the mitigations that were in place and those that should have been in place. We can then use this learning to prevent similar accidents from happening in the future.”

Data can pinpoint hazards which, if not corrected, could lead to an accident. Information can also be used for proactive action, based on past results. Photograph: iStock

The warehouse will also store more nuanced information using the stories and context of accidents in documents such as RIDDOR reports and HSE inspector reports.

Januszewski added: “Investigation reports contain much more information about why an incident happened and how it could have been prevented. They encapsulate the learning and training of highly experienced inspectors, so have a great deal of learning to offer.”

Over the next year, HSE will share the first set of data as a ‘proof of concept’ with a subset of users, who will be able to use it to develop their own products and systems.

“We will be engaging with industry in the coming months to find out how they would use the data warehouse and gain most value from it. We will then develop the warehouse further based on their opinions,” said Januszewski.

Discovering Safety would like to hear from anyone in industry who is interested in finding out more or in helping develop the data warehouse by giving their perspective or sharing data, email: [email protected]