Invented by the artificial intelligence company Zone7, who are based in California’s Silicon Valley, Liverpool have been using cutting-edge computer algorithms that detect injury risk and recommend pre-emptive action.
It all helps to explain why manager Jurgen Klopp chose to rotate nine key players in beating Southampton on Tuesday night, barely three days after needing 120 minutes to win the FA Cup.
It perhaps also helps to explain how Liverpool have slashed their number of lost days this season to injury by more than a third and retained such remarkable performance levels across 61 games.
News of the partnership can be disclosed today for the first time, as well as Liverpool’s decision to extend their use of the artificial intelligence platform by a further two seasons, as well as with the women’s and U-23 teams.
The Liverpool men’s first-team squad have been using Zone7’s technology since the start of this current 2021/’22 season. The platform analyses comprehensive player information, including in-game and training data, as well as biometric, strength, sleep, flexibility and stress levels to create risk signals and practical interventions, all aimed at improving performance while lowering injury rates.
That information is then directly delivered via an app to a club’s key decision-makers, ranging from the manager through to his various sports science, medical and coaching staff.
“Football has become very data rich and, if you can extract deep value from the data, then you can have a competitive advantage,” says Tal Brown, the chief executive and founder of Zone7.
“This is already very well established in the area of talent identification, and it is now starting to happen in measuring and trying to optimise player wellbeing and performance.”
Brown was a first-class graduate of computer systems engineering at the University of Warwick before starting his career in the Israel defence force’s intelligence corps. His team have long been designing predictive software in other industries, ranging from cyber security to financial services, and began working in football four years ago. They duly gathered millions of hours of data from more than 30 teams worldwide, including Getafe, Glasgow Rangers and Hull City.
In its quest to identify patterns that might get missed by purely human analysis, the algorithm provides information at various levels, from football as a sport through to teams and individual players. It is designed constantly to update and improve with new data.
“The software can simulate optimal scenarios on a day-by-day basis so that the players are trending towards their peak and injury risk is minimised,” explains Brown. “Sometimes risk may mean a reduction in workload – less running of a specific type, like sprinting. Sometimes a player can be under-trained and additional work may be required.”
Central to Zone7’s philosophy has been to also employ people with experience inside professional football to advise and help deliver the information in a way that is practical and accessible.
“These are Premier League veterans – it’s not just a couple of people from Silicon Valley running around with spreadsheets,” says Brown. “It was a long process to create adaptations that make the software usable in a football environment.
“Football is not stock trading and neither is it anything else out there on a professional or human experience.”
At the time of the first Covid-19 lockdown in 2020, Zone7 had evolved to the point where they believed that their systems could detect 70pc of injuries up to seven days before they occurred.
They specifically highlighted the correlation between game-load and injury, emphasising the elevated risk of six matches over a 30-day period. Liverpool have just completed their ninth match in 30 days, including the last seven back-to-back midweeks.
Brown cannot talk about the specific findings of any one club, and stresses that there “are no certainties”, but does reveal some fascinating insights.
Although there is indeed a general correlation between game-load and injury risk, this changes according to mitigations that are put in place and there are also clear dangers associated with too much rest.
“We have found across all teams that, in about a third of cases, injury risk is attributed to under-training and not over-training,” he says. Environmental factors, such as travel and sleep, and whether a team have stayed in a hotel immediately after a fixture, are areas that are producing increasingly striking results. Zone7 also now works with teams in the NBA and NFL, allowing their systems to identify trends which may be distinct or common to different sports.
“The algorithm is as good as the data – the more examples, the better it will become and, over time, it will have less black spots,” says Brown. Events like the condensed Covid programme and Liverpool’s current schedule have therefore provided rich opportunities to harvest new information.
According to Premier Injuries, a company which analyses injuries across England’s top flight, Liverpool have recorded vast improvements this season.
They have so far lost 1,008 days to injury, compared to more than 1,500 in 2020-’21.
Crucially, the days lost to what are deemed ‘substantial injuries’, which are those lasting more than nine days, have almost halved from 1,409 to 841.