Alcaraz and Sabalenka Stumble in Asia: Could AI Reveal What Happens Under Pressure?

Carlos Alcaraz and Aryna Sabalenka are among the biggest names in tennis. Both have suffered surprising defeats during the Asian swing, raising an intriguing question about the future of sports technology.

Could artificial intelligence identify when elite athletes are struggling under pressure?

Sabalenka’s latest defeat makes the question particularly timely.

The world No. 2 was eliminated from the Wuhan Open on Wednesday, losing 3-6, 6-4, 7-6(5) to American Ann Li. The match featured an extraordinary finish, with Sabalenka saving nine match points before Li finally converted her tenth.

According to Reuters’ match report, Sabalenka committed 44 unforced errors during the two-hour, 27-minute contest.

It was her second consecutive early exit in Asia.

On October 4, Sabalenka lost 6-4, 6-3 to Nikola Bartunkova in Beijing, failing to convert any of her five break-point opportunities, according to the WTA’s official match analysis.

Meanwhile, Alcaraz suffered his own upset at the Shanghai Masters, falling 7-5, 7-6(4) to Belgium’s Zizou Bergs.

The ATP Tour reported that Bergs broke Alcaraz’s serve three times, ending the Spaniard’s seven-match winning streak.

Can AI detect pressure on the tennis court?

Computer vision technology can already identify facial movements, track body positioning, and measure changes in an athlete’s physical behavior.

Researchers are exploring whether these observations, combined with physiological information and match statistics, could help identify patterns associated with stress.

Imagine comparing Alcaraz’s movement and shot selection during routine points with his performance in a deciding tiebreak.

Or examining Sabalenka’s serving patterns during the closing stages of her dramatic loss to Li.

AI might identify measurable changes that traditional match statistics don’t immediately reveal.

But there’s an important limitation.

A facial expression cannot reliably establish what an athlete is feeling.

A tightened jaw, furrowed brow, or change in eye movement might reflect concentration, physical effort, frustration, or several other factors.

Without additional evidence, labeling those expressions as psychological stress would be speculation.

What the numbers tell us

Sabalenka’s 44 unforced errors against Li and her inability to convert break points against Bartunkova are measurable performance outcomes.

Alcaraz’s struggles against Bergs are similarly documented.

In his post-match comments published by the ATP Tour, Alcaraz acknowledged that his level had fallen short while crediting Bergs for his performance.

Those observations offer a stronger foundation for analysis than attempting to determine either player’s emotional state from television footage.

They also illustrate why AI systems would need to consider opponents’ performances, physical condition, match circumstances, and the players’ own accounts.

Could AI become tennis’s next competitive advantage?

For decades, coaches have relied on statistics, video analysis, and personal observation to understand performance under pressure.

AI could expand those capabilities by identifying patterns across thousands of points and comparing physical movements with changes in performance.

But there is a difference between detecting a change in behavior and explaining its psychological cause.

Neither Alcaraz’s nor Sabalenka’s defeats prove that stress determined the outcome. And no validated AI stress analysis of these matches has been presented.

Still, their unexpected losses highlight an interesting direction for sports science.

The next breakthrough may not be teaching AI to read an athlete’s mind, but helping coaches understand how performance changes when the stakes are highest.