Each of us appears to have a unique way of moving, a physical “signature” that is ours alone, like our face or fingerprints, according to a remarkable new study of people and their muscles. The study, which used machine learning to find one-of-a-kind patterns in people’s muscular contractions, could have implications for our understanding of health, physical performance, personalized medicine and whether and why people can respond so differently to the same exercise.
Intuitively, most of us probably know there is something in the way we move, and that that something defines us. In studies and daily life, most people can pick out their friends and loved ones, based solely on how they walk. At least one surveillance company also claims to be able to identify and track people using their gaits.
But those identifications, whether fond or creepy, rely on external cues about how we look in motion and depend on anatomical features, such as height, limb length or how we swing our arms, which may not be stable. Wear heels, develop sore feet, limp, and you could move differently.
Some scientists have speculated that other subtler, interior movement patterns, such as the ways in which our muscles fire in choreography with one another when we will our body to move, might be particular to each of us and relatively constant. But little research had delved into what our muscles are up to when we move.
So, for the new study, which was published this month in the Journal of Applied Physiology, French and Australian researchers decided to turn to algorithms to ferret out whether unique, personal muscle patterns exist.
The scientists began by recruiting 80 healthy men and women of varying physical sizes and fitness and inviting them to a human performance lab.
There, the volunteers sat on stationary bicycles while researchers adjusted the pedals, handlebars and seats so that everyone’s riding style would be the same. The researchers also attached electrodes to eight of the muscles in the volunteers’ legs. The electrodes were designed to read and record electrical activity in those muscles while they contracted. Then the volunteers cycled for 90 seconds multiple times at a range of pedaling speeds.
Next, they moved over to treadmills and, still wearing the electrodes, walked barefoot during multiple 90-second strolls.
Several days later, most of the volunteers returned to the lab and repeated the cycling, walking and electrodes routines.
The researchers then fed all of the muscular-activation readouts into a machine-learning software program, which is a type of artificial intelligence. For the first few examples, the program was told which readouts belonged to which person and directed the program to, in effect, learn that person’s muscular-activation style, if it existed.
Finally, the program’s algorithm was directed to differentiate the movement patterns, without names attached, and assign them to the correct volunteer.
It turned out to be quite adept, accurately recognizing anonymous movement patterns more than 99 percent of the time when using readouts from all eight muscles. Even when it considered activity from only two muscles, it knew the muscles’ owners more than 80 percent of the time.
Perhaps most important, the algorithm remained correct about 90 percent of the time when analyzing the readouts from people’s second lab visits.
Taken as a whole, these data suggest that people have distinct, detectable and durable ways of using their muscles, says François Hug, a professor of movement science at the University of Nantes who led the new study. The individual patterns remained recognizable even from one day to the next.
The findings are important, Dr. Hug says, because “understanding how movement is controlled remains one of the main challenges for many scientific fields.” Our simplest-seeming moves are bogglingly complex. “A 5-year-old child can manipulate objects with superior dexterity to any robot,” he says.
So, quantifying the unique ways in which people walk, pedal or hold a glass could enable scientists to improve and refine robotics, prosthetics, physical therapy and personalized exercise programs.
At a more intimate level, understanding movement signatures conceivably could improve sports training, Dr. Hug says, if it turns out that world-class athletes activate their muscles in ways that can be emulated by those of us who are less swift and graceful.
Movement signatures also might serve as coal-mine canaries for disease or injury risk, he says. He and his colleagues already are studying the relationships between certain muscle-activation patterns and Achilles’ tendon problems.
But this research is in its infancy. Dr. Hug cautions. Scientists do not yet know how permanent movement signatures are; if and how they alter with age, weight change or lifestyle; or if it ever will be feasible and affordable for most of us to learn our particular movement signature.
But Dr. Hug hopes this study will remind scientists, doctors and us of every person’s immutable exceptionalism.
“Differences in the way people move and respond to an intervention are often ignored,” he says, but they matter “for addressing fundamental questions about health, aging and disease.”