In sci-fi shows like Star Trek, people wear jumpsuits because, well, it’s the future. In real life, babies could soon wear special high-tech jumpsuits designed to help doctors monitor their movements and look for any possible mobility issues that are developing.
The smart jumpsuit in question has been developed by medical and A.I. researchers in Finland’s Helsinki Children’s Hospital. In a recent demonstration, they fitted 22 babies, some as young as four months, with jumpsuits equipped with motion sensors. These enabled the suits to register the acceleration and positional data of wearers and relay it to a nearby smartphone. A neural network was then trained to recognize posture and movement by comparing data from the suits with video shot by the researchers.
“We [showed] that it is possible to monitor infant’s motor activity very accurately in an out-of-hospital setting,” Sampsa Vanhatalo, a professor in the Department of Neurosciences, told Digital Trends. “This allows detailed assessment in a native environment, [such as] an infant’s home, which has been unreachable in the past. The current practice is to assess infants in the hospital rooms, during brief visits to doctor or physiotherapists. This assessment is mostly qualitative. It is known, however, that infant’s spontaneous performance in their native environment may be very different, and the current clinical assessment protocols fall short in their capture.”
The hope is that being able to identify possible movement-related (or movement-indicated) issues at an early stage could allow necessary therapy or other interventions to be introduced more rapidly. While some people will likely balk at the idea of putting data-gathering wearables on very young kids, this could therefore turn out to be a very useful invention from a healthcare perspective.
“The current study shows that our system is as reliable as a human observer in assessing motility in up to seven-month-old infants,” Vanhatalo continued. “[That means] infants that have not yet learned sitting or standing. Our goal during the first half of 2020 is to train the algorithms for walking as well, and to enable longer at-home recordings. We are looking into commercialization as a medical product that could be used as part of neurological assessment in the clinical or academic use. The first clinical trials to validate our methods could start as early as [this year].”
A paper describing the work, titled “Automatic Posture and Movement Tracking of Infants with Wearable Movement Sensors,” is available to read online at electronic preprint repository arXiv.
- Nvidia’s latest A.I. results prove that ARM is ready for the data center
- Google’s LaMDA is a smart language A.I. for better understanding conversation
- Emotion-sensing A.I. is here, and it could be in your next job interview
- Why teaching robots to play hide-and-seek could be the key to next-gen A.I.
- The BigSleep A.I. is like Google Image Search for pictures that don’t exist yet