Summary: Researchers have developed a smart onesie that accurately measures the spontaneous and voluntary movements of infants from five months. The smart-clothing could help assess abnormal neurological and motor development in infants.
Source: University of Helsinki
A new innovation makes it possible, for the first time, to quantitatively assess children’s spontaneous movement in the natural environment.
Researchers have developed a smart jumpsuit, or a garment that accurately measures the spontaneous and voluntary movement of infants from the age of five months. Details on their motility help in assessing abnormal neurological development, among other things.
The study on the smart jumpsuit and the related analysis method applied to 7-month-old infants was published in the Scientific Reports journal. In the future, the jumpsuit can also be used to study older children.
The assessment of spontaneous and voluntary movements is part of the neurological examination of infants. Previously, the quantitative tracking of children’s spontaneous motility in the natural environment has not been possible. Instead, children have been primarily qualitatively assessed at the physician’s or physiotherapist’s practice, which requires taking into account the fact that the infant’s behaviour in the practice setting does not necessarily entirely match that seen at home.
“The smart jumpsuit provides us with the first opportunity to quantify infants’ spontaneous and voluntary movements outside the laboratory. The child can be sent back home with the suit for the rest of the day. The next day, it will be returned to the hospital where the results will then be processed,” explains Sampsa Vanhatalo, professor of clinical neurophysiology at the University of Helsinki.
Vanhatalo says that the new analysis method quantifies infant motility as reliably as a human being would be able to do by viewing a video recording. After the measurement, the infant’s actual movements and physical positions will be known to the second, after which computational measures can be applied to the data.
“This is a revolutionary step forward. The measurements provide a tool to detect the precise variation in motility from the age of five months, something which medical smart clothes have not been able to do until now.” Neurological abnormalities should be detected early on
The data gleaned by the smart jumpsuit is valuable, since the detection of abnormalities in the neurological development of infants at an early stage enables early support. Brain plasticity is at its strongest in early childhood, and is benefited by measures supporting development, which are targeted at recurring everyday activities.
At least 5% of Finnish children suffer from problems associated with language development, attention regulation and motor development. Often, such problems overlap. The pathogenic mechanisms underlying developmental disorders are complex, but preterm birth, perinatal brain damage and the lack of early care, as well as insufficient stimulation in the growth environment aggravate the risk of developmental problems.
According to Leena Haataja, professor of paediatric neurology, developmental disorders in today’s pressure-dominated world pose a considerable risk that can lead to learning difficulties and obstacles in the competition for education and jobs. Furthermore, they are a risk factor associated with exclusion from contemporary society.
“The early identification of developmental disorders and support for infants’ everyday functional capacity in interaction with the family and the growth environment constitute a significant factor on the level of individuals, families and society,” Haataja notes.
In the future, the smart jumpsuit can be used for the objective measurement of how various therapies and treatments affect children’s development.
“This is the million-dollar question in Western healthcare. In addition, we may be able to quantify how early motor development associates with later cognitive development,” Vanhatalo says.
The smart jumpsuit was developed under the Rhythms in Infant Brain (RIB) project, part of the Health from Science (TERVA) programme funded by the Academy of Finland, the Foundation for Pediatric Research and the Finnish Brain Foundation. The multidisciplinary research group, which operates in the New Children’s Hospital, is headed by neurophysiologist Sampsa Vanhatalo and paediatric neurologist Leena Haataja. In addition to physicians, the group comprises psychologists, physiotherapists, nurses and engineers.
The textile and usability design of the smart jumpsuit was coordinated by researcher Elina Ilén, while researchers Manu Airaksinen and Okko Räsänen from Aalto University were in charge of AI analyses. The project utilised the Movesense sensor, an open-source device developed in Finland by Suunto, and a mobile application developed by the German company Kaasa.
About this neuroscience research article
Source: University of Helsinki Media Contacts: Sampsa Vanhatalo – University of Helsinki Image Source: The image is credited to Sampsa Vanhatalo.
Automatic Posture and Movement Tracking of Infants with Wearable Movement Sensors
Infants’ spontaneous and voluntary movements mirror developmental integrity of brain networks since they require coordinated activation of multiple sites in the central nervous system. Accordingly, early detection of infants with atypical motor development holds promise for recognizing those infants who are at risk for a wide range of neurodevelopmental disorders (e.g., cerebral palsy, autism spectrum disorders). Previously, novel wearable technology has shown promise for offering efficient, scalable and automated methods for movement assessment in adults. Here, we describe the development of an infant wearable, a multi-sensor smart jumpsuit that allows mobile accelerometer and gyroscope data collection during movements. Using this suit, we first recorded play sessions of 22 typically developing infants of approximately 7 months of age. These data were manually annotated for infant posture and movement based on video recordings of the sessions, and using a novel annotation scheme specifically designed to assess the overall movement pattern of infants in the given age group. A machine learning algorithm, based on deep convolutional neural networks (CNNs) was then trained for automatic detection of posture and movement classes using the data and annotations. Our experiments show that the setup can be used for quantitative tracking of infant movement activities with a human equivalent accuracy, i.e., it meets the human inter-rater agreement levels in infant posture and movement classification. We also quantify the ambiguity of human observers in analyzing infant movements, and propose a method for utilizing this uncertainty for performance improvements in training of the automated classifier. Comparison of different sensor configurations also shows that four-limb recording leads to the best performance in posture and movement classification.