SmarToyGym: Smart Detection of Atypical Toy-oriented Actions in At-risk Infants

The study aims to develop a SmarToyGym where sensitized, wireless toys are strategically hung and placed within reach of infants to elicit toy-oriented body and arm/hand movements. Each toy will be equipped with sensors capable of measuring the infant's grasping actions such as squeezing, pinching, tilting, etc. A low-cost 3D motion capture system will be used to collect video data and the infants' reaching and body kinematics in response to the toys. A pressure mat will be used to measure postural changes to detect weight shifts, rolling, crawling and other movements away from the initial posture. By capitalizing on these wireless and low-cost technologies, it will permit the regular and non-invasive monitoring of infants, which can lead to detailed, non-obtrusive, quantitative evaluation of motor development. In this vein, the investigators also aim to conduct proof-of-concept testing of the SmarToyGym with atypical and typical developing infants. The investigators will include infants' ages 3 to 11 months who are categorized as high-risk or low-risk using the Bayley Infant Neurodevelopmental Screener.

The proposed research is specifically designed to investigate the ability of a novel tool to identify atypically developing infants from their typically developing peers. Twenty-four infants will be recruited to participate, including 12 who are developing typically and 12 who are identified as at-risk for neuromotor delay. Infants with typical development will be at least 3 months and less than 11 months of age, score in the low-risk category on the Bayley Infant Neurodevelopmental Screener (BINS), score a greater than 85 on all sub-scales of the Bayley Scale of Infant Development (BSID-II), have no history of significant cardiac, orthopedic, or neurological condition, and gestational age at least 37 weeks. Infants at risk for neuromotor delay will be at least 3 months and less than 11 months of age (corrected for preterm birth if applicable), score in the moderate or high risk categories on the BINS, and score an 85 or less on the motor sub-scales of the Bayley Scale of Infant Development (BSID-II). In an effort to decrease variability of the data, infants in each group will be further stratified into an older group (8-10+ months) and a younger group (3-5 months).

Cerebral Palsy, Developmental Delay, Stroke, Fine Motor Delay, Infant Development, Other Development Delays

Two populations will be involved in testing in the SmarToyGym: 1. Infants exhibiting typical development between 3 months and 11 months of age 2 . Infants exhibiting atypical development (at-risk for neuromotor delay) between 3 months and 11 months of age.

We aim to develop a SmarToyGym where sensitized, wireless toys are strategically hung and placed within reach of infants to elicit toy-oriented body and arm/hand movements. Each toy will be equipped with sensors capable of measuring the infant's grasping actions such as squeezing, pinching, tilting, etc. A low-cost 3D motion capture system will be used to collect video data and the infants' reaching and body kinematics in response to the toys. A pressure mat will be used to measure postural changes to detect weight shifts, rolling, crawling and other movements away from the initial posture.

Inclusion Criteria: Infants exhibiting typical development between 3 months and 11 months of age who score in the low-risk category on the Bayley Infant Neurodevelopment Screener (BINS), score greater than 85 on all sub-scales of the Bayley Scale of Infant Development (BSID-II), have no history of significant cardiac, orthopedic or neurological condition and have a gestational age at least 37 weeks. Infants exhibiting atypical development (at-risk for neuromotor delay) between 3 months and 11 months of age, score in the moderate or high risk categories on the BINS, and score an 85 or less on the motor sub-scales of the BSID-II. Exclusion Criteria: Infants outside age range of 3-11 months

Prosser LA, Aguirre MO, Zhao S, Bogen DK, Pierce SR, Nilan KA, Zhang H, Shofer FS, Johnson MJ. Infants at risk for physical disability may be identified by measures of postural control in supine. Pediatr Res. 2022 Apr;91(5):1215-1221. doi: 10.1038/s41390-021-01617-0. Epub 2021 Jun 26.

Lysenko S, Seethapathi N, Prosser L, Kording K, Johnson MJ. Towards Automated Emotion Classification of Atypically and Typically Developing Infants. Proc IEEE RAS EMBS Int Conf Biomed Robot Biomechatron. 2020 Nov-Dec;2020:503-508. doi: 10.1109/BioRob49111.2020.9224271. Epub 2020 Oct 15.

Chambers C, Seethapathi N, Saluja R, Loeb H, Pierce SR, Bogen DK, Prosser L, Johnson MJ, Kording KP. Computer Vision to Automatically Assess Infant Neuromotor Risk. IEEE Trans Neural Syst Rehabil Eng. 2020 Nov;28(11):2431-2442. doi: 10.1109/TNSRE.2020.3029121. Epub 2020 Nov 6.

Goyal V, Torres W, Rai R, Shofer F, Bogen D, Bryant P, Prosser L, Johnson MJ. Quantifying infant physical interactions using sensorized toys in a natural play environment. IEEE Int Conf Rehabil Robot. 2017 Jul;2017:882-887. doi: 10.1109/ICORR.2017.8009360.