SmarToyGym: Smart detection of atypical toy-oriented actions in at-risk infants

 描述(由申请人提供)：医学上脆弱的婴儿存活率的提高导致更多的儿童在以后的生活中有功能障碍。迫切需要临床工具，能够在自然环境中对这些高危婴儿进行非侵入性监测，并及早发现运动延迟和损伤。及早发现延迟或损害为早期治疗提供了机会，从而改善了他们一生中的健康结果。运动发育可以通过研究婴儿的游戏行为和与玩具的互动来评估。因此，我们的长期目标是开发一个先进的游戏环境，SmartoGym，通过它，我们可以客观地评估高危婴儿的运动发育，并量化未来干预的效果。我们的工作假设是，当婴儿在这种环境中玩耍时，通过测量身体和手臂/手的运动得出的指标将识别出具有非典型运动行为的婴儿。我们的第一个特别节目 目的是开发一种SmartoGym，在这种健身房中，感应式无线玩具被战略性地悬挂并放置在婴儿可以接触到的地方，以引发玩具导向的身体和手臂/手的动作。每个玩具都将配备传感器，能够测量婴儿的抓握动作，如挤压、挤压和摇晃/倾斜。一个低成本的3D动作捕捉系统将被用来收集视频数据，以及婴儿对玩具的伸手和身体运动学。压力垫将被用来测量姿势的变化，以检测体重转移、滚动、爬行和其他偏离初始姿势的动作。我们的第二个具体目标是对发育不典型和典型的婴儿进行SmartoGym的概念验证测试。我们将包括24名3至11个月大的婴儿，他们使用贝利婴儿神经发育筛查(BINS)判别工具被归类为高风险或低风险。非典型婴儿的纳入标准将是运动障碍和/或认知障碍，由贝利婴儿发育量表(BSID-III)评估工具的分项分数定义。12名非典型婴儿和12名典型婴儿将被观察到连续5天在有玩具和没有玩具的SmartoGym内玩耍。通过这项研究，我们将1)确定一系列能够区分非典型婴儿和典型婴儿的指标，2)确定测量的可靠性/重复性，3)确定最敏感的指标的最佳集群，以形成易于使用的家庭筛查方法。R21的结果将为设计一项更大规模的试验提供依据，以改进该工具并探索扩大该工具用于治疗应用的潜力。这个 我们的工作的潜在影响是世界范围的，可以通过更早的干预和更好的长期功能结果改变成千上万儿童的生活。

 DESCRIPTION (provided by applicant): Increased survival rates of medically fragile infants lead to an increased number of children with functional impairments later in life. There is a critical need for clinical tools that can provide non- invasive monitoring of these at-risk infantsin their natural settings and early detection of motor delays and impairments. Early detection of delay or impairment provides the opportunity for early treatment which improves health outcomes for them over the lifespan. Motor development can be evaluated by studying infant play behavior and interactions with toys. As such, our long-term goal is to develop an advanced play environment, SmarToyGym, through which we can objectively assess the motor development of at-risk infants and quantify the effects of future interventions. Our working hypothesis is that metrics derived from measuring body and arm/hand movements while infants play within this environment will identify infants with atypical motor behavior. Our first specific aim is to develop a SmarToyGym where sensorized, 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, and shaking/tilting. 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. Our second specific aim is to conduct proof-of-concept testing of the SmarToyGym with atypical and typical developing infants. We will include 24 infants ages 3 to 11 months who are categorized as high-risk or low-risk using the Bayley Infant Neurodevelopmental Screener (BINS) discriminative tool. Inclusion criteria for atypical infants will be motor impairment and/or cognitive impairment as defined by sub-scores on Bayley Scale of Infant Development (BSID-III) evaluation tool. Twelve atypical and 12 typical infants will be observed playing within SmarToyGym with and without toys for 5 consecutive days. Using this study, we will 1) identify a battery of metrics that are able to discriminate between atypical and typical infants, 2) determine the reliability/reproducibility of the measurements, and 3) determine the best clustering of the most sensitive metrics into an easy to use home screening methodology. Results from this R21 will inform the design of a larger trial to refine the tool and explore the potential for expanding the tool for treatment applications. The potential impact of our work is world-wide and can alter the lives of thousands of children through earlier intervention and better long-term functional outcomes.