Michelle J. Johnson, Ph.D. - US grants

? 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.

PROJECT SUMMARY/ABSTRACT The overall goal of this R01 project is to develop an automated assessment system that can capitalize on state of the art sensing technologies and machine learning algorithms to enable accurate and early detection of infants at risk for neurodevelopmental disabilities. In the USA, 1 in 10 infants are born at risk for these disabilities. For children with neurodevelopmental disabilities, early treatment in the first year of life improves long-term outcomes. However, we are currently held back by inadequacies of available clinical tests to measure and predict impairment. Existing tests are hard to administer, require specialized training, and have limited long- term predictive value. There is a critical need to develop an objective, accurate, easy-to-use tool for the early prediction of long-term physical disability. The field of pediatrics and infant development would greatly benefit from a quantitative score that would correlate with existing clinical measures used today to detect movement impairments in very young infants. To realize a new generation of tests that will be easy to administer, we will obtain large datasets of infants playing in an instrumented gym or simply being recorded while moving in a supine posture. Video and sensor data analyses will convert movement into feature vectors based on our knowledge of the problem domain. Our approach will use machine learning to relate these feature vectors to currently recommended clinical tests or other ground truth information. The power of this design is that algorithms can utilize many aspects of movement to produce the relevant scores. Our preliminary data allows us to lay the following aims: 1)Aim 1: To assess concurrent validity of a multimodal instrumented gym with existing clinical tools. Here, using 150 infants (75 with early brain injury and 75 controls), we will focus on converting data from an instrumented gym into estimates of the standard clinical tests; 2)Aim 2: To develop a computer vision-based algorithm to quantify infant motor performance from single camera video. Here using video data from 1200 infants (400 with early brain injury, 400 preterm without early brain injury, 400 controls), plus those gathered from Aim 1 and Aim 3, we will extract pose data from single-camera video recordings and convert these into kinematic features and relevant scores needed to classify infant movement; 3)Aim3: To discover the features related to long-term motor development. Here we will convert data collected longitudinally from 50 infants (25 with early brain injury and 25 controls) using both instrumented gym and video recordings into estimates standard clinical tests change over time and track features over developmental timescales. These three aims spearhead the use of real world behavior for movement scoring. Our aims will bring us closer to a universal non-invasive test for early detection of neurodevelopmental disabilities and lay the groundwork for long-term prediction of disability. But above all, it promises to scale to infants worldwide, producing an affordable tool to aid in infant health assessment.

PROJECT SUMMARY About 37 million people are living with HIV (PLWH) worldwide. As they age and their HIV status becomes more chronic, they face new challenges associated with the chronic management of HIV and experience a range of physical, cognitive, and mental health-related issues that detrimentally impact their ability to perform instrumental activities of daily living (IADLs) such as managing finances and medication management. Studies indicate that 80% of PLWH report experiencing at least one impairment, activity limitation, or social participation restriction while others suggest 50%-70% have a ?global? impairment in everyday functioning. While these impairments can be partially attributed to traditional risks factors associated with aging, HIV itself preferentially impacts the frontostriatal regions of the brain, leading to deficits in motor function, attention, information processing, executive function, and memory. Most often these issues are overlooked in HIV and very little attempt is made to rehabilitate them. Our long-term goal is to expand robot-based neurorehabilitation strategies to PLWH. The objective of this proposal is to first objectively quantify the impact of aging with HIV on real-world IADLs. Since IADLs often require both high levels of executive functioning during the performance of motor activities, we also seek to apply a novel robot-based method to study how ?IADL-like conditions? characterized by systematically increasing cognitive demand in the executive function affect motor performance in adults aging with HIV as oppose to their counterparts aging without HIV. In Aim 1, we will assess concurrent validity of a novel robot- based motor and cognitive task with existing clinical tools used to predict motor impairment, cognitive impairment and IADL function in older adults living with HIV. 42 participants aging with HIV and controls with varying levels of IADL function will be evaluated using our robot-based task that simultaneously engages motor and cognitive domains and standard clinical test battery. We hypothesize that our new robot-based task will be an objective method that demonstrates concurrent validity with the clinical scales, especially those related to gross and fine upper limb motor impairment, executive function and IADL function. In Aim 2, we will assess interactions between increasing cognitive demand and motor performance in older adults living with HIV and controls without HIV. 59 participants aging with HIV and controls will be evaluated using our novel robot- based task while we will vary cognitive difficulty. We will measure changes in motor performance as a function of increasing levels of task difficulty and HIV status. We hypothesize that the HIV group will demonstrate worse motor performance as the task difficulty increases compared to controls. We will determine if this new task can objectively probe how performance on complex IADLs may suffer with HIV status. This project supports the use of robot-based assessment strategies for fast and objective assessment of cognitive-motor performance and IADL function and provides insight into differences between HIV and age-matched non-HIV controls.