PANDA Gym: Automated Assessment of Neurodevelopment in Infants at Risk for Motor Disability

University of Pennsylvania

Status: Enrolling

Conditions: Neurodevelopmental Disorders; Pediatric ALL; Infant Development

Treatments: Diagnostic Test: PANDA Gym; Other: Mobile App

Study type: Observational

Funder types: Other

Identifiers

NCT04321200

833180

Details and patient eligibility

About

Early childhood detection of motor delays or impairments provides the opportunity for early treatment which improves health outcomes. This study will use state of the art sensors combined with machine learning algorithms to develop objective, accurate, easy-to-use tools for the early scoring of deficits and lays the foundation for the early prediction of physical disability.

Full description

For children with neurodevelopmental disabilities, early treatment in the first year of life improves long-term outcomes. However, the investigators 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, the investigators 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.

Enrollment: 1,700 estimated patients

Sex: All

Ages: Under 6 months old

Volunteers: Accepts Healthy Volunteers

Inclusion and exclusion criteria

Infants, male and female, between 0-6 months (Infants older than 6 months before initial enrollment will be excluded).

• Infants with early brain injury (EBI):

  • Hydrocephalus
  • Hypoxic-ischemic encephalopathy (HIE)
  • Periventricular leukomalacia (PVL)
  • Intraventricular hemorrhage (IVH)
  • Stroke

• Healthy infants (controls):

  o No history of early brain injury (EBI)

• Infants without EBI/risk for future disability:

  • Infants without known brain injuries, but with a history of preterm birth less than 32-week gestation with significant medical problems, difficulty eating, or who lack head control at 4 months of age or later will be classified as moderate risk.

Trial design

1,700 participants in 3 patient groups

Cross-sectional-150 infants (atypical vs typical)

Description:

Arm (Study)1: To assess the concurrent validity of a multimodal instrumented gym with existing clinical tools. Here, using 150 infants, we will focus on converting data from an instrumented gym into estimates of the standard clinical tests.

Treatment:

Diagnostic Test: PANDA Gym

Longitudinal cohort - 50 infants (atypical vs typical)

Description:

Arm (Study) 2: To discover the features related to long-term motor development. Here we will convert data collected longitudinally from 50 infants, using both instrumented gym and video recordings, into estimates standard clinical tests change over time and track features over developmental timescales.

Treatment:

Diagnostic Test: PANDA Gym

Cross-sectional-1500 infants (atypical vs typical)

Description:

Arm (Study) 3: To develop a computer vision-based algorithm to quantify infant motor performance from a single-camera video. Here using video data from 1200 infants, plus those gathered from Arm 1 and Arm 2, we will extract pose data from single-camera video recordings and convert these into kinematic features and relevant scores needed to classify infant movement.

Treatment:

Other: Mobile App