Background: Early identification of cerebral palsy (CP) during infancy will provide opportunities for early therapies and treatments. The aim of the present study was to present a novel machine-learning model, the Computer-based Infant Movement Assessment (CIMA) model, for clinically feasible early CP prediction based on infant video recordings. Methods: The CIMA model was designed to assess the proportion (%) of CP risk-related movements using a time–frequency decomposition of the movement trajectories of the infant’s body parts. The CIMA model was developed and tested on video recordings from a cohort of 377 high-risk infants at 9–15 weeks corrected age to predict CP status and motor function (ambulatory vs. non-ambulatory) at mean 3.7 years age. The performance of the model was compared with results of the general movement assessment (GMA) and neonatal imaging. Results: The CIMA model had sensitivity (92.7%) and specificity (81.6%), which was comparable to observational GMA or neonatal cerebral imaging for the prediction of CP. Infants later found to have non-ambulatory CP had significantly more CP risk-related movements (median: 92.8%, p = 0.02) compared with those with ambulatory CP (median: 72.7%). Conclusion: The CIMA model may be a clinically feasible alternative to observational GMA.

BACKGROUND AND PURPOSE: Very preterm infants (birth weight, <1500 g) are at increased risk of cognitive and motor impairment, including cerebral palsy. These adverse neurodevelopmental outcomes are associated with white matter abnormalities on MR imaging at term-equivalent age. Cerebral palsy has been predicted by analysis of spontaneous movements in the infant termed “General Movement Assessment.” The goal of this study was to determine the utility of General Movement Assessment in predicting adverse cognitive, language, and motor outcomes in very preterm infants and to identify brain imaging markers associated with both adverse outcomes and aberrant general movements. MATERIALS AND METHODS: In this prospective study of 47 preterm infants of 24–30 weeks9 gestation, brain MR imaging was performed at term-equivalent age. Infants underwent T1- and T2-weighted imaging for volumetric analysis and DTI. General movements were assessed at 10–15 weeks9 postterm age, and neurodevelopmental outcomes were evaluated at 2 years by using the Bayley Scales of Infant and Toddler Development III. RESULTS: Nine infants had aberrant general movements and were more likely to have adverse neurodevelopmental outcomes, compared with infants with normal movements. In infants with aberrant movements, Tract-Based Spatial Statistics analysis identified significantly lower fractional anisotropy in widespread white matter tracts, including the corpus callosum, inferior longitudinal and fronto-occipital fasciculi, internal capsule, and optic radiation. The subset of infants having both aberrant movements and abnormal neurodevelopmental outcomes in cognitive, language, and motor skills had significantly lower fractional anisotropy in specific brain regions. CONCLUSIONS: Aberrant general movements at 10–15 weeks9 postterm are associated with adverse neurodevelopmental outcomes and specific white matter microstructure abnormalities for cognitive, language, and motor delays.

Preterm infants born before 32 weeks gestation have increased risks for neurodevelopmental impairment at two years of age. How brain function differs between preterm infants with normal or impaired development is unknown. However, abnormal spontaneous motor behavior at 12–15 weeks post-term age is associated with neurodevelopmental impairment. We imaged brain blood oxygen level-dependent signals at term-equivalent age in 62 infants born at <32 weeks gestation and explored whether resting state functional connectivity (rsFC) differed with performances on the General Movement Assessment (GMA) at 12–15 weeks, and Bayley III scores at two years of corrected age. Infants with aberrant general movements exhibited decreased rsFC between the basal ganglia and regions in parietal and frontotemporal lobes. Infants with normal Bayley III cognitive scores exhibited increased rsFC between the basal ganglia and association cortices in parietal and occipital lobes compared with cognitively impaired children. Infants with normal motor scores exhibited increased rsFC between the basal ganglia and visual cortices, compared with children with motor impairment. Thus, the presence of abnormal general movements is associated with region-specific differences in rsFC at term. The association of abnormal long-term neurodevelopmental outcomes with decreased rsFC between basal ganglia and sub-score specific cortical regions may provide biomarkers of neurodevelopmental trajectory and outcome.

Background: Early prediction of cerebral palsy (CP) using the General Movement Assessment (GMA) during the fidgety movements (FM) period has been recommended as standard of care in high-risk infants. The aim of this study was to determine the accuracy of GMA, alone or in combination with neonatal imaging, in predicting cerebral palsy (CP). Methods: Infants with increased risk of perinatal brain injury were prospectively enrolled from 2009–2014 in this multi-center, observational study. FM were classified by two certified GMA observers blinded to the clinical history. Abnormal GMA was defined as absent or sporadic FM. CP-status was determined by clinicians unaware of GMA results. Results: Of 450 infants enrolled, 405 had scorable video and follow-up data until at least 18–24 months. CP was confirmed in 42 (10.4%) children at mean age 3 years 1 month. Sensitivity, specificity, positive and negative predictive values, and accuracy of absent/sporadic FM for CP were 76.2, 82.4, 33.3, 96.8, and 81.7%, respectively. Only three (8.1%) of 37 infants with sporadic FM developed CP. The highest accuracy (95.3%) was achieved by a combination of absent FM and abnormal neonatal imaging. Conclusion: In infants with a broad range of neonatal risk factors, accuracy of early CP prediction was lower for GMA than previously reported but increased when combined with neonatal imaging. Sporadic FM did not predict CP in this study.