Associating neuromotor outcomes at 12 months with wearable sensor measures collected during early infancy in rural Guatemala.

Background: Sensitive measures to predict neuromotor outcomes from data collected early in infancy are lacking. Measures derived from the recordings of infant movement using wearable sensors may be a useful new technique.

Methods: We collected full-day leg movement of 41 infants in rural Guatemala across 3 visits between birth and 6 months of age using wearable sensors. Average leg movement rate and fuzzy entropy, a measure to describe the complexity of signals, of the leg movements' peak acceleration time series and the time series itself were derived. We tested the three measures for the predictability of infants' developmental outcome, Bayley Scales of Infant and Toddler Development III motor, language, or cognitive composite score assessed at 12 months of age. We performed quantile regressions with clustered standard errors, accounting for the multiple visits for each infant.

Results: Fuzzy entropy was associated with the motor composite score at the 0.5 quantiles; this association was not found for the other two measures. Also, no leg movement characteristic was associated with language or cognitive composite scores.

Conclusion: We propose that the entropy of leg movement associated peak accelerations calculated from the wearable sensor data collected for a full-day can be considered as one predictor for infants' motor developmental outcome assessed with Bayley Scales of Infant and Toddler Development III at 12 months of age.