Establishing the reliability and developmental validity of a neurobehavioral assessment for preterm infants: a methodological process

Abstract

The Neurobehavioral Assessment of the Preterm Infant was developed in 3 phases: a pilot study, an exploratory study, and a validation study. In the exploratory study, clusters characterized by conceptual cohesion and face validity were systematically subjected to statistical analyses to determine whether they also had high test-retest reliability and developmental validity. In the validation study, a shortened version of the test was used with an independent cohort of 290 preterm infants. A step-by-step methodological process was used to test whether the results from the exploratory study would generalize over cohorts, different versions of the test, different hospitals, and changes in examiners. This process yielded 7 highly stable, developmentally valid, and representative preterm neurobehavioral functions that generalized over the exploratory and the validation studies. These were: motor development and vigor, scarf sign, popliteal angle, alertness and orientation, percent asleep ratings, irritability, and vigor of crying.