Predictive and concurrent validity of standardized neurodevelopmental examinations by the Griffiths scales and Bayley scales of infant development II

Abstract

Standardized examinations of preterm infants are used to identify candidates for early intervention. We aimed to assess the predictive power and concurrent validity of the mental development index of the Bayley scales of infant development II (Bayley MDI) and the Griffiths scales developmental quotient (Griffiths DQ) in healthy term and preterm infants <1500 g birth weight without major perinatal complications.137 Infants (89 term, 48 preterm) were examined by both tests at a corrected age of 6, 12, and 22 months, and 114 went on to undergo Bayley assessments at 39 months.There were significant correlations between Bayley and Griffiths results at 6, 12, and 22 months (r=0.530, 0.714, and 0.833, respectively, p<0.001) but Bland Altman plots revealed major systematic bias at 6 months (Griffiths>Bayley, mean differences 14.3±9.8) and 22 months (Bayley>Griffiths, mean difference 5.2±13.9) and wide 95% limits of agreement at 6, 12 and 22 months (35.9%, 40.0%, and 52.4%, respectively). The agreement for a presumptive diagnosis of developmental impairment in the group of preterm infants between Bayley examinations obtained at 39 months corrected age (reference) and previous examinations was poor at 6, 12, and 22 months for both Bayley and Griffiths (Cohen's kappa for Griffiths: 0.225, 0.192, 0.369; for Bayley: 0.121, 0.316, 0.369, respectively).Caution should be exercised when interpreting results from standardized neurodevelopmental examinations obtained during the first 2 years of life in comparatively well preterm infants.