The objective of this study was to assess the prevalence and trends for neonatal hyperbilirubinemia, and the development of bilirubin neurotoxicity in the USA. We used a de-identified national dataset for the years 2002-2017. The study included all newborn inpatients with postnatal age ≤28 days. Cochran-Armitage trend test was used for trend analyses. Regression analyses were performed and adjusted odds ratios (aOR) were reported. The study included 57,989,476 infants; of them 53,259,758 (91.8%) were term infants and 4,725,178 (8.2%) were preterm infants. Bilirubin neurotoxicity decreased over the years in term infants (Z = 0.36, p = 0.03) without change in preterm infants (Z = 42.5, p = 0.12). Black neonates were less likely to be diagnosed with hyperbilirubinemia than White neonates (aOR = 0.77, 95% confidence interval (CI): 0.77-0.78, p < 0.001) and more likely to develop bilirubin neurotoxicity than White neonates (aOR = 3.0.5, 95% CI: 2.13-4.36, p < 0.001). Bilirubin neurotoxicity rate in the overall population was 2.4 per 100,000 live births. Bilirubin neurotoxicity has significantly decreased in term infants and did not change in preterm infants. Despite the less diagnosis of hyperbilirubinemia in Black newborns, they are disproportionately at increased risk of developing bilirubin neurotoxicity when compared to White newborns. In this article, we analyzed the National Inpatient Database. This is the largest study of its kind using data on 57,989,476 neonates. The article has multiple novel findings: (1) it demonstrated that utilization of phototherapy has increased significantly over the years, (2) the rate of kernicterus for neonates decreased in term infants and did not change in preterm babies, (3) kernicterus was mostly encountered in infants without isoimmunization jaundice, and (4) there is a clear racial disparity in neonatal jaundice; although Black newborns have less neonatal jaundice, they are at increased risk of developing kernicterus.