Extended Lombardy's Neonatal Screening Dataset

The Neonatal Screening dataset comprises de-identified medical records collected from routine newborn screening programs. It includes data from [insert number] neonates screened within 2012-2021, across more than 100 hospitals. The dataset captures early-life biological and demographic information, including gestational age, birth weight, sex, and time of sample collection, as well as biochemical markers obtained from dried blood spot samples typically collected within 24–72 hours after birth. The dataset also contains confirmatory diagnostic information for screen-positive cases, allowing for the evaluation of screening accuracy and follow-up outcomes. This dataset supports epidemiological analysis, algorithm development for early disease detection, and assessments of screening program performance.