In public health, unfavorable obstetric and neonatal outcomes pose a significant challenge due to their consequences for both mothers and newborns. These outcomes range from minor complications to severe conditions, such as preeclampsia, postpartum hemorrhage, and neonatal complications like low birth weight and respiratory distress. Understanding the factors leading to these unfavorable obstetric and neonatal outcomes is essential for proposing interventions and improving maternal and child health. Factors such as maternal age, marital status, and race are associated with higher risks in Brazil. In this study, the data is first divided into groups using K-means, then Apriori is applied to explore patterns in each cluster and identify factors associated with the health and well-being of newborns. The analysis was based on records from the Live Birth Information System (SINASC), aiming to identify key variables determining newborn health and well-being through the Apgar score. A total of 2,561,922 birth records were analyzed. The minimum metrics used as parameters for the Apriori algorithm were 25% support and 95% confidence, resulting in the generation of ten association rules.