Preterm delivery is greatly associated with perinatal mortality and morbidity, while there is no objective way to identify high-risk newborns currently. This study aimed at discovering the risk factor for Apgar score less than 7 at 1 minute of preterm neonates born with vaginal delivery. A retrospective study was performed in single pregnancy women with a vaginal delivery before 37 weeks of gestation. All the preterm infants were categorized into three types: very preterm birth (28 to 32 weeks), moderate preterm birth (32 to 34 weeks) and late preterm birth (34 to 37 weeks). Risk factors were identified through logistic regression analysis in every category of newborns mentioned above. And the receiver operating characteristic analysis was used in continuous variables to determine the best threshold of the outcome. On the basis of the selected factors, the predicting models are created and its prognosticating ability is compared by the area under the curve. A nomogram was established for the proved best model. A total of 981 cases were investigated, of whom 55 were found with 1 min Apgar scores less than 7. The nomogram was set for the predicting model with larger area under the receiver operating characteristic curve, of which is 0.742(95% confidence interval = 0.670–0.805) in very preterm birth, with the variables of first and second labor stage(> = 1.6 hours), birthweight and MgSO4(magnesium sulfate), and is 0.807(95% confidence interval = 0.776–0.837) in late preterm birth, with the variables of second labor stage(> = 1.23 hours), birthweight, a history of previous cesarean delivery, fetal distress and placental abruption. The combination of first and second labor stage, newborn weight and MgSO4 use can predict 74.2% of 1 minute Apgar score < 7 in very preterm neonates. And 80.7% high-risk infants can be identified when second labor stage, newborn weight, VBAC (vaginal birth after cesarean) and the occur of placental abruption and fetal distress were combined in the predicting model for late preterm birth. These predicting models would bring out great assistance towards obstetricians and reduce unnecessary adverse fetal outcomes.