Objective To investigate the risk factors of germinal matrix-intraventricular hemorrhage (GM-IVH) in preterm infants by multifactorial analysis, and to construct the corresponding prediction model. Methods Forty preterm infants with GM-IVH who received treatment at the First People’s Hospital of Zhengzhou were selected as the observation group, and the inclusion period was from January 2021 to December 2024, and 40 cases of healthy preterm infants in the same period were selected as the control group, comparing the two groups of preterm infants in the prenatal and neonatal periods and other clinical indicators, and adopting multifactorial logistic regression model to screen the relevant influencing factors, constructing the prediction model of the nomogram, and evaluating the model differentiation degree through the Receiver Operating Characteristic (ROC). The ROC curves were used to assess the differentiation of the model, and the calibration curves were used to assess its calibration degree to comprehensively evaluate the efficacy of the prediction model. Results There was no statistical significance in the comparison of prenatal indicators such as gender, prenatal hormone therapy, intrauterine distress and intrauterine infection between the two groups (P >0.05). The incidence of gestational age <32 weeks, birth weight <2100g, asphyxia at delivery, chorioamnionitis, dopamine treatment, and metabolic acidosis was higher in the observation group than that in the control group (P <0.05). The results of multifactorial logistic regression analysis showed that gestational age <32 weeks, birth weight <2100g, asphyxia at delivery, chorioamnionitis, and incidence of metabolic acidosis were risk factors for GM-IVH in preterm infants (P < 0.05). A prediction model was further developed based on the results of multifactorial logistic regression analysis, Logit (P)=–4.275+2.740× gestational age <32 weeks+1.681×birth weight <2100g+2.071× asphyxia at delivery+2.468× chorioamnionitis+1.780× metabolic acidosis. According to the Hosmer-Lemeshow test, the goodness of fit was 5.963, P=0.576, indicating that the constructed model had a good fit. The ROC curves showed that the AUCs for gestational age <32 weeks, birth weight <2100g, birth asphyxia, chorioamnionitis, incidence of metabolic acidosis, and the joint prediction of GM-IVH in preterm infants were 0.725, 0.650, 0.638, 0.600, 0.587, 0.865. Conclusions Small for gestational age ( <32 weeks), low birth weight (<2100g), asphyxia, chorioamnionitis, and metabolic acidosis in preterm infants are the high-risk factors for the occurrence of GM-IVH, and the prediction model constructed by using the above factors showed good efficacy.