The researchers constructed and validated a nomogram prediction model for recurrent spontaneous abortion (RSA) based on MALAT1, miR-515-5p and MCL1 mRNA expression in 135 patients in the training set and 58 in the validation set. Independent risk factors for RSA were advanced maternal age, more than 3 abortions, low progesterone level at the beginning of pregnancy, high MALAT1 expression, low miR-515-5p expression, and low MCL1 mRNA expression (p < 0.05). The nomogram model had a C-index of 0.915 in the training set and 0.869 in the validation set. The calibration curve showed good agreement between predicted and actual values with mean absolute errors of 0.012 and 0.034; The Hosmer-Lemeshow test had p values of 0.362 and 0.779. The ROC curve achieved an AUC of 0.916 (95% CI 0.858–0.974) in the training set and 0.867 (95% CI 0.742–0.992) in the validation set. Decision curve analysis confirmed the clinical value of the model. MCL1 mRNA is useful for early-stage RSA prediction and clinical decisions.