Objective To construct a prediction model for the efficacy of conjoint fascial sheath (CFS) suspension based on the recovery trajectory of marginal reflex distance 1 (MRD1). Methods A total of 80 patients with simple congenital ptosis who underwent CFS suspension in our hospital from June 2022 to June 2025 were retrospectively enrolled and followed up for 6 months. MRD1 values before operation, at 1 week, 1 month, 3 months and 6 months after operation were recorded. Linear mixed model and Logistic regression were used for data analysis, and ROC curve, Bootstrap method and decision curve were applied to evaluate the model. Results There were 64 patients with favorable efficacy and 16 patients with poor efficacy. The decline in MRD1 from 1 to 3 months postoperatively was more significant in the poor efficacy group (interaction effect P <0.001). Preoperative MRD1, levator palpebrae muscle function, postoperative 1-month MRD1 ≥3.0 mm and MRD1 decrease＞0.5 mm from 1 to 3 months were independent influencing factors. The AUC of the model was 0.891 (95%CI : 0.812~0.970), the Bootstrap-corrected AUC was 0.874, and the Brier score was 0.109. Conclusion A significant decline in MRD1 from 1 to 3 months postoperatively may indicate poor long-term efficacy. The trajectory-enhanced model exhibits good predictive performance, making it suitable for stratified follow-up.