Abstract: Background　Early menopause is a condition that significantly impacts female reproductive health, not only diminishing fertility but also increasing the risk of developing various chronic diseases such as osteoporosis and cardiovascular disorders. Existing research indicates that genetic factors play a significant role in variations in menopausal age. Polygenic risk score models, constructed based on genome-wide association studies, can be used to assess individual genetic susceptibility. However, their applicability among Chinese women remains to be validated. Objective　To evaluate the discriminatory ability and risk stratification value of previously developed models for predicting early menopause based on polygenic risk scores (PRS) in Chinese women. Methods　Women with early menopause recruited from September 2023 to June 2024 were assigned to the early menopause group, while 45 volunteer participants recruited from April 2025 to August 2025, who had reached the age of 45 or older and had not yet undergone menopause, were assigned to the normal menopause control group. Genomic single-nucleotide polymorphisms were detected using the Illumina ASA gene chip, and PRS scores were calculated. Based on the participants' PRS percentile results, the predictive performance of existing PRS-based early menopause prediction models in Chinese women was externally validated. Logistic regression analysis was used to examine the association between PRS risk stratification and the occurrence of early menopause, and the odds ratio and its 95% confidence interval were calculated. The discriminatory ability of PRS percentiles for early menopause was evaluated by plotting receiver operating characteristic (ROC) curves and calculating the area under the curve (AUC). Based on PRS risk stratification criteria established by existing models and previous studies, differences in the distribution of early menopause cases across different genetic risk strata were compared. Results　A total of 145 Chinese women were enrolled, comprising 100 with premature menopause and 45 with normal-age menopause. Complete height and weight data were available for 95 cases in the premature menopause group and 41 cases in the control group. The mean age in the early menopause group was significantly lower than that in the control group (36.2 ± 6.8 years vs 52.3 ± 5.2 years, P＜0.001), and body mass index (BMI) was slightly lower (22.2 ± 2.8 kg/m2 vs 23.5 ± 3.6 kg/m2, P = 0.032). with similar rates of smoking and alcohol consumption, whilst staying up late was more common in the early menopause group (74.5% vs 19.5%, P＜0.001). The PRS percentile in the early menopause group was significantly lower than that in the normal menopause control group 17.2% (4.1%, 37.1%) vs 40.0% (19.5%, 58.8%), P＜0.001, and the proportion of individuals with high genetic risk (PRS percentile ≤ 10%) was significantly higher (40.0% vs 15.6%, P = 0.004). Logistic regression analysis revealed a significantly increased risk of early menopause in the high genetic risk group (OR=3.619, 95% CI: 1.545 - 9.565); this association remained statistically significant after adjusting BMI and lifestyle factors (adjusted OR=7.974, 95% CI: 2.617 - 28.754). Furthermore, frequent late-night sleeping was significantly associated with an increased risk of early menopause, while BMI was negatively correlated with the risk of early menopause. ROC analysis indicated that the predictive performance of this PRS model among Chinese women was moderate, with an AUC of 0.705 (95% CI: 0.613- 0.795), which was close to the AUC reported for the original model (0.723).Conclusion　The PRS-based model for predicting early menopause, developed using GWAS data from European populations, demonstrates a certain degree of cross-population discriminatory power and value for risk stratification in Chinese women. It can be used to identify individuals at high genetic risk of early menopause; however, its predictive performance remains limited, and further optimization of the model is required in the future by incorporating clinical and environmental factors.