Prenatal exploratory model for gestational trophoblastic neoplasia after hydatidiform mole with a coexistent normal fetus: a retrospective cohort study

Hydatidiform mole with a coexistent normal fetus (HMCF) has a relatively high risk of developing gestational trophoblastic neoplasia (GTN), but no prenatal model is currently available to estimate GTN risk after HMCF. For these reasons, we developed a prenatal exploratory model for GTN progression after HMCF. This retrospective cohort study included women with HMCF confirmed by histopathological examination. Univariate and multivariable Firth logistic regression analyses were used to identify prenatal variables that were retained in the exploratory multivariable model, which were then incorporated into a Firth logistic regression–based nomogram. Model performance was assessed by stratified 5‑fold cross‑validation, AUC, calibration, and decision curve analysis (DCA). A risk classification system was derived from total nomogram scores. Among 337,790 pregnancies and 1,785 molar pregnancies during the study period, 40 women met the inclusion criteria for HMCF; 16 (40.0%) developed GTN. Compared with women who did not develop GTN, those who developed GTN had higher peak serum hCG levels and larger maximum molar tissue volumes on ultrasound (both P < 0.05). Multivariate analyses revealed that both high peak serum hCG levels (≥ 107,602 IU/L; OR, 12.55; 95% CI, 1.04–1830.66; P = 0.046) and large molar tissue volume (≥ 276.3 cm³; OR, 10.27; 95% CI, 2.34–57.35; P = 0.002) were retained as prenatal variables associated with GTN progression. The Firth logistic regression model demonstrated good discrimination (AUC = 0.773) and satisfactory calibration. The final nomogram based on this model stratified patients into low- and high-risk groups using a cutoff score of 200 points: Twenty-five women (62.5%) were classified as low-risk (predicted GTN probability 3.9–25.0%; observed rate 16.0% [4/25]), and 15 (37.5%) were classified as high-risk (predicted GTN probability 73.0%; observed rate 80.0% [12/15]). A simple two-parameter nomogram based on available prenatal data showed relative predictive performance and stratified women with HMCF into low- and high-risk groups with different GTN rates. Although exploratory and requiring external validation before clinical implementation, this model may help estimate prenatal risk of GTN progression and tailoring of post-molar surveillance intensity in women with HMCF.