A risk-scoring model for the prediction of endometrial cancer among symptomatic postmenopausal women with endometrial thickness > 4 mm

Abstract

Objective: To develop and test a risk-scoring model for the prediction of endometrial cancer among symptomatic postmenopausal women at risk of intrauterine malignancy.

Methods: We prospectively studied 624 postmenopausal women with vaginal bleeding and endometrial thickness > 4 mm undergoing diagnostic hysteroscopy. Patient characteristics and endometrial assessment of women with or without endometrial cancer were compared. Then, a risk-scoring model, including the best predictors of endometrial cancer, was tested. Univariate, multivariate, and ROC curve analysis were performed. Finally, a split-sampling internal validation was also performed.

Results: The best predictors of endometrial cancer were recurrent vaginal bleeding (odds ratio (OR) = 2.96), the presence of hypertension (OR = 2.01) endometrial thickness > 8 mm (OR = 1.31), and age > 65 years (OR = 1.11). These variables were used to create a risk-scoring model (RHEA risk-model) for the prediction of intrauterine malignancy, with an area under the curve of 0.878 (95% CI 0.842 to 0.908; P < 0.0001). At the best cut-off value (score ≥ 4), sensitivity and specificity were 87.5% and 80.1%, respectively.

Conclusion: Among symptomatic postmenopausal women with endometrial thickness > 4 mm, a risk-scoring model including patient characteristics and endometrial thickness showed a moderate diagnostic accuracy in discriminating women with or without endometrial cancer. Based on this model, a decision algorithm was developed for the management of such a population.

Figure 1

ROC curve associated with the risk-scoring model. The area under the curve was 0.878 (95% CI 0.842 to 0.908; P < 0.0001).

Figure 2

Flow-chart showing a decision algorithm for the management of symptomatic postmenopausal women with endometrial thickness > 4 mm.