Endometrial Carcinoma

This retrospective study developed machine learning models to improve long-term prognostic assessment in endometrial cancer. By integrating routine laboratory tests with FIGO staging, researchers demonstrated a significant enhancement in predicting 5- and 10-year overall and disease-free survival. The K-nearest neighbour model achieved an AUC of 0.876 for 10-year overall survival, outperforming FIGO staging and age alone. This low-cost and accessible approach could optimize prognostic assessment, especially in settings where advanced molecular profiling is limited.

This study assessed the cost-effectiveness of ProMisE (Proactive Molecular Risk Classifier for Endometrial Cancer) testing to guide initial treatment in stage III/IV primary advanced or recurrent endometrial cancer. Using a decision tree and partitioned survival model, researchers compared lifetime costs and outcomes with and without molecular testing. The findings indicate that ProMisE testing is cost-effective from a payer perspective, with an incremental cost-effectiveness ratio (ICER) of $66,321 USD per quality-adjusted life-year (QALY) gained, well below the $150,000 USD threshold. From a societal perspective, ProMisE testing even resulted in lower costs and higher QALYs. This personalized approach is considered clinically meaningful and of high value.

The FIGO staging system for endometrial cancer underwent a significant revision in 2023, incorporating refined anatomical criteria and molecular determinants. This update aims to optimize adjuvant treatment selection by maximizing therapeutic benefits while minimizing harm. Molecular subgroups include POLEmut, p53abn, MMRd, and NSMP. The 2025 ESGO-ESTRO-ESP recommendations further enhance this framework by mandating estrogen receptor (ER) assessment within the NSMP category, identifying early-stage disease with an increased risk of recurrence and mortality.