Chen Li

Cervical cancer (CC) is the fourth-most common and lethal cancer in women worldwide, with ~ 23% of cases in Chinese patients. We sought to characterize real-world treatment patterns and decision drivers for locally advanced CC (LACC) in China. We conducted a cross-sectional, 3-phase survey (quantitative development, cognitive, and quantitative interviews) of 360 physicians across 21 cities in China. Primary outcomes included treatment patterns and decision drivers for Chinese patients with LACC. Cancer stage was reported per International Federation of Gynecology and Obstetrics (FIGO) 2018. Respondents were gynecologists (55.6%), radiation oncologists (36.1%), and medical oncologists (8.3%), who reported 67.7% patients had LACC (stage IB3-IVA). Treatment patterns varied by stage: chemoradiotherapy (CRT) alone was used by 18.1%, 42.2%, and 52.1% of respondents for stages IB3-IIA2, IIB, and III-IVA CC, respectively, with surgery-based treatment used by 67.1%, 42.0%, and 26.6% of respondents. Among patients with LACC receiving concurrent CRT, 57.7% received external-beam radiotherapy (EBRT) plus brachytherapy (BT). The most important LACC treatment decision drivers were treatment efficacy (91.7%), CC stage (89.7%), and safety (88.6%). Only 63.9% reported that both EBRT and BT could be performed at their hospitals. Radiotherapy-related issues were reported as the top unmet medical need by 66.4%. There is a significant LACC burden among female patients in China, and deviations from guideline-concordant concurrent CRT. Addressing implementation gaps in concurrent CRT adoption requires improved radiotherapy access, greater multidisciplinary team use, guideline-aligned quality control, enhanced physician and patient education, and improved affordability. Future research should incorporate patient perspectives to improve patient-centered care and outcomes.

PURPOSE: Current prognostic systems are inadequate for intermediate trophoblastic tumors (ITTs). The aim of this study was to develop a machine learning (ML)-based model to predict progression-free survival (PFS) in patients with ITT and implement a web-based tool for individualized risk stratification. MATERIALS AND METHODS: We analyzed a retrospective cohort of 236 patients with ITT treated at a national tertiary center between 2000 and 2024. A multimodal feature selection strategy—integrating Cox regression, LASSO, Gradient Boosting Machine (GBM), and Random Survival Forest (RSF)—was used to identify robust predictors from clinicopathologic and inflammatory variables. The final prognostic model was constructed using the RSF approach. Model performance was evaluated through a rigorous nested 5-fold cross-validation framework to prevent data leakage. RESULTS: Five key predictors were identified: International Federation of Gynecology and Obstetrics stage, interval from antecedent pregnancy, Ki-67 index, neutrophil-to-lymphocyte ratio, and systemic immune-inflammation index. The RSF model demonstrated robust discrimination with a cross-validated concordance index of 0.816 (95% CI, 0.721 to 0.895) and excellent calibration (Integrated Brier Score, 0.113). Decision-curve analysis confirmed clinical utility within the relevant 20%-60% threshold range. An interactive web tool (Shinyapps) was deployed to generate real-time individualized PFS predictions with 95% confidence intervals. CONCLUSION: To our knowledge, this study presents the first ML-based prognostic model specifically for ITT. By integrating immune-inflammatory markers with traditional clinicopathologic features, the RSF model offers superior risk stratification compared with anatomic staging or alternative models. The developed online tool serves as a proof-of-concept prototype to facilitate future external validation and research on personalized clinical decision making for this rare malignancy.

Li C, et al. J Gynecol Oncol. 2024 Oct;36:e44. https://doi.org/10.3802/jgo.2025.36.e44