Development of a Machine Learning‑Based Prognostic Model for Intermediate Trophoblastic Tumors: A Single-Center Study
Weidi Wang1, Yunshu Jiao2, Yuan Li1
1National Clinical Research Center for Women's Health and Obstetric and Gynecologic Diseases, Department of Obstetrics and Gynecology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China.
This study developed a machine learning model to predict progression-free survival for intermediate trophoblastic tumors (ITT). The model integrates immune markers and clinicopathologic features, offering improved risk stratification for patients with this rare malignancy.
Area of Science:
- Gynecologic Oncology
- Machine Learning in Medicine
- Cancer Prognostics
Background:
- Current prognostic systems for intermediate trophoblastic tumors (ITT) are insufficient.
- Accurate risk stratification is crucial for personalized treatment of ITT.
Purpose of the Study:
- To develop a machine learning (ML)-based prognostic model for predicting progression-free survival (PFS) in patients with ITT.
- To create a web-based tool for individualized risk stratification of ITT.
Main Methods:
- Retrospective analysis of 236 ITT patients (2000-2024).
- Multimodal feature selection integrating Cox regression, LASSO, GBM, and RSF.
- Prognostic model built using Random Survival Forest (RSF) with nested 5-fold cross-validation.
Main Results:
- Identified five key predictors: FIGO stage, interval from antecedent pregnancy, Ki-67 index, neutrophil-to-lymphocyte ratio, and systemic immune-inflammation index.
- RSF model showed strong discrimination (C-index 0.816) and calibration (IBS 0.113).
- An interactive web tool was developed for real-time PFS prediction.
Conclusions:
- Presents the first ML-based prognostic model specifically for ITT.
- The RSF model, incorporating immune-inflammatory markers, outperforms traditional staging.
- The online tool facilitates personalized decision-making and future external validation.
More Related Videos
12:41Multiparametric Tumor Organoid Drug Screening Using Widefield Live-Cell Imaging for Bulk and Single-Organoid Analysis
Published on: December 23, 2022
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025