Development of a Machine Learning-Based Prognostic Model for Intermediate Trophoblastic Tumors: A Single-Center Study With Web-Based Tool Implementation
A machine-learning prognostic tool for rare placental tumors provides individualized predictions via free online calculator, requiring external validation.
The first ML-based prognostic model for intermediate trophoblastic tumors integrates immune-inflammatory markers with clinicopathologic features via Random Survival Forest, achieving C-index 0.816 in 236 patients over 24 years. A public Shiny web tool enables real-time individualized PFS predictions pending external multi-center validation.
What the study was
- Study design
- Retrospective cohort + Random Survival Forest ML model development
- Population
- ITT patients, Peking Union Medical College Hospital 2000–2024
- Sample size
- 236
- Category
- Diagnostics
- Maturity
- Exploratory
- Journal
- JCO Precision Oncology
Why it surfaced
First ML prognostic model for a rare gynecologic malignancy (ITT) with web tool deployment; JCO Precis Oncol.
A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.