Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
March 16, 2026Nature CommunicationsOpen Access

An international multi-centre study to develop and validate federated learning-based prognostic models for anal cancer

View Full Paper
Ask AI
Bookmark
Share

Authors

STStelios TheophanousPLPer-Ivar LønneACAnanya Choudhury

Discussion

Loading...

Member takes

Overview

International multi-centre study develops models to predict outcomes in anal cancer, indicating improved survival and control factors.

Key Points

  • The aim is to develop and validate federated learning-based models to predict outcomes for anal cancer patients.
  • Conducted across 14 centres with 1428 patients and validated in 2 additional centres with 277 patients.
  • Utilized federated multivariable Cox models for analysis.
  • Focused on variables related to patient outcomes, including T stage, tumour volume, and treatment type.
  • Achieved c-indices of 0.68-0.79, indicating good model performance.
  • Identified predictors of improved overall survival, including lower T stage and female sex.
  • Determined that smaller tumour volume is linked to better locoregional control and reduced distant metastases.

Cite This Study

Theophanous et al. (2026) studied this question.

synapsesocial.com/papers/69b79e7c8166e15b153abebehttps://doi.org/10.1038/s41467-026-70297-3
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Predicting near‐complete pathological response to (chemo)radiotherapy in patients with rectal cancer: A federated learning study2025
  2. 2A decentralized federated learning-based cancer survival prediction method with privacy protection2024 · 4 citations
  3. 3Federated CT foundation models for multi-center detection of lymph node metastasis in pancreatic cancer2026 · 1 citations
  4. 4Predicting treatment response in multicenter non-small cell lung cancer patients based on federated learning2024 · 15 citations
  5. 5A Collaborative Federated Learning Framework for Lung and Colon Cancer Classifications2024 · 9 citations