EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Predicting near‐complete pathological response to (chemo)radiotherapy in patients with rectal cancer: A federated learning study

Pedro Mateus, Mariachiara Savino, Nikola Dino Capocchiano, Maaike Berbee, Maria Antonietta Gambacorta, Giuditta Chiloiro, Yves C P Willems, Andrea Damiani, Biche Osong, Andre Dekker, Inigo Bermejo

Medical Physics · 2025-08 · 52 (8)

DOI: 10.1002/mp.18034 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, online erschienen am 08.08.2025. Verfasst von Pedro Mateus und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, the Netherl…. Hauptthemen laut MEDLINE: Rectal Neoplasms, Chemoradiotherapy, Machine Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Bowel Research UK.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Organ preservation in patients with locally advanced rectal cancer has attracted interest due to improved quality of life and functional outcomes compared with total mesorectal excision. Hence, patients who achieve clinical complete response (cCR) after (chemo)radiotherapy are offered a watch‐and‐wait strategy. Those who are likely to fall short of the strict criteria of cCR and only achieve near complete response (NCR) might benefit from radiation boosting to avoid surgery.

Purpose

To develop a prediction model that estimates the probability of NCR trained on data from different clinics.

Methods

We used data from two clinics (Maastro and Gemelli) on 1305 patients. We set up and used a federated learning infrastructure to leverage patient data from the clinics without transferring it. We used Bayesian networks for their capacity to combine expert knowledge with data and their ability to handle missing data. In this article, we propose a novel federated learning algorithm for Bayesian networks. In addition, we explore different approaches to handle missing data and train the models, combining expert elicited structures and those learnt from data. The discriminative performance of the models is reported using the area under the ROC curve (AUC).

Results

The model trained on data from both clinics and a structure learnt from data performed well (AUC 0.77). When using a structure elicited from an expert, the performance of the model decreased (AUC 0.68). Fine‐tuning the expert structure with data led to a middle ground performance (AUC 0.72). Models trained on data from a single clinic failed to generalize when tested on data from the other clinic (AUCs 0.50 and 0.59).

Conclusions

The model trained with federated learning showed good discriminative performance, which indicates that it could be useful to identify which patients with rectal cancer would benefit the most from a radiotherapy boost. This study shows that federated learning has the potential to lead to better models by allowing access to more data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Rectal NeoplasmsChemoradiotherapyMachine LearningHumansBayes TheoremTreatment OutcomeFederated Learning

Stichwörter der Autor:innen

Radiotherapyartificial intelligencefederated learningprediction model

Autor:innen und Institutionen

  • Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, the Netherlands.
  • Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy.
  • Data Science Institute (DSI), Hasselt University, Hasselt, Belgium.

Förderung

  • Bowel Research UK

Zitieren

APA

Mateus, P., Savino, M., Capocchiano, N. D., Berbee, M., Gambacorta, M. A., Chiloiro, G., Willems, Y. C. P., Damiani, A., Osong, B., Dekker, A., & Bermejo, I. (2025). Predicting near‐complete pathological response to (chemo)radiotherapy in patients with rectal cancer: A federated learning study. Medical Physics, 52(8). https://doi.org/10.1002/mp.18034

Vancouver

Mateus P, Savino M, Capocchiano ND, Berbee M, Gambacorta MA, Chiloiro G, et al. Predicting near‐complete pathological response to (chemo)radiotherapy in patients with rectal cancer: A federated learning study. Medical Physics. 2025;52(8). doi:10.1002/mp.18034

BibTeX
@article{Mateus2025,
  author = {Mateus, Pedro and Savino, Mariachiara and Capocchiano, Nikola Dino and Berbee, Maaike and Gambacorta, Maria Antonietta and Chiloiro, Giuditta and Willems, Yves C P and Damiani, Andrea and Osong, Biche and Dekker, Andre and Bermejo, Inigo},
  title = {Predicting near‐complete pathological response to (chemo)radiotherapy in patients with rectal cancer: A federated learning study},
  journal = {Medical Physics},
  year = {2025},
  volume = {52},
  number = {8},
  doi = {10.1002/mp.18034}
}
Kostenlos starten →