What type of study is this?

September 10, 2025Medical PhysicsOpen Access

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

View Full Paper

Ask AI

Bookmark

Authors

This federated learning approach identifies likelihood of near complete response to radiotherapy in rectal cancer, suggesting new treatment paths.

The federated learning model achieved an area under the ROC curve (AUC) of 0.77 for predicting near complete response.
When expert knowledge structures were used, model performance decreased to an AUC of 0.68, highlighting data importance.
Using data from multiple clinics improved model reliability compared to those trained on single clinics, which showed poor generalizability.
Federated learning enables better data access and machine learning model development while maintaining patient data privacy.

Mateus et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

September 10, 2025Medical PhysicsOpen Access

View Full Paper

Ask AI

Bookmark

Authors

This federated learning approach identifies likelihood of near complete response to radiotherapy in rectal cancer, suggesting new treatment paths.

The federated learning model achieved an area under the ROC curve (AUC) of 0.77 for predicting near complete response.
When expert knowledge structures were used, model performance decreased to an AUC of 0.68, highlighting data importance.
Using data from multiple clinics improved model reliability compared to those trained on single clinics, which showed poor generalizability.
Federated learning enables better data access and machine learning model development while maintaining patient data privacy.

Mateus et al. (2025) studied this question.

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

View Full Paper

Ask AI

Bookmark