Federated Learning Survival Model and Potential Radiotherapy Decision Support Impact Assessment for Non–small Cell Lung Cancer Using Real-World Data

Published in Clinical Oncology, 2024

Graphical abstract

Graphical abstract showing a seven-clinic federated learning workflow for stage I-III non-small cell lung cancer radiotherapy, with 1655 eligible patients, model AUC 0.68, and a projected 11% increase in 2-year survival.

Authors: M. Field, S. Vinod, G. P. Delaney, N. Aherne, M. Bailey, M. Carolan, A. Dekker, S. Greenham, E. Hau, J. Lehmann, J. Ludbrook, A. Miller, A. Rezo, J. Selvaraj, J. Sykes, D. Thwaites, L. Holloway

Published in: Clinical Oncology

DOI / Publisher link: https://doi.org/10.1016/j.clon.2024.03.008

Keywords: Decision support, federated learning, lung cancer, machine learning, radiation oncology

BibTeX: Download

Recommended citation: M. Field, S. Vinod, G. P. Delaney, N. Aherne, M. Bailey, M. Carolan, A. Dekker, S. Greenham, E. Hau, J. Lehmann, J. Ludbrook, A. Miller, A. Rezo, J. Selvaraj, J. Sykes, D. Thwaites, L. Holloway (2024). "Federated Learning Survival Model and Potential Radiotherapy Decision Support Impact Assessment for Non–small Cell Lung Cancer Using Real-World Data." Clinical Oncology. 36(7), e197-e208.
Download Paper | Download Bibtex