Journal Article

DKFZ-2026-00599

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png An international multi-centre study to develop and validate federated learning-based prognostic models for anal cancer.

Theophanous, S. ; Lønne, P.-I. ; Choudhury, A. ; Berbee, M. ; Deijen, C. ; Dekker, A. ; Field, M. ; Gambacorta, M. A. ; Gilbert, A. ; Grønlie Guren, M. ; Jadon, R. ; Kochhar, R. ; Martin, D.DKFZ* ; Mohamed, A. A. ; Muirhead, R. ; Parés, O. ; Raszewski, Ł. ; Roy, R. ; Scarsbrook, A. ; Sebag-Montefiore, D. ; Spezi, E. ; Vassiliou, V. ; Malinen, E. ; Wee, L. ; Appelt, A. ; Consortium, a. (Collaboration Author) ; Adams, R. (Contributor) ; Adamska, K. (Contributor) ; Amin, M. (Contributor) ; Capocchiano, N. D. (Contributor) ; Chlap, P. (Contributor) ; Colley, P. (Contributor) ; Damiani, A. (Contributor) ; De Luca, V. (Contributor) ; Demetriou, A. (Contributor) ; Deshpande, S. (Contributor) ; Eble, M. J. (Contributor) ; Espinoza, A. (Contributor) ; Fokas, E. (Contributor) ; Georgiou, L. (Contributor) ; Henry, A. (Contributor) ; Hoole, A. (Contributor) ; Holloway, L. C. (Contributor) ; Jansen, T. (Contributor) ; Janssen, T. (Contributor) ; Kritikopoulos, A. (Contributor) ; Lau, J. Y. G. (Contributor) ; Lee, M. T. (Contributor) ; Lilley, J. (Contributor) ; Lima, G. (Contributor) ; Lopes, P. (Contributor) ; Loveday, A. (Contributor) ; Manfrida, S. (Contributor) ; Marsden, J. (Contributor) ; Masciocchi, C. (Contributor) ; Mercer, J. (Contributor) ; Papageorgiou, E. (Contributor) ; Price, G. (Contributor) ; Rackley, T. (Contributor) ; Rödel, C. M. (Contributor) ; Savino, M. (Contributor) ; Sdrolia, A. (Contributor) ; Stroom, J. (Contributor) ; Stylianou, I. (Contributor) ; Thwaites, D. (Contributor) ; Trojanowski, M. (Contributor) ; Valentini, V. (Contributor) ; van Haveren, R. (Contributor) ; van Triest, B. (Contributor) ; Walker, A. (Contributor)

2026
Springer Nature [London]

Abstract: Precision oncology relies on access to high-quality data for increasingly smaller patient subgroups. The international atomCAT consortium investigates the potential of federated learning to support this, using anal cancer as a rare cancer exemplar. Here, we show that federated multivariable Cox models trained across 14 centres (1428 patients) and externally validated in two additional centres (277 patients) achieve consistent calibration and discrimination during leave-one-centre-out and external validation (c-indices 0.68-0.79). Lower T stage, absence of nodal involvement, smaller tumour volume, female sex, younger age, and mitomycin- or cisplatin-based chemotherapy are associated with improved overall survival. Lower T stage, smaller tumour volume, and female sex are associated with improved locoregional control, while absence of nodal involvement and smaller tumour volume are associated with better freedom from distant metastases. These findings demonstrate that federated learning enables robust, privacy-preserving prognostic modelling for rare cancers using real-world data, supporting international collaboration without data sharing.

Note: epub

---

Contributing Institute(s):

1. DKTK Koordinierungsstelle Frankfurt (FM01)

Research Program(s):

1. 899 - ohne Topic (POF4-899) (POF4-899)

Appears in the scientific report 2026

---

Database coverage:
; ; Article Processing Charges ; BIOSIS Previews ; Biological Abstracts ; Clarivate Analytics Master Journal List ; Current Contents - Agriculture, Biology and Environmental Sciences ; Current Contents - Life Sciences ; Current Contents - Physical, Chemical and Earth Sciences ; DOAJ Seal ; Essential Science Indicators ; Fees ; IF >= 15 ; JCR ; PubMed Central ; SCOPUS ; Science Citation Index Expanded ; Web of Science Core Collection ; Zoological Record

---