ESTRO 2022 - Abstract Book

S1010

Abstract book

ESTRO 2022

Conclusion Despite advancements in the treatment of metastatic breast cancer, BM is associated with a poor prognosis. PS, MC, metastatic burden, BC subtype, and number of systemic treatment lines before BM influenced survival. These factors should be considered when deciding treatment for pts with BM.

PO-1190 Machine learning to predict locoregional relapse in pT1-2pN0-1 breast cancer following mastectomy

S. Volpe 1 , F. Bellerba 2 , M. Zaffaroni 1 , M. Pepa 1 , L.J. Isaksson 1 , G. Maimone 3 , B. Menzani 3 , I. Monaco 3 , P. Maisonneuve 4 , I.R. Scognamiglio 1 , S. Dicuonzo 1 , M.A. Zerella 1 , D.P. Rojas 1 , G. Marvaso 1 , C. Fodor 1 , S. Gandini 2 , E. De Momi 3 , P. Veronesi 5 , G. Corso 5 , V.E. Galimberti 5 , M.C. Leonardi 1 , B.A. Jereczek-Fossa 1 1 Istituto Europeo di Oncologia IRCCS, Radiation Oncology, Milan, Italy; 2 Istituto Europeo di Oncologia IRCCS, Experimental Oncology, Milan, Italy; 3 Politecnico di Milano, Electronics, Information and Bioengineering, Milan, Italy; 4 Istituto Europeo di Oncologia IRCCS, Epidemiology and Biostatistics, Milan, Italy; 5 Istituto Europeo di Oncologia IRCCS, Breast Surgery, Milan, Italy Purpose or Objective While post-mastectomy radiotherapy is a mainstay for the treatment of locally-advanced breast cancer patients, indications for early stages (namely, pT1-2 pN0-1) are less defined, and a clear understanding of predictive factors of locoregional relapse (LRR) is warranted to better establish clinical indications. This study explores the potentials of machine learning (ML)-based algorithms in this clinical setting. Materials and Methods A total of 2632 patients, treated at the European Institute of Oncology IRCCS, Milan, Italy between 1998 and 2006, who underwent mastectomy without subsequent radiotherapy was considered for the analysis. Three ML- and statistics-based regression models were trained to predict LRR and to estimate the hazard ratios for all the predictor variables. For ML models the importance of the clinical features on the outcome was estimated by permuting out-of-bag (OOB) cases. The concordance index (c-index) was used to compare the performances.

Results