ESTRO 2022 - Abstract Book

S668

Abstract book

ESTRO 2022

The Kaplan-Meier plots (fig 2) show that the gain from the RCA factor is centre-dependent. Due to the stratified approach, baseline risks can also be calculated per centre. Differences between centres are observed, indicating that differences in OS cannot be fully accounted for based only on the included model parameters. Additional parameters are needed to improve the original model’s centre-specific performance to account for this.

Conclusion A TRIPOD type 4 evaluation has been performed of the Egelmeer et al. model using distributed learning to protect patient privacy. It is shown that the model needed RCA to increase the predictive accuracy. However, the improvement in prediction power was institution-dependent, indicating that differences within the cohorts exist beyond those accounted for by the original model parameters. This indicates the need to evaluate the regression value for the included model parameter or include additional parameters, e.g. smoking status and tumour volume.

OC-0755 Big data prediction models to select head and neck patients for personalized dose prescription

L.V. van Dijk 1 , S. Ahmed 2 , A.S.R. Mohammed 2 , K. Wahid 2 , N.M. Sijtsema 3 , B. Gunn 2 , A.S. Garden 2 , J.A. Langendijk 4 , C.D. Fuller 2 1 University Medical Center Groningen; MD Anderson Cancer Center, Radiation Oncology, Groningen, The Netherlands; 2 MD Anderson Cancer Center, Radiation Oncology, Houston, USA; 3 University Medical Center Groningen, Radiation Oncology, Groningen, The Netherlands; 4 University Medical Center Groningn, Radiation Oncology, Groningen, The Netherlands

Purpose or Objective