ESTRO 2022 - Abstract Book

S667

Abstract book

ESTRO 2022

Conclusion This study highlights that small errors, some of which are well within machine tolerance specifications, can have significant dosimetric impact on spine SABR plans. Furthermore, it was shown that PSQA can miss some of these errors. The robustness of such plans to subtle errors and PSQA tolerances should be carefully considered.

OC-0754 TRIPOD level-4 validation for a larynx cancer survival model using distributed learning

C.R. Hansen 1,2,3,4 , M. Field 5 , G. Price 6 , N. Sarup 1 , R. Zukauskaite 7 , J. Johansen 7 , J.G. Eriksen 8 , F. Aly 9 , A. McPartlin 6 , L. Holloway 10 , D.I. Thwaites 4 , C. Brink 1,11 1 Odense University Hospital, Laboratory of Radiation Physics, Odense, Denmark; 2 University of Southern Denmark, Department of Clinical Research, Odense C, Denmark; 3 Aarhus University Hospital, Danish Centre for Particle Therapy, Aarhus, Denmark; 4 University of Sydney, Institute of Medical Physics, School of Physics, Sydney, Australia; 5 University of New South Wales, SouthWest Sydney Clinical School, Sydney, Australia; 6 University of Manchester, The Christie NHS Foundation Trust, Manchester, United Kingdom; 7 Odense University Hospital, Department of Oncology, Odense, Denmark; 8 Aarhus University Hospital, Department of Oncology, Aarhus, Denmark; 9 Ingham Institute, Applied Medical Research, Sydney, Australia; 10 Liverpool and Macarthur Cancer Therapy Centres, Department of Oncology, Sydney, Australia; 11 University of Southern Denmark, Department of Clinical Research, Odense , Denmark Purpose or Objective Prediction models are needed to support clinical decision making; however, models need to be robustly validated in diverse cohorts to demonstrate generalisability to the clinical community. Healthcare providers also have a competing responsibility to protect sensitive patient data. The current study used distributed learning to validate a larynx cancer survival model in an international multi-centre setting without patient data leaving their own host institute. Materials and Methods Patients receiving radiotherapy for larynx cancer from 2005-2018 at three international centres were identified to validate the overall survival (OS) model of Egelmeer et al. (Radiother. Oncol. 2011). This model utilises the parameters: time corrected EQD2 tumour dose, haemoglobin at treatment start, sex, age, site (glottic vs non-glottic), tumour and nodal stage. Data imputation for a maximum of one missing variable was allowed. An institution-stratified Cox regression model was developed utilising an open-source privacy-by-design distributed learning network. The validation aimed to test whether the hazard predicted from the original model would benefit from multiplication by a recalibration (RCA) factor. The study is a TRIPOD level 4 validation, where the model is fully supported if RCA=1. During the entire model optimisation, no patient data left their own hospital. Results 1930 patients were identified, with 1278 suitable for use in the evaluation. The RCA factor determined across the centres was 0.76 [95%CI 0.62-0.91], i.e. showing the original model would benefit from recalibration. The three centres' Harrell C- indices were 0.68±0.06, 0.74±0.02 and 0.70±0.04 (95%CI), indicating a generally acceptable model performance. The distributed learning system produced centre-specific calibration plots and comparisons between observed and predicted Kaplan-Meier curves split by risk group. Following RCA, the data in the calibration plot is close to the identity line, indicating the model's general applicability (fig 1).