ESTRO 36 Abstract Book

S860 ESTRO 36 _______________________________________________________________________________________________

EP-1595 NTCP models for early toxicities in patients with prostate or brain tumours receiving proton therapy A. Dutz 1,2 , L. Agolli 1,3 , E.G.C. Troost 1,2,3,4,5 , M. Krause 1,2,3,4,5 , M. Baumann 1,2,3,4,5 , A. Lühr 1,2,3,4 , S. Löck 1,3,5 1 OncoRay - Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus- Technische Universität Dresden, Dresden, Germany 2 Helmholtz-Zentrum Dresden-Rossendorf, Institute of Radiooncology, Dresden, Germany 3 Department of Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus- Technische Universität Dresden, Dresden, Germany 4 German Cancer Research Center DKFZ, Heidelberg and German Cancer Consortium DKTK partner site Dresden, Dresden, Germany 5 National Center for Tumor Diseases, partner site Dresden, Dresden, Germany Purpose or Objective To identify patients who are likely to benefit most from proton therapy, based on the potential reduction in normal tissue complication probability (NTCP) compared to photon therapy. The NTCP models required for this comparison were developed using clinical data on early side effects for patients with brain or prostate cancer having received proton therapy. Material and Methods Eighty patients with primary brain tumours and 30 patients with adenocarcinoma of the prostate who received proton therapy were included in this study. For the brain tumour patients, the radiation-induced early toxicities alopecia, erythema, pain and fatigue were considered, while for prostate cancer proctitis, diarrhoea, urinary frequency, urgency and incontinence, obstructive symptoms and radiation-induced cystitis were investigated. The occurrence of these side effects was correlated with different dose-volume parameters of associated organs at risk. NTCP models were created using logistic regression. A retrospective comparative treatment planning study was conducted to predict the potential reduction in NTCP of proton therapy compared to volumetric modulated arc therapy using the created models. For patients with brain tumours different subgroups were defined to identify patient groups which show a particularly high reduction in the considered toxicities. Results For patients with primary brain tumours significant correlations between the occurrence of alopecia grade 2 as well as erythema grade ≥ 2 and the dose-volume parameters D5% and V25Gy of the skin were found. Plan comparison showed an average reduction in NTCP for alopecia grade 2 of more than 5 % (see figure) and for erythema grade ≥ 2 of about 5 % using proton therapy. For patients with a brain tumour located in the skull base, with a clinical target volume less than 115 cm³ or with a prescribed dose less than 60 Gy, a potential reduction in NTCP for alopecia grade 2 of about 10 % could be achieved. For patients with prostate cancer significant correlations between obstructive symptoms grade ≥ 1 and the dose parameter D30% of the bladder as well as radiation- induced cystitis grade ≥ 1 and D20% of the bladder were found. Plan comparison showed an average reduction in NTCP for obstructive symptoms ≥ grade 1 of about 25 % and for radiation-induced cystitis about 15 % using proton therapy.

Conclusion We found significant correlations between the occurence of early toxicities and dose-volume parameters of associated organs at risk for patients with primary brain tumours or prostate cancer receiving proton therapy. A reduction of NTCP could be predicted for proton therapy based on comparative treatment planning. After validation, these results may be used to identify patients who are likely to benefit most from proton therapy, as suggested by the model-based approach [1]. [1] Langendijk JA et al. (2013) Radiother Oncol 107, 267 - 273. EP-1596 Developing and validating a survival prediction model for NSCLC patients using distributed learning A. Jochems 1 , T. Deist 1 , I. El-Naqa 2 , M. Kessler 2 , C. Mayo 2 , J. Reeves 2 , S. Jolly 2 , M. Matuszak 2 , R. Ten Haken 2 , J. Van Soes 1 , C. Oberije 1 , C. Faivre-Finn 3 , G. Price 3 , P. Lambin 1 , A. Dekker 1 1 MAASTRO Clinic, Radiotherapy, Maastricht, The Netherlands 2 University of Michigan, Radiation oncology, Ann-Arbor, USA 3 The University of Manchester, Manchester Academic Health Science Centre, Manchester, United Kingdom Purpose or Objective The golden standard for survival prediction in NSCLC patients, the TNM stage system, is of limited quality for patients receiving (chemo)radiotherapy[1]. In this work, we develop an up-to-date predictive model for survival prediction based on a large volume of patients using a big data distributed learning approach. Distributed learning is defined as learning from multiple patient datasets without these data leaving their respective hospitals. Furthermore, we compare performance of our model to a TNM stage based model. We demonstrate that the TNM stage system performs poorly on the validation cohorts, whereas our model performs significantly above the chance level. Material and Methods Clinical data from 1299 lung cancer patients, treated with curative intent with chemoradiation (CRT) or radiotherapy (RT) alone were collected and stored in 3 different cancer institutes. Two-year post-treatment survival was chosen as the endpoint. Data from two institutes (1152 patients at Institute 1 and 147 at Institute 2) was used to develop the model while data from the 3 rd institute (207 patients at Institute 3) was used for model validation. A Bayesian network model using clinical and dosimetric variables was adapted for distributed learning (watch the animation: link censored). The Institute 1 cohort data is publicly available at (link censored) and the developed models can be found at (link censored). Results A Bayesian network (BN) structure was determined based on expert advice and can be observed in figure 1. Variables included in the final model were TNM stage, age,