ESTRO 2021 Abstract Book

S1522

ESTRO 2021

Conclusion The considered diffusion-based tumour growth model to simulate the microscopic infiltration of high-grade gliomas appears robust with respect to its parameters. Mathematical modelling may therefore be used to improve the clinical target delineation in high-grade gliomas. PO-1796 Machine learning-based models of toxicity in prostate cancer ultra-hypofractionated radiotherapy M. Pepa 1 , M. Zaffaroni 1 , S. Volpe 1,2 , G. Marvaso 1,2 , J.L. Isaksson 1 , S. Barzaghi 3 , F. Benigni 3 , M. Callegari 3 , A. Gismundi 3 , F.M. La Fauci 4 , G. Corrao 1,2 , M. Augugliaro 1 , F. Cattani 4 , G. Baroni 3 , E. De Momi 3 , R. Orecchia 5 , B.A. Jereczek-Fossa 1,2 1 IEO European Institute of Oncology IRCCS, Division of Radiation Oncology, Milan, Italy; 2 University of Milan, Department of Oncology and Hemato-Oncology, Milan, Italy; 3 Politecnico di Milano, Department of Electronics Information and Bioengineering (DEIB), Milan, Italy; 4 IEO European Institute of Oncology IRCCS, Medical Physics Unit, Milan, Italy; 5 IEO European Institute of Oncology IRCCS, Scientific Direction, Milan, Italy Purpose or Objective In the last decades, radiotherapy (RT) treatments have become safer and more effective, allowing for dose escalation to the target volume without jeopardizing the sparing of surrounding organs at risk (OARs). However, effective toxicity prediction tools are essential in the era of tailored treatments. The purpose of the study is to test machine learning (ML)-based predictive models of toxicity in prostate cancer (PCa) patients (pts) treated with ultra-hypofractionated RT regimens. Materials and Methods Two cohorts of 61 and 186 non-metastatic low-intermediate risk PCa pts (from AIRC IG-13218 prospective trial and “Give me Five” retrospective trial, respectively), who underwent ultra- hypofractionated RT (35 Gy/5 fractions), were considered (Ethics Committee Notification UID 2410). Dosimetric and clinical features were used to train different ML models to predict genitourinary (GU) and gastrointestinal (GI) acute toxicities. The area under the receiver operating characteristic curve (AUC) was used to compare the model performances. Results Separate analyses of the three groups (61, 186 and 247) were carried out. Bagged trees outperformed all the others on the 61 cohort ( Fig. 1a ), with an AUC of 0.75, while SVM resulted the best algorithm on the 186 ( Fig 1b ) and 247 cohort ( Fig 1c ), with an AUC of 0.94 and 0.66, respectively. Overall, the best performing algorithm was LR, since, among the 8 best results, 4 were achieved with this one. The most predictive features were found to be T-stage, age, OARs volume and DVH punctual values. No significant correlation with the outcome was found for sub-areas under the DVH. Overall, the models achieved better AUC values when the two subgroups of pts were considered separately. The study presents some limitations, such as the relatively low occurrence of toxicity events, often resulting in a scarce capability of identifying true positives, and low AUC values in certain configurations. Figure 1