ESTRO 2021 Abstract Book

S765

ESTRO 2021

Results For prostate cancer 11/12 of the monitored symptoms were predicted with high accuracy. 7/12 performed well with three severity classes and for 4/12 two were used (* after MCC value indicates two classes in the table). Hematuria could not be predicted due to its rarity. For breast cancer 7/7 symptoms were predicted with high accuracy. 4/7 performed well with three severity classes and for 3/7 two were used. Similar results were obtained for post treatment follow-up (data not shown).

Prostate symptoms

MCC (* = two severity classes)

constipation

0.47

erectile dysfunction

0.72

fatigue

0.60

prostatic pain

0.49

urinary frequency

0.61

urinary incontinence

0.69

urinary retention

0.52

diarrhea

0.58*

painful urination

0.59*

rectal pain

0.54*

urinary urgency

0.65*

Breast symptoms

MCC (* = two severity classes)

ECOG performance status

0.73

fatigue

0.70

pain

0.61

breast shape

0.66

difficulty swallowing 0.69* radiation induced skin reaction 0.67* swelling 0.58*

Conclusion The study suggests that the occurrence and severity of patient reported symptoms during the upcoming week can be predicted with excellent accuracy for breast and prostate cancer patients undergoing RT. Such ML models could be used for, e.g., proactive patient guidance and alerting the clinical staff to enable earlier interventions. The results should be validated in a prospective clinical trial. PD-0925 An European cross-cultural analysis of worsening of functional scales in prostate cancer patients after RT A. Cicchetti 1 , N. Joseph 2 , P. Seibold 3 , B. Avuzzi 4 , R. Valdagni 5 , A. Webb 6 , D. De Ruysscher 7 , M. Lambrecht 8 , E. Sperk 9 , R. Elliott 10 , C. Talbot 11 , L. Veldeman 12 , J. Chang-Claude 3 , A. Choudhury 13 , A. Vega 14 , D. Azria 15 , T. Rancati 16 , C. West 17 1 Fondazione IRCCS Istituto Nazionale dei Tumori di Milano, Prostate Cancer Program, Milan, Italy; 2 General Hospital Chilaw, Ministry of Health, Chilaw, Sri Lanka; 3 German Cancer Research Center (DKFZ), Division of Cancer Epidemiology, Heidelberg, Germany; 4 Fondazione IRCCS Istituto Tumori di Milano, Radiation Oncology 1, Milan, Italy; 5 University of Milan, Department oncology and hematoncology, Milan, Italy; 6 University of Leicester, Department of Genetics and Genome Biology, Leicester, United Kingdom; 7 Maastricht University Medical Center, Department of Radiation Oncology, Maastricht, Belgium; 8 University Hospitals Leuven, -, Leuven, Belgium; 9 University of Heidelberg, Department of Radiation Oncology, Mannheim,, Germany; 10 University of Manchester, Translational Radiobiology Group, Division of Cancer Sciences, Manchester, United Kingdom; 11 University of Leicester, Leicester Cancer Research Centre,, Leicester, United Kingdom; 12 Ghent University, Department of Human Structure and Repai, Ghent, Belgium; 13 University of Manchester, Christie Hospital, Division of Cancer Sciences Translational Radiobiology Group, Manchester, United Kingdom; 14 Fundación Pública Galega de Medicina Xenómica, Grupo de Medicina Xenómica (USC), Santiago de Compostela, Spain; 15 Montpellier Cancer Institute, Department of Radiation Oncology, Montpellier, France; 16 Fondazione IRCCS Istituto Nazionale dei Tumori, Prostate Cancer Program, milan, Italy; 17 University of Manchester, Manchester Academic Health Science Centre,, Translational Radiobiology Group, Division of Cancer Sciences,, Manchester, United Kingdom Purpose or Objective The study aimed to evaluate the deterioration of functional outcomes in localized prostate cancer (PCa) patients (pts) treated with external beam radiotherapy (RT), including analysis of differences possibly due to cultural effects. Materials and Methods EORTC QLQ-C30 (version 3.0) was administered to pts enrolled in a multicenter prospective observational study in 7 European countries (UK, BE, NH, DE, IT, ES, FR). For this analysis, we specifically considered one symptom scale (Fatigue) and three functional scales (Physical, Role, Social) at three time-points: baseline, RT end and 2-year after RT. The average score variation in acute and late phases as stratified by country was determined. We used radar plots to report results quantitatively, and we computed the hexagonal areas from these plots to obtain a summary variable describing the functional status. Worsening in at least 2 (wrs2) or 3

Made with FlippingBook Learn more on our blog