Introduction: We hypothesized that increasing the pelvic integral dose (ID) and a higher dose per fraction correlate with worsening fatigue and functional outcomes in localized prostate cancer (PCa) patients treated with external beam radiotherapy (EBRT). Methods: The study design was a retrospective analysis of two prospective observational cohorts, REQUITE (development, n=543) and DUE-01 (validation, n=228). Data were available for comorbidities, medication, androgen deprivation therapy, previous surgeries, smoking, age, and body mass index. The ID was calculated as the product of the mean body dose and body volume. The weekly ID accounted for differences in fractionation. The worsening (end of radiotherapy versus baseline) of European Organisation for Research and Treatment of Cancer EORTC) Quality of Life Questionnaire (QLQ)-C30 scores in physical/role/social functioning and fatigue symptom scales were evaluated, and two outcome measures were defined as worsening in ≥2 (WS2) or ≥3 (WS3) scales, respectively. The weekly ID and clinical risk factors were tested in multivariable logistic regression analysis. Results: In REQUITE, WS2 was seen in 28% and WS3 in 16% of patients. The median weekly ID was 13.1 L·Gy/week [interquartile (IQ) range 10.2-19.3]. The weekly ID, diabetes, the use of intensity-modulated radiotherapy, and the dose per fraction were significantly associated with WS2 [AUC (area under the receiver operating characteristics curve) =0.59; 95% CI 0.55-0.63] and WS3 (AUC=0.60; 95% CI 0.55-0.64). The prevalence of WS2 (15.3%) and WS3 (6.1%) was lower in DUE-01, but the median weekly ID was higher (15.8 L·Gy/week; IQ range 13.2-19.3). The model for WS2 was validated with reduced discrimination (AUC=0.52 95% CI 0.47-0.61), The AUC for WS3 was 0.58. Conclusion: Increasing the weekly ID and the dose per fraction lead to the worsening of fatigue and functional outcomes in patients with localized PCa treated with EBRT.
Background: REQUITE (validating pREdictive models and biomarkers of radiotherapy toxicity to reduce side effects and improve QUalITy of lifE in cancer survivors) is an international prospective cohort study. The purpose of this project was to analyse a cohort of patients recruited into REQUITE using a deep learning algorithm to identify patient-specific features associated with the development of toxicity, and test the approach by attempting to validate previously published genetic risk factors. Methods: The study involved REQUITE prostate cancer patients treated with external beam radiotherapy who had complete 2-year follow-up. We used five separate late toxicity endpoints: ≥grade 1 late rectal bleeding, ≥grade 2 urinary frequency, ≥grade 1 haematuria, ≥ grade 2 nocturia, ≥ grade 1 decreased urinary stream. Forty-three single nucleotide polymorphisms (SNPs) already reported in the literature to be associated with the toxicity endpoints were included in the analysis. No SNP had been studied before in the REQUITE cohort. Deep Sparse AutoEncoders (DSAE) were trained to recognize features (SNPs) identifying patients with no toxicity and tested on a different independent mixed population including patients without and with toxicity. Results: One thousand, four hundred and one patients were included, and toxicity rates were: rectal bleeding 11.7%, urinary frequency 4%, haematuria 5.5%, nocturia 7.8%, decreased urinary stream 17.1%. Twenty-four of the 43 SNPs that were associated with the toxicity endpoints were validated as identifying patients with toxicity. Twenty of the 24 SNPs were associated with the same toxicity endpoint as reported in the literature: 9 SNPs for urinary symptoms and 11 SNPs for overall toxicity. The other 4 SNPs were associated with a different endpoint. Conclusion: Deep learning algorithms can validate SNPs associated with toxicity after radiotherapy for prostate cancer. The method should be studied further to identify polygenic SNP risk signatures for radiotherapy toxicity. The signatures could then be included in integrated normal tissue complication probability models and tested for their ability to personalize radiotherapy treatment planning.
