Search

• IHU is a prospective multi-institute study dealing with toxicity after PNI. • Dosimetry and clinical predictors of 2-year G2+ lymphopenia were investigated. • DVHs of Body and of pelvic bone marrow were associated with the end-point. • Multi-variable modelling showed baseline ALC as the most relevant predictor. • Smoke, lumbosacral DVH and acute G3 lymphopenia independently modulate the risk. Given the substantial lack of knowledge, we aimed to assess clinical/dosimetry predictors of late hematological toxicity on patients undergoing pelvic-nodes irradiation (PNI) for prostate cancer (PCa) within a prospective multi-institute study. Clinical/dosimetry/blood test data were prospectively collected including lymphocytes count (ALC) at baseline, mid/end-PNI, 3/6 months and every 6 months up to 5-year after PNI. DVHs of the Body, ileum (BMILEUM), lumbosacral spine (BMLS), lower pelvis (BMPELVIS), and whole pelvis (BMTOT) were extracted. Current analysis focused on 2-year CTCAEv4.03 Grade ≥ 2 (G2+) lymphopenia (ALC < 800/μL). DVH parameters that better discriminate patients with/without toxicity were first identified. After data pre-processing to limit overfitting, a multi-variable logistic regression model combining DVH and clinical information was identified and internally validated by bootstrap. Complete data of 499 patients were available: 46 patients (9.2 %) experienced late G2+ lymphopenia. DVH parameters of BMLS/BMPELVIS/BMTOT and Body were associated to increased G2+ lymphopenia. The variables retained in the resulting model were ALC at baseline [HR = 0.997, 95 %CI 0.996–0.998, p < 0.0001], smoke (yes/no) [HR = 2.9, 95 %CI 1.25–6.76, p = 0.013] and BMLS-V ≥ 24 Gy (cc) [HR = 1.006, 95 %CI 1.002–1.011, p = 0.003]. When acute G3+ lymphopenia (yes/no) was considered, it was retained in the model [HR = 4.517, 95 %CI 1.954–10.441, p = 0.0004]. Performances of the models were relatively high (AUC = 0.87/0.88) and confirmed by validation. Two-year lymphopenia after PNI for PCa is largely modulated by baseline ALC, with an independent role of acute G3+ lymphopenia. BMLS-V24 was the best dosimetry predictor: constraints for BMTOT (V10Gy < 1520 cc, V20Gy < 1250 cc, V30Gy < 850 cc), and BMLS (V24y < 307 cc) were suggested to potentially reduce the risk. [ABSTRACT FROM AUTHOR]

• The overall worsening at two years of intestinal function in men treated with radiotherapy including pelvic node irradiation (PNI) for prostate cancer is generally mild. • Nevertheless, such worsening may be greater in a non-negligible fraction of patients, especially for specific symptoms such as frequency, gas passage, rectal bleeding and accidental soiling. • Men experiencing severe acute bowel symptoms from PNI are at higher risk of symptom persistence two years after irradiation. • This risk is only minimally dependent on baseline bowel symptoms, and not related to radiotherapy intent. To quantify patient-reported 2-year intestinal toxicity (IT) from pelvic nodal irradiation (PNI) for prostate cancer. The association between baseline/acute symptoms and 2-year worsening was investigated. Patient-reported IT was prospectively assessed through the Inflammatory Bowel Disease Questionnaire (IBDQ), filled in at baseline, radiotherapy mid-point and end, at 3 and 6 months and every 6 months until 5 years. Two-year deterioration of IBDQ scores relative to the Bowel Domain was investigated for 400 patients with no severe baseline symptoms and with questionnaires available at baseline, 2 years, RT mid-point and/or end and at least three follow-ups between 3 and 18 months. The significance of the 2-year differences from baseline was tested. The association between baseline values and Δ Acute (the worst decline between baseline and RT mid-point/end) was investigated. In the IBDQ lower scores indicate worse symptoms. A significant (p < 0.0001) 2-year mean worsening, mostly in the range of −0.2/-0.4 points on a 1–7 scale, emerged excepting one question (IBDQ29, "nausea/feeling sick"). This decline was independent of treatment intent while baseline values were associated with 2-year absolute scores. The Δ Acute largely modulated 2-year worsening: patients with Δ Acute greater than the first quartile (Q1) and Δ Acute less or equal than Q1 showed no/minimal and highly significant (p < 0.0001) deterioration, respectively. Rectal incontinence, urgency, frequency and abdominal pain showed the largest mean changes (-0.5/-1): risk of severe worsening (deemed to be of clinical significance if ≤ 2) was 3–5 fold higher in the Δ Acute ≤ Q1 vs Δ Acute > Q1 group (p < 0.0001). A modest but significant deterioration of two-year patient-reported intestinal symptoms from PNI compared to baseline was found. Patients experiencing more severe acute symptoms are at higher risk of symptom persistence at 2 years, with a much larger prevalence of clinically significant symptoms. [ABSTRACT FROM AUTHOR]

Simple Summary: Studies comparing performances of machine learning (ML) methods in building predictive models of toxicity in RT are rare. Thanks to the availability of a large cohort (n = 1314) of breast cancer patients homogeneously treated with tangential fields, different ML approaches could be compared. This work shows how more complex models typically achieve higher performances. At the same time, for this test case, the importance is given mainly by a few variables, and toxicity can be predicted by simpler models with similar performances. The availability of more individually characterizing features (here partially missing) is expected to have a likely much higher impact than the choice of the best-performing ML/DL approach. Purpose. Different ML models were compared to predict toxicity in RT on a large cohort (n = 1314). Methods. The endpoint was RTOG G2/G3 acute toxicity, resulting in 204/1314 patients with the event. The dataset, including 25 clinical, anatomical, and dosimetric features, was split into 984 for training and 330 for internal tests. The dataset was standardized; features with a high p-value at univariate LR and with Spearman ρ > 0.8 were excluded; synthesized data of the minority were generated to compensate for class imbalance. Twelve ML methods were considered. Model optimization and sequential backward selection were run to choose the best models with a parsimonious feature number. Finally, feature importance was derived for every model. Results. The model's performance was compared on a training–test dataset over different metrics: the best performance model was LightGBM. Logistic regression with three variables (LR3) selected via bootstrapping showed performances similar to the best-performing models. The AUC of test data is slightly above 0.65 for the best models (highest value: 0.662 with LightGBM). Conclusions. No model performed the best for all metrics: more complex ML models had better performances; however, models with just three features showed performances comparable to the best models using many (n = 13–19) features. [ABSTRACT FROM AUTHOR]

To evaluate the persistence of symptoms after radiotherapy (RT) for localised prostate cancer (PCa) and the association with quality of life (QOL). Prospective patient-reported outcome (PRO) from a multi-institutional study on PCa treated with radical RT (2010–2014) was analysed. Data was collected at baseline (BL) and follow-ups (FUPs) up to 5 years. Patients with BL and ≥3 late FUPs (≥6 months) were analysed. PRO was scored by means of the IPSS and ICIQ-SF (urinary), LENT-SOMA (gastrointestinal [GI]), and EORTC-C30 (pain, insomnia, fatigue, and QOL) questionnaires. Symptoms were defined 'persistent' if the median score over FUPs was ≥3 (urinary) or ≥2 (GI, pain, insomnia, and fatigue), and worse than BL. Different thresholds were chosen to have enough events for each symptom. QOL was linearly transformed on a continuous scale (0–100). Linear-mixed models were used to identify significant differences between groups with and without persistent symptoms including age, smoking status, previous abdominal surgery, and diabetes as confounders. Mean QOL differences between groups were evaluated longitudinally over FUPs. The analysis included 293 patients. Persistent urinary symptoms ranged from 2% (straining) to 12% (weak stream, and nocturia). Gastrointestinal symptoms ranged from 7% (rectal pain, and incontinence) to 30% (urgency). Proportions of pain, insomnia, and fatigue were 6, 13, and 18%. Significant QOL differences of small-to-medium clinical relevance were found for urinary incontinence, frequency, urgency, and nocturia. Among GI symptoms, rectal pain and incontinence showed small-to-medium differences. Fatigue was associated with the largest differences. The analysis showed that symptoms after RT for PCa occur with different persistence and their association with QOL varies in magnitude. A number of persistent urinary and GI symptoms showed differences in a comparable range. Urinary incontinence and frequency, rectal pain, and faecal incontinence more often had significant associations. Fatigue was also prevalent and associated with largely deteriorated QOL. [ABSTRACT FROM AUTHOR]