Emergency approval of vaccines against COVID-19 provides an opportunity for us to return to pre-pandemic oncology care. However, safety data in cancer patients is lacking due to their exclusion from most phase III trials. We included all patients aged less than 65 years who received a COVID-19 vaccine from 8 December 2020 to 28 February 2021 at our London tertiary oncology centre. Solicited and unsolicited vaccine-related adverse events (VRAEs) were collected using telephone or face-to-face consultation. Within the study period, 373 patients received their first dose of vaccine: Pfizer/BioNTech (75.1%), Oxford/AstraZeneca (23.6%), Moderna (0.3%), and unknown (1.1%). Median follow-up was 25 days (5–85). Median age was 56 years (19–65). Of the patients, 94.9% had a solid malignancy and 76.7% were stage 3–4. The most common cancers were breast (34.0%), lung (13.4%), colorectal (10.2%), and gynaecological (10.2%). Of the patients, 88.5% were receiving anti-cancer treatment (36.2% parenteral chemotherapy and 15.3% immunotherapy), 76.1% developed any grade VRAE of which 2.1% were grade 3. No grade 4/5 or anaphylaxis were observed. The most common VRAEs within 7 days post-vaccination were sore arm (61.7%), fatigue (18.2%), and headaches (12.1%). Most common grade 3 VRAE was fatigue (1.1%). Our results demonstrate that COVID-19 vaccines in oncology patients have mild reactogenicity.

5074 Background: Existing clinicopathological tools are unable to accurately identify renal cell carcinoma (RCC) patients who will develop metastases after surgery. As a result, it is unclear how long and how often to follow-up patients post-operatively. Tumor macropathology, as assayed by CT scanning, represents the sum product of tumor biology and microenvironment. We hypothesized that quantitative tumor features extracted from CT scans (termed radiomics) could discriminate between metastatic and non-metastatic RCCs. Methods: This retrospective study incorporated three cohorts of clear-cell RCC patients (n = 279, from TCGA, CPTAC and KiTS19 datasets) treated with nephrectomy. The study cohort was sub-divided into metastatic (n = 54, M1 at diagnosis or recurrence after surgery), high metastatic risk/HMR (n = 85, N1, T3-4, T2G3/4, T1G4) or low metastatic risk/LMR (n = 140, absence of these features) subsets. 3D primary tumor segmentation of arterial contrast CT scans was performed by trained investigators. Features were extracted using pyRadiomics 2.2.0 (n = 839) with gray value and voxel size normalization. For random forest (RF) model training, the cohort was randomly split into training (75%) and validation (25%) sets. Results: Multidimensional clustering of radiomic features by t-SNE analysis showed that metastatic and HMR tumors predominantly cluster together, while LMR tumors cluster separately. Consistent with this, there were no differentially regulated radiomic features (DR-features) between HMR and metastatic tumors. In contrast, we identified 26 DR-features (adjusted p-value < 0.05) between presumed-metastatic (n = 139, HMR and metastatic tumors) and LMR tumors, which were then used as input to a RF binary classifier. In the training set, the trained classifier discriminated between presumed-metastatic and LMR tumors with bootstrapped AUC = 0.81. In the validation set, the classifier discriminated subsets with AUC = 0.80. Conclusions: High-risk and metastatic tumors have similar radiomic properties, suggesting common biology driving metastasis in RCC. We propose a novel radiomic classifier that accurately distinguishes between presumed-metastatic and low-risk tumors. Further work will assess whether this tool can identify patients with micrometastatic disease at diagnosis, who may benefit from adjuvant therapy or closer, long-term surveillance.

Objectives: To develop an evidence-based intervention to prevent burnout in oncology doctors. Methods: A novel well-being intervention was developed and involved breathing and relaxation exercises, clinical debriefing, reflective practice and mindfulness. Resident doctors at a tertiary cancer centre were invited to attend weekly sessions facilitated by a clinical psychologist. Warwick-Edinburgh Mental Wellbeing Scale (WEMWBS) scores were collected at the start and end of placement. Results: Over 12 months, 28 resident doctors in inpatient oncology participated in our optional weekly well-being sessions (average 3–6 sessions per rotation). Baseline average and median WEMWBS were 51 (SD ±5.8) and 50.5 (range 41–62). At baseline, 82.12% (n=23/28) had average well-being scores. There was a statistically significant improvement in overall WEMWBS from 51.00 (SD ±5.80) to 54.57 (SD ±7.59) (p=0.0017). 57.14% (n=16/28) of participants had an increase in three or more points (range +4 to +15) in total WEMWBS; 7.14% (n=2/28) had a decrease in three or more points (range −10 to −10). All were either ‘satisfied’ (n=1/28) or ‘very satisfied’ (n=27/28) with the session facilitation. All found the sessions either ‘helpful’ (n=25/28) or ‘very helpful’ (n=3/28). Conclusions: In this pilot study, our novel well-being intervention preserved, and in some cases improved, mental well-being among resident doctors working in oncology.

Treatment options for malignant loculated pericardial effusions are limited and effusions often reaccumulate following surgical management. For posterior e

Background: CT-based radio-biomarkers could provide non-invasive insights into tumour biology to risk-stratify patients. One of the limitations is laborious manual segmentation of regions-of-interest (ROI). We present a deep learning auto-segmentation pipeline for radiomic analysis. Patients and Methods: 153 patients with resected stage 2A-3B non-small cell lung cancer (NSCLCs) had tumours segmented using nnU-Net with review by two clinicians. The nnU-Net was pretrained with anatomical priors in non-cancerous lungs and finetuned on NSCLCs. Three ROIs were segmented: intra-tumoural, peri-tumoural, and whole lung. 1967 features were extracted using PyRadiomics. Feature reproducibility was tested using segmentation perturbations. Features were selected using minimum-redundancy-maximum-relevance with Random Forest-recursive feature elimination nested in 500 bootstraps. Results: Auto-segmentation time was ∼36 seconds/series. Mean volumetric and surface Dice-Sørensen coefficient (DSC) scores were 0.84 (±0.28), and 0.79 (±0.34) respectively. DSC were significantly correlated with tumour shape (sphericity, diameter) and location (worse with chest wall adherence), but not batch effects (e.g. contrast, reconstruction kernel). 6.5% cases had ‘missed’ segmentations; 6.5% required major changes. Pre-training on anatomical priors resulted in better segmentations compared to training on tumour-labels alone ( p <0.001) and tumour with anatomical labels ( p <0.001). Most radiomic features were not reproducible following perturbations and resampling. Adding radiomic features, however, did not significantly improve the clinical model in predicting 2-year disease-free survival: AUCs 0.67 (95%CI 0.59-0.75) vs 0.63 (95%CI 0.54-0.71) respectively ( p =0.28). Conclusion: Our study demonstrates that integrating auto-segmentation into radio-biomarker discovery is feasible with high efficiency and accuracy. Whilst radiomic analysis show limited reproducibility, our auto-segmentation may allow more robust radio-biomarker analysis using deep learning features.