Between 5% and 10% of patients with rectal cancer present with locally advanced rectal cancer (LARC), and 10% of rectal cancers recur after surgery, of which half are limited to locoregional disease only (locally recurrent rectal cancer). Exenterative surgery offers the best long-term outcomes for patients with LARC and locally recurrent rectal cancer so long as a complete (R0) resection is achieved. Accurate preoperative multimodal staging is crucial in assessing the potential operability of advanced rectal tumors, and resectability may be enhanced with neoadjuvant therapies. Unfortunately, surgical options are limited when the tumor involves the lateral pelvic sidewall or high sacrum due to the technical challenges of achieving histological clearance, and must be balanced against the high morbidity associated with resection of the bony pelvis and significant lymphovascular structures. This group of patients is usually treated palliatively and subsequently survival is poor, which has led surgeons to seek innovative new solutions, as well as revisit previously discarded radical approaches. A small number of centers are pioneering new techniques for resection of beyond-total mesorectal excision tumors, including en bloc resections of the sciatic notch and composite resections of the first two sacral vertebrae. Despite limited experience, these new techniques offer the potential for radical treatment of previously inoperable tumors. This narrative review sets out the challenges facing the management of LARCs and discusses evolving management options.
Aim We aim to compare machine learning with neural network performance in predicting R0 resection (R0), length of stay > 14 days (LOS), major complication rates at 30 days postoperatively (COMP) and survival greater than 1 year (SURV) for patients having pelvic exenteration for locally advanced and recurrent rectal cancer. Method A deep learning computer was built and the programming environment was established. The PelvEx Collaborative database was used which contains anonymized data on patients who underwent pelvic exenteration for locally advanced or locally recurrent colorectal cancer between 2004 and 2014. Logistic regression, a support vector machine and an artificial neural network (ANN) were trained. Twenty per cent of the data were used as a test set for calculating prediction accuracy for R0, LOS, COMP and SURV. Model performance was measured by plotting receiver operating characteristic (ROC) curves and calculating the area under the ROC curve (AUROC). Results Machine learning models and ANNs were trained on 1147 cases. The AUROC for all outcome predictions ranged from 0.608 to 0.793 indicating modest to moderate predictive ability. The models performed best at predicting LOS > 14 days with an AUROC of 0.793 using preoperative and operative data. Visualized logistic regression model weights indicate a varying impact of variables on the outcome in question. Conclusion This paper highlights the potential for predictive modelling of large international databases. Current data allow moderate predictive ability of both complex ANNs and more classic methods.
Background A resection with clear margins (R0 resection) is the most important prognostic factor in patients with locally recurrent rectal cancer (LRRC). However, this is achieved in only 60 per cent of patients. The aim of this study is to investigate whether the addition of induction chemotherapy to neoadjuvant chemo(re)irradiation improves the R0 resection rate in LRRC. Methods This multicentre, international, open-label, phase III, parallel-arms study will enrol 364 patients with resectable LRRC after previous partial or total mesorectal resection without synchronous distant metastases or recent chemo- and/or radiotherapy treatment. Patients will be randomized to receive either induction chemotherapy (three 3-week cycles of CAPOX (capecitabine, oxaliplatin), four 2-week cycles of FOLFOX (5-fluorouracil, leucovorin, oxaliplatin) or FOLFORI (5-fluorouracil, leucovorin, irinotecan)) followed by neoadjuvant chemoradiotherapy and surgery (experimental arm) or neoadjuvant chemoradiotherapy and surgery alone (control arm). Tumours will be restaged using MRI and, in the experimental arm, a further cycle of CAPOX or two cycles of FOLFOX/FOLFIRI will be administered before chemoradiotherapy in case of stable or responsive disease. The radiotherapy dose will be 25 × 2.0 Gy or 28 × 1.8 Gy in radiotherapy-naive patients, and 15 × 2.0 Gy in previously irradiated patients. The concomitant chemotherapy agent will be capecitabine administered twice daily at a dose of 825 mg/m2 on radiotherapy days. The primary endpoint of the study is the R0 resection rate. Secondary endpoints are long-term oncological outcomes, radiological and pathological response, toxicity, postoperative complications, costs, and quality of life. Discussion This trial protocol describes the PelvEx II study. PelvEx II, designed as a multicentre, open-label, phase III, parallel-arms study, is the first randomized study to compare induction chemotherapy followed by neoadjuvant chemo(re)irradiation and surgery with neoadjuvant chemo(re)irradiation and surgery alone in patients with locally recurrent rectal cancer, with the aim of improving the number of R0 resections.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.