published version features the final layout of the paper including the volume, issue and page numbers. Link to publication General rightsCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.• Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal.If the publication is distributed under the terms of Article 25fa of the Dutch Copyright Act, indicated by the "Taverne" license above, please follow below link for the End User

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

No abstract

Background The optimal treatment for patients with locally recurrent rectal cancer (LRRC) is controversial. The aim of this study was to investigate different treatment strategies in two leading tertiary referral hospitals in Europe. Methods All patients who underwent curative surgery for LRRC between January 2003 and December 2017 in Catharina Hospital, Eindhoven, the Netherlands (CHE), or Karolinska University Hospital, Stockholm, Sweden (KAR), were studied retrospectively. Available MRIs were reviewed to obtain a uniform staging for optimal comparison of both cohorts. The main outcomes studied were overall survival (OS), local re-recurrence-free survival (LRFS), and metastasis-free survival (MFS). Results In total, 377 patients were included, of whom 126 and 251 patients came from KAR and CHE respectively. At 5 years, the LRFS rate was 62.3 per cent in KAR versus 42.3 per cent in CHE (P = 0.017), whereas OS and MFS were similar. A clear surgical resection margin (R0) was the strongest prognostic factor for survival, with a hazard ratio of 2.23 (95 per cent c.i. 1.74 to 2.86; P < 0.001), 3.96 (2.87 to 5.47; P < 0.001), and 2.00 (1.48 to 2.69; P < 0.001) for OS, LRFS, and MFS respectively. KAR performed more extensive operations, resulting in more R0 resections than in CHE (76.2 versus 61.4 per cent; P = 0.004), whereas CHE relied more on neoadjuvant treatment and intraoperative radiotherapy, to reduce the morbidity of multivisceral resections (P < 0.001). Conclusion In radiotherapy-naive patients, neoadjuvant full-course chemoradiation confers the best oncological outcome. However, neoadjuvant therapy does not diminish the need for extended radical surgery to increase R0 resection rates.

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.