Search

Objectives To assess the current state-of-the-art in deep learning methods applied to pre-operative radiologic staging of colorectal cancer lymph node metastasis. Specifically, by evaluating the data, methodology and validation of existing work, as well as the current use of explainable AI in this fast-moving domain.Design Scoping review.Data sources Academic databases MEDLINE, Embase, Scopus, IEEE Xplore, Web of Science and Google Scholar were searched with a date range of 1 January 2018 to 1 February 2024.Eligibility criteria Includes any English language research articles or conference papers published since 2018 which have applied deep learning methods for feature extraction and classification of colorectal cancer lymph nodes on pre-operative radiologic imaging.Data extraction and synthesis Key results and characteristics for each included study were extracted using a shared template. A narrative synthesis was then conducted to qualitatively integrate and interpret these findings.Results This scoping review covers 13 studies which met the inclusion criteria. The deep learning methods had an area under the curve score of 0.856 (0.796 to 0.916) for patient-level lymph node diagnosis and 0.904 (0.841 to 0.967) for individual lymph node assessment, given with a 95% confidence interval. Most studies have fundamental limitations including unrepresentative data, inadequate methodology, poor model validation and limited explainability techniques.Conclusions Deep learning methods have demonstrated the potential for accurately diagnosing colorectal cancer lymph nodes using pre-operative radiologic imaging. However, several methodological and validation flaws such as selection bias and lack of external validation make it difficult to trust the results. This review has uncovered a research gap for robust, representative and explainable deep learning methods that are end-to-end from automatic lymph node detection to the diagnosis of lymph node metastasis.

Abstract Background No residual disease (CC 0) following cytoreductive surgery is pivotal for the prognosis of women with advanced stage epithelial ovarian cancer (EOC). Improving CC 0 resection rates without increasing morbidity and no delay in subsequent chemotherapy favors a better outcome in these women. Prerequisites to facilitate this surgical paradigm shift and subsequent ramifications need to be addressed. This quality improvement study assessed 559 women with advanced EOC who had cytoreductive surgery between January 2014 and December 2019 in our tertiary referral centre. Following implementation of the Enhanced Recovery After Surgery (ERAS) pathway and prehabilitation protocols, the surgical management paradigm in advanced EOC patients shifted towards maximal surgical effort cytoreduction in 2016. Surgical outcome parameters before, during, and after this paradigm shift were compared. The primary outcome measure was residual disease (RD). The secondary outcome parameters were postoperative morbidity, operative time (OT), length of stay (LOS) and progression-free-survival (PFS). Results R0 resection rate in patients with advanced EOC increased from 57.3% to 74.4% after the paradigm shift in surgical management whilst peri-operative morbidity and delays in adjuvant chemotherapy were unchanged. The mean OT increased from 133 + 55 min to 197 + 85 min, and postoperative high dependency/intensive care unit (HDU/ICU) admissions increased from 8.1% to 33.1%. The subsequent mean LOS increased from 7.0 + 2.6 to 8.4 + 4.9 days. The median PFS was 33 months. There was no difference for PFS in the three time frames but a trend towards improvement was observed. Conclusions Improved CC 0 surgical cytoreduction rates without compromising morbidity in advanced EOC is achievable owing to the right conditions. Maximal effort cytoreductive surgery should solely be carried out in high output tertiary referral centres due to the associated substantial prerequisites and ramifications.

Introduction The empty pelvis syndrome is a significant source of morbidity following pelvic exenteration surgery. It remains poorly defined with research in this field being heterogeneous and of low quality. Furthermore, there has been minimal engagement with patient representatives following pelvic exenteration with respect to the empty pelvic syndrome. ‘PelvEx—Beating the empty pelvis syndrome’ aims to engage both patient representatives and healthcare professionals to achieve an international consensus on a core outcome set, pathophysiology and mitigation of the empty pelvis syndrome.Methods and analysis A modified-Delphi approach will be followed with a three-stage study design. First, statements will be longlisted using a recent systematic review, healthcare professional event, patient and public engagement, and Delphi piloting. Second, statements will be shortlisted using up to three rounds of online modified Delphi. Third, statements will be confirmed and instruments for measurable statements selected using a virtual patient-representative consensus meeting, and finally a face-to-face healthcare professional consensus meeting.Ethics and dissemination The University of Southampton Faculty of Medicine ethics committee has approved this protocol, which is registered as a study with the Core Outcome Measures in Effectiveness Trials Initiative. Publication of this study will increase the potential for comparative research to further understanding and prevent the empty pelvis syndrome.Trial registration number NCT05683795.

[This corrects the article DOI: 10.1371/journal.pone.0275025.].

Introduction Rectal cancer is common with a 60% 5-year survival rate. Treatment usually involves surgery with or without neoadjuvant chemoradiotherapy or adjuvant chemotherapy. Sphincter saving curative treatment can result in debilitating changes to bowel function known as low anterior resection syndrome (LARS). There are currently no clear guidelines on the management of LARS with only limited evidence for different treatment modalities.Methods and analysis Patients who have undergone an anterior resection for rectal cancer in the last 10 years will be approached for the study. The feasibility trial will take place in four centres with a 9-month recruitment window and 12 months follow-up period. The primary objective is to assess the feasibility of recruitment to the POLARiS trial which will be achieved through assessment of recruitment, retainment and follow-up rates as well as the prevalence of major LARS.Feasibility outcomes will be analysed descriptively through the estimation of proportions with confidence intervals. Longitudinal patient reported outcome measures will be analysed according to scoring manuals and presented descriptively with reporting graphically over time.Ethics and dissemination Ethical approval has been granted by Wales REC1; Reference 22/WA/0025. The feasibility study is in the process of set up. The results of the feasibility trial will feed into the design of an expanded, international trial.Trial registration number CT05319054.

The COVID-19 pandemic created an urgent need for high-quality rapid research. One clinical challenge was how to minimise the risk of transmission in the hospital setting. The CLEAN study conducted a rapid evaluation of the potential utility of a spray-based disinfectant in a hospital setting. The study was undertaken between December 2020 and March 2021 and involved the implementation of the spray in 10 different clinical areas in one UK teaching hospital. A mixed-methods approach was adopted (including observations, surveys, and qualitative interviews) informed by the theories for understanding the implementation of new healthcare technologies. The evaluation found that while the spray had a number of perceived benefits when added to existing disinfection processes, other factors limited its potential utility. These findings informed a number of recommendations for future adoption within hospital settings. This paper describes and reflects on the rapid methodology that allowed us to undertake the study and deliver results in a short space of time. We experienced a number of pressures during set-up and fieldwork due to the challenging conditions caused by the pandemic, and the methodological approach had to evolve throughout the study because of the changing clinical context. The involvement of clinicians from the research setting as full members of the research team was key to the rapid delivery of the research. They provided an essential link to the implementation environment, and their experiential knowledge of the setting added an important perspective to the analysis. Balancing their involvement with their clinical roles was challenging, however, as was coordinating a large and diverse team of interviewers in such a short space of time. Overall, the study highlighted the value of rapid research to inform urgent healthcare decisions in a pandemic. Although our experience suggests that conducting such research requires some practical and methodological trade-offs, we found that there were also numerous benefits of using rapid methods and identified various opportunities to ensure their robustness.

Defunctioning stomas (ileostomy and colostomy) may be used prior to commencement of neoadjuvant therapy in patients with locally advanced colon or rectal cancer, in order to prevent clinical large bowel obstruction caused by radiotherapy associated oedema or progression of disease in patients who are not obstructed. However, the exact rate of clinical obstruction in patients undergoing neoadjuvant therapy who do not receive a defunctioning stoma is not known. Furthermore, it is not clear which factors predispose patients to developing clinical large bowel obstruction. Given that defunctioning stomas are associated with post operative and intra-operative risks, it is not currently possible to tailor defunctioning stomas to patients who have the greatest risk of developing obstruction. This systematic review which is in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analysis statement (PRISMA), aims to define the role of defunctioning stomas in prevention of obstruction patients with locally advanced colon or rectal cancer while undergoing neoadjuvant therapy. Two researchers will perform the literature search which will include all published and "in process" articles published in the English language between 2002-2022 in the following databases: EMBASE (OVID), MEDLINE (EBSCO), CINHAL complete, Web of Science, Cochrane Central Registry of Controlled Trials, Clinical Trials Registry. The full text of the selected articles will be independently screened by two researchers against the inclusion criteria. Data will be extracted from each article regarding: study design, participants, type of intervention and outcomes. The effect size will be expressed in incidence rates and when appropriate in relative risk with 95% confidence intervals. If possible, we will perform a meta-analysis. Heterogeneity will be assessed using I2 statistics. We will pool the data extracted from the randomised controlled trials to perform a meta-analysis using the Review Manager 5 software (RevMan 5). The Grades of Recommendation, Assessment, Development and Evaluation (GRADE) system will be used to assess the certainty of the evidence.