A systematic scoping review protocol to summarise and appraise the use of artificial intelligence in the analysis of digital videos of invasive general surgical procedures.

Background: Intraoperative video recordings are a valuable addition to operative written documentation. However, the review of these videos often requires surgical expertise and takes considerable time. While a large amount of work has been undertaken to understand the role of artificial intelligence (AI) in healthcare more generally, the application of these techniques to automate the analysis of surgical videos is currently unclear. In this systematic scoping review, we sought to give a contemporary overview of the use of AI research in the analysis of digital videos of invasive general surgical procedures. We will describe and summarise the study characteristics, purpose of the applications and stage of development, to ascertain how these techniques might be applied in future research and to identify gaps in current knowledge (e.g. uncertainties about the study methods). Methods: Systematic searches will be conducted in OVID Medline and Embase, using terms related to 'artificial intelligence', 'surgery' and 'video' to identify all potentially relevant studies published since 1st January 2012. All primary studies where AI has been applied to the analysis of videos (recorded by conventional digital cameras or laparoscopic or robotic-assisted technology) of general surgical procedures will be included. Data extraction will include study characteristics, governance, details of video datasets and AI models, measures of accuracy, validation and any reported limitations. Ethics and dissemination: No ethical approval is required as primary data will not be collected. The results will be disseminated at relevant conferences, on social media and published in a peer-reviewed journal.

Remote assessment of surgical site infection (SSI) using patient-taken wound images: Development and evaluation of a method for research and routine practice.

BACKGROUND/AIM: Clinical assessment of wounds for surgical site infection (SSI) after hospital discharge is challenging and resource intensive. Remote assessment using digital images may be feasible and expedite SSI diagnosis. Acceptable and accurate methods for this process are needed. This study developed and evaluated the feasibility, acceptability and usability of a method for patients to capture standardised wound images for remote wound assessment to detect SSI. MATERIALS AND METHODS: The work was conducted in two phases. Phase I involved: i) a review of literature to identify key components of photography relevant to taking wound images, ii) development of wound photography instructions for patients and a secure process for transmission of images using electronic survey software and iii) pre-testing of the photography instructions and processing method with a sample of 16 patients using cognitive interviews and observations. Phase II involved a prospective cohort study of 89 patients to evaluate the feasibility, acceptability and usability of the remote method following discharge from hospital after surgery. Quality of the images was assessed by three independent clinical reviewers. RESULTS: Some 21 key components for photographing wounds were identified from 11 documents. Of these, 16 were relevant to include in instructions for patients to photograph their wounds. Pre-testing and subsequent iterations improved understanding and ease of use of the instructions and the process for transmitting images. Fifty-two of 89 (58.4%) patients testing the method remotely took an image of their wound(s) and 46/52 (88.5%) successfully transmitted images. When it was possible to ascertain a reason for not taking/transmitting images, this was primarily health problems (n = 7) or lack of time/poor engagement with the study (n = 4) rather than problems relating to technology/competency (n = 2) or practical issues relating to the wound itself (n = 2). Eighty-seven (85.3%) of the 102 images received were evaluated to be of high quality and sufficient to remotely assess SSI by at least two independent reviewers. CONCLUSION: A simple, standardised and acceptable method for patients to take and transmit wound images suitable for remote assessment of SSI has been developed and tested and is now available for use in routine clinical care and research.

Managing surgical demand when needs outstrip resource: qualitative investigation of colorectal cancer surgery provision in the first wave of the COVID-19 pandemic.

BACKGROUND: At the onset of the COVID-19 pandemic, elective surgical provision was severely affected by the need for hospital reorganization to care for critically ill patients. In response, National Health Service (NHS) England issued national guidance proposing acceptable time intervals for postponing different types of surgical procedure. This study reports healthcare professionals' private accounts of the strategies adopted to manage the imbalance of demand and resource, using colorectal cancer surgery as a case study. METHODS: Twenty-seven semistructured interviews were conducted with healthcare professionals between June and November 2020. A key informant sampling approach was used, followed by snowballing to achieve maximum regional variation across the UK. Data were analysed thematically using the constant comparison approach. RESULTS: In the context of considerable resource constraint, surgical teams overcame challenges to continue elective cancer provision. They achieved this by pursuing a combination of strategies: relocating surgical services; prioritizing patients within and across surgical specialties; adapting patient treatment plans; and introducing changes to surgical team working practices. Despite national guidance, prioritization decisions were framed as complex, and the most challenging of the strategies to implement, both practically and emotionally. CONCLUSION: There is a need to better support surgeons tasked with prioritizing patients when capacity exceeds demand.

Protocol for a Global Burns Research Priority Setting Partnership to agree the most important unanswered questions in international burns care.

INTRODUCTION: Burns affect 11 million people globally and can result in long-term disability with substantial associated healthcare costs. There is limited research funding to support trials to provide evidence for clinical decision-making. Research prioritisation ensures that research focuses on the topics most important to stakeholders, addressing issues of research waste and evidence gaps. The aim of this project is to agree the global top 10 research priorities important to international patients, carers and clinicians from all income status countries. METHODS AND ANALYSIS: The Global Burns Research Priority Setting Partnership will use James Lind Alliance methods to establish the top 10 research priorities in global burns care. An initial international online multilingual survey will collect candidate research priorities from stakeholders. To increase equity in participation, the survey will also be available via the social media app WhatsApp. Additionally, interviews will be conducted. Data will be analysed to identify and collate research questions and to verify that the priorities are true clinical uncertainties. This list will then be ranked by stakeholders in order of importance via a second online survey. Finally, a consensus meeting will identify the top 10 research priorities. ETHICS AND DISSEMINATION: The University of Bristol Medical School Faculty Ethical Committee has approved this project. Research into burn care should be prioritised to ensure that funding is focused where most needed. This should be undertaken internationally, to ensure inclusion of the views of professionals and patients from lower income countries, where the incidence of thermal burns is highest. The involvement of the James Lind Alliance will ensure that the methodology is robust and that the patient voice is heard. The final top 10 priorities will be disseminated to funders, governments and researchers internationally to inform future global burns research.