Machine learning models to predict surgical case duration compared to current industry standards: scoping review.

BACKGROUND: Surgical waiting lists have risen dramatically across the UK as a result of the COVID-19 pandemic. The effective use of operating theatres by optimal scheduling could help mitigate this, but this requires accurate case duration predictions. Current standards for predicting the duration of surgery are inaccurate. Artificial intelligence (AI) offers the potential for greater accuracy in predicting surgical case duration. This study aimed to investigate whether there is evidence to support that AI is more accurate than current industry standards at predicting surgical case duration, with a secondary aim of analysing whether the implementation of the models used produced efficiency savings. METHOD: PubMed, Embase, and MEDLINE libraries were searched through to July 2023 to identify appropriate articles. PRISMA extension for scoping reviews and the Arksey and O'Malley framework were followed. Study quality was assessed using a modified version of the reporting guidelines for surgical AI papers by Farrow et al. Algorithm performance was reported using evaluation metrics. RESULTS: The search identified 2593 articles: 14 were suitable for inclusion and 13 reported on the accuracy of AI algorithms against industry standards, with seven demonstrating a statistically significant improvement in prediction accuracy (P < 0.05). The larger studies demonstrated the superiority of neural networks over other machine learning techniques. Efficiency savings were identified in a RCT. Significant methodological limitations were identified across most studies. CONCLUSION: The studies suggest that machine learning and deep learning models are more accurate at predicting the duration of surgery; however, further research is required to determine the best way to implement this technology.

Microbial Community Composition in Explanted Cystic Fibrosis and Control Donor Lungs.

To date, investigations of the microbiota in the lungs of people with Cystic Fibrosis (PWCF) have primarily focused on microbial community composition in luminal mucus, with fewer studies observing the microbiota in tissue samples from explanted lung tissue. Here, we analysed both tissue and airway luminal mucus samples extracted from whole explanted lungs of PWCF and unused donor lungs. We determined if the lung microbiota in end-stage CF varied within and between patients, was spatially heterogeneous and related to localized structural damage. Microbial community composition was determined by Illumina MiSeq sequencing and related to the CF-Computed Tomography (CT) score and features of end-stage lung disease on micro-CT. Ninety-eight CF tissue (n=11 patients), 20 CF luminal mucus (n=8 patients) and 33 donor tissue (n=4 patients) samples were analysed. Additionally, we compared 20 paired CF tissue and luminal mucus samples that enabled a direct "geographical" comparison of the microbiota in these two niches. Significant differences in microbial communities were apparent between the 3 groups. However, overlap between the three groups, particularly between CF and donor tissue and CF tissue and CF luminal mucus was also observed. Microbial diversity was lower in CF luminal mucus compared to CF tissue, with dominance higher in luminal mucus. For both CF and donor tissue, intra- and inter-patient variability in ecological parameters was observed. No relationships were observed between ecological parameters and CF-CT score, or features of end-stage lung disease. The end-stage CF lung is characterised by a low diversity microbiota, differing within and between individuals. No clear relationship was observed between regional microbiota variation and structural lung damage.