Preventing iatrogenic ureteral injury in colorectal surgery: a comprehensive and systematic review of the last 2 decades of literature and future perspectives.

Iatrogenic ureteral injury (IUI) during colorectal surgery is a rare complication but related to a serious burden of morbidity. This comprehensive and systematic review aims to provide a critical overview of the most recent literature about IUI prevention techniques in colorectal surgery. We performed a comprehensive and systematic review of studies published from 2000 to 2022 and assessed the use of techniques for ureteral injury prevention and intraoperative localization. 26 publications were included, divided into stent-based (prophylactic/lighted ureteral stent and near-infrared fluorescent ureteral catheter [PUS/LUS/NIRFUC]) and fluorescent dye (FD) groups. Costs, the percentage and number of IUIs detected, reported limitations, complication rates and other outcome points were compared. The IUI incidence rate ranged from 0 to 1.9% (mean 0.5%) and 0 to 1.2% (mean 0.3%) in the PUS/LUS/NIRFUC and FD groups, respectively. The acute kidney injury (AKI) and urinary tact infection (UTI) incidence rate ranged from 0.4 to 32.6% and 0 to 17.3%, respectively, in the PUS/LUS/NIRFUC group and 0-15% and 0-6.3%, respectively, in the FD group. Many other complications were also compared and descriptively analyzed (length-of-stay, mortality, etc.). These techniques appear to be feasible and safe in select patients with a high risk of IUI, but the delineation of reliable guidelines for preventing IUI will require more randomized controlled trials.

Endoscopy-based IBD identification by a quantized deep learning pipeline.

BACKGROUND: Discrimination between patients affected by inflammatory bowel diseases and healthy controls on the basis of endoscopic imaging is an challenging problem for machine learning models. Such task is used here as the testbed for a novel deep learning classification pipeline, powered by a set of solutions enhancing characterising elements such as reproducibility, interpretability, reduced computational workload, bias-free modeling and careful image preprocessing. RESULTS: First, an automatic preprocessing procedure is devised, aimed to remove artifacts from clinical data, feeding then the resulting images to an aggregated per-patient model to mimic the clinicians decision process. The predictions are based on multiple snapshots obtained through resampling, reducing the risk of misleading outcomes by removing the low confidence predictions. Each patient's outcome is explained by returning the images the prediction is based upon, supporting clinicians in verifying diagnoses without the need for evaluating the full set of endoscopic images. As a major theoretical contribution, quantization is employed to reduce the complexity and the computational cost of the model, allowing its deployment on small power devices with an almost negligible 3% performance degradation. Such quantization procedure holds relevance not only in the context of per-patient models but also for assessing its feasibility in providing real-time support to clinicians even in low-resources environments. The pipeline is demonstrated on a private dataset of endoscopic images of 758 IBD patients and 601 healthy controls, achieving Matthews Correlation Coefficient 0.9 as top performance on test set. CONCLUSION: We highlighted how a comprehensive pre-processing pipeline plays a crucial role in identifying and removing artifacts from data, solving one of the principal challenges encountered when working with clinical data. Furthermore, we constructively showed how it is possible to emulate clinicians decision process and how it offers significant advantages, particularly in terms of explainability and trust within the healthcare context. Last but not least, we proved that quantization can be a useful tool to reduce the time and resources consumption with an acceptable degradation of the model performs. The quantization study proposed in this work points up the potential development of real-time quantized algorithms as valuable tools to support clinicians during endoscopy procedures.

Automatically detecting Crohn's disease and Ulcerative Colitis from endoscopic imaging.

BACKGROUND: The SI-CURA project (Soluzioni Innovative per la gestione del paziente e il follow up terapeutico della Colite UlceRosA) is an Italian initiative aimed at the development of artificial intelligence solutions to discriminate pathologies of different nature, including inflammatory bowel disease (IBD), namely Ulcerative Colitis (UC) and Crohn's disease (CD), based on endoscopic imaging of patients (P) and healthy controls (N). METHODS: In this study we develop a deep learning (DL) prototype to identify disease patterns through three binary classification tasks, namely (1) discriminating positive (pathological) samples from negative (healthy) samples (P vs N); (2) discrimination between Ulcerative Colitis and Crohn's Disease samples (UC vs CD) and, (3) discrimination between Ulcerative Colitis and negative (healthy) samples (UC vs N). RESULTS: The model derived from our approach achieves a high performance of Matthews correlation coefficient (MCC) > 0.9 on the test set for P versus N and UC versus N, and MCC > 0.6 on the test set for UC versus CD. CONCLUSION: Our DL model effectively discriminates between pathological and negative samples, as well as between IBD subgroups, providing further evidence of its potential as a decision support tool for endoscopy-based diagnosis.

Enhancing self-resources in patients with chronic diseases: development and initial validation of the Disease and Care Management Score.

INTRODUCTION: Despite the importance of the assessment in the primary care of the self-resources among patients with chronic diseases, there is not available a measurement that allows this kind of comprehensive assessment. For this reason, the aim of this study was to develop a multi-dimensional score to determine the level of self-resources in chronic patients, describing its initial validation through face and content validity. The developed score was labelled as Disease and Care Management Score. METHODS: We performed a methodological study, encompassing two main phases. The first phase was aimed to develop the Disease and Care Management score, choosing the most suitable measurement to assess each pre-identified determinant of wellbeing in chronic patients. The second phase was aimed to determine the Disease and Care Management score face and content validity through the views of 20 experts. RESULTS: Disease and Care Management score shows evidence of face and content validity. All the obtained quantitative content validity indices (i.e. Content Validity Ratio, Content Validity Indices) were higher than 0,70, showing the pertinence and the adequacy of each pre-identified measure to compute Disease and Care Management score. CONCLUSION: Disease and Care Management score has the potential of addressing the health coaching interventions in primary care for chronic patients. Future research should show its predictive performance, as well as the cut-off to discriminate patients.