Search

Simple Summary: Device-assisted enteroscopy is the only diagnostic and therapeutic exam capable of exploring the entire gastrointestinal tract. However, the diagnostic yield of this procedure is not sufficient enough to assure a cost-effective panendoscopy, and there is significant interobserver variability during the exam. Artificial intelligence tools have been proved to be beneficial in several areas of medicine, namely in Gastroenterology, with a strong image component. However, the development of deep learning models for application in device-assisted enteroscopy is still in an embryonic phase. The authors herein aimed to develop a multidevice convolutional neural network based on 338 exams performed in two renowned centers. The present model was able to accurately identify multiple clinically relevant lesions across the entire gastrointestinal tract, with an image processing time that favors its clinical applicability. The first worldwide panendoscopic model showed the potential of artificial intelligence in augmenting the accuracy and cost-effectiveness of device-assisted enteroscopy. Device-assisted enteroscopy (DAE) is capable of evaluating the entire gastrointestinal tract, identifying multiple lesions. Nevertheless, DAE's diagnostic yield is suboptimal. Convolutional neural networks (CNN) are multi-layer architecture artificial intelligence models suitable for image analysis, but there is a lack of studies about their application in DAE. Our group aimed to develop a multidevice CNN for panendoscopic detection of clinically relevant lesions during DAE. In total, 338 exams performed in two specialized centers were retrospectively evaluated, with 152 single-balloon enteroscopies (Fujifilm®, Porto, Portugal), 172 double-balloon enteroscopies (Olympus®, Porto, Portugal) and 14 motorized spiral enteroscopies (Olympus®, Porto, Portugal); then, 40,655 images were divided in a training dataset (90% of the images, n = 36,599) and testing dataset (10% of the images, n = 4066) used to evaluate the model. The CNN's output was compared to an expert consensus classification. The model was evaluated by its sensitivity, specificity, positive (PPV) and negative predictive values (NPV), accuracy and area under the precision recall curve (AUC-PR). The CNN had an 88.9% sensitivity, 98.9% specificity, 95.8% PPV, 97.1% NPV, 96.8% accuracy and an AUC-PR of 0.97. Our group developed the first multidevice CNN for panendoscopic detection of clinically relevant lesions during DAE. The development of accurate deep learning models is of utmost importance for increasing the diagnostic yield of DAE-based panendoscopy. [ABSTRACT FROM AUTHOR]

Background: Asymptomatic infection is the most common outcome of exposure to Leishmania parasites. In the Mediterranean region, where Leishmania infantum is endemic, studies on the prevalence of asymptomatic infection have often relied on serological testing in blood donors. In Spain, regional studies have shown seroprevalence in blood donors between 1 and 8%; in Portugal, values of 0 and 2% were suggested by two localized studies, in different populations. The purpose of this study was (i) to estimate the prevalence of asymptomatic Leishmania infection in blood donors in mainland Portugal, and (ii) to study the association between the detection of antibodies to Leishmania and sociodemographic factors, and also the knowledge, perceptions and practices (KPP) of the blood donors regarding leishmaniasis. Methods: A cross-sectional study targeted the population of people who donated blood in mainland Portugal. Participants, distributed proportionally by municipality and aged between 18 and 65 years, were selected randomly in 347 blood collection points between February and June 2022, and completed a sociodemographic and a KPP questionnaire. Detection of anti-Leishmania antibodies in serum was performed using an ELISA commercial kit. Individual KPP scores were calculated by adding grades defined for each question. Results: Globally, 201/3763 samples were positive. The estimated national true seroprevalence was 4.8% (95% CI 4.1–5.5%). The proportion of positive results was significantly different between NUTS (Nomenclature of Territorial Units for Statistics) regions. Models suggested that seropositivity was significantly higher in male sex, people older than 25 years, or residing in the Centro NUTS2 region, but not in dog owners nor people with lower KPP scores. Overall, 72.3% of participants had previously heard of leishmaniasis and, in multivariate analysis, a higher Knowledge score was associated with age 25–40 years, female sex, ownership of dogs, and higher education. Conclusions: Global estimated true seroprevalence (4.8%) was similar to previous regional studies in blood donors in neighboring Spain. Higher seroprevalence values in the NUTS2 Centro region were consistent with incidence data from humans and seroprevalence studies in dogs. On the other hand, the low values in the Alentejo and the high values in the northern subregions may be the result of geographical shifts in parasite circulation due to climate change and should prompt localized and integrated, vector, canine, and human research, following a One Health approach. [ABSTRACT FROM AUTHOR]

The present evidence-based guidelines are focused on the use of device-assisted enteroscopy in the management of small-bowel diseases. A panel of experts selected by the Spanish and Portuguese small-bowel study groups reviewed the available evidence focusing on the main indications of this technique, its role in the management algorithm of each indication, and its diagnostic and therapeutic yield. A set of recommendations was issued accordingly.