Advancements in biliopancreatic endoscopy: a comprehensive review of artificial intelligence in EUS and ERCP.

The development and implementation of artificial intelligence (AI), particularly deep learning (DL) models, has generated significant interest across various fields of gastroenterology. While research in luminal endoscopy has seen rapid translation to clinical practice with approved AI devices, its potential extends far beyond, offering promising benefits for biliopancreatic endoscopy like optical characterization of strictures during cholangioscopy or detection and classification of pancreatic lesions during diagnostic endoscopic ultrasound (EUS). This narrative review provides an up-to-date of the latest literature and available studies in this field. Serving as a comprehensive guide to the current landscape of AI in biliopancreatic endoscopy, emphasizing technological advancements, main applications, ethical considerations, and future directions for research and clinical implementation.

The Natural History of Patients With Pre-Existing and De Novo Inflammatory Bowel Disease After Solid Organ Transplantation: EITOS Study of GETECCU.

BACKGROUND: Limited data are available on the outcome of inflammatory bowel disease (IBD) in patients with solid organ transplantation (SOT). We describe the natural history of pre-existing IBD and de novo IBD after SOT. METHODS: This was a retrospective, multicenter study that included patients with pre-existing IBD at the time of SOT and patients with de novo IBD after SOT. The primary outcome was IBD progression, defined by escalation of medical treatment, surgical therapy, or hospitalization due to refractory IBD. Risk factors were identified using multivariate Cox proportional hazard analysis. RESULTS: A total of 177 patients (106 pre-existing IBD and 71 de novo IBD) were included. Most patients with pre-existing IBD (92.5%) were in remission before SOT. During follow-up, 32% of patients with pre-existing IBD had disease progression, with a median time between SOT and IBD progression of 2.2 (interquartile range, 1.3-4.6) years. In the de novo cohort, 55% of patients had disease progression with a median time to flare of 1.9 (interquartile range, 0.8-3.9) years after diagnosis. In the pre-existing IBD cohort, active IBD at the time of SOT (hazard ratio, 1.80; 95% confidence interval, 1.14-2.84; P = .012) and the presence of extraintestinal manifestations (hazard ratio, 3.10; 95% confidence interval, 1.47-6.54; P = .003) were predictive factors for IBD progression. CONCLUSIONS: One-third of patients with pre-existing IBD and about half of patients with de novo IBD have disease progression after SOT. Active IBD at the time of SOT and the presence of extraintestinal manifestations were identified as risk factors for IBD progression.

Design and biopharmaceutical preclinical characterisation of a new thermosensitive hydrogel for the removal of gastric polyps.

BACKGROUND AND AIMS: Submucosal injection agents are widely used solutions in gastric polyp resection techniques. Currently, many different solutions are used in clinical practice, but most are not authorised for this use or are not biopharmaceutical characterised. The objective of this multidisciplinary work is to test the efficacy of a novel thermosensitive hydrogel designed specifically for this indication. METHODS: A mixture design of various components (Pluronic®, hyaluronic acid and sodium alginate) was carried out to select the combination with optimal properties for this use. Three final thermosensitive hydrogels were selected on which biopharmaceutical characterisation was performed and stability and biocompatibility were analysed. Efficacy in maintaining elevation was tested ex vivo on pig mucosa and in vivo in pigs RESULTS: The mixture design allowed selection of the ideal combinations of agents for the characteristics sought. The thermosensitive hydrogels studied showed high values of hardness and viscosity at 37 °C, maintaining good syringeability. One of them demonstrated superiority in maintaining polyp elevation in the ex vivo assay and non-inferiority in the in vivo assay. CONCLUSION: The thermosensitive hydrogel specifically designed for this use is promising both for its biopharmaceutical characteristics and for its demonstrated efficacy. This study lays the foundation for evaluating the hydrogel in humans.

Connected Elbow Exoskeleton System for Rehabilitation Training Based on Virtual Reality and Context-Aware.

Traditional physiotherapy rehabilitation systems are evolving into more advanced systems based on exoskeleton systems and Virtual Reality (VR) environments that enhance and improve rehabilitation techniques and physical exercise. In addition, due to current connected systems and paradigms such as the Internet of Things (IoT) or Ambient Intelligent (AmI) systems, it is possible to design and develop advanced, effective, and low-cost medical tools that patients may have in their homes. This article presents a low-cost exoskeleton for the elbow that is connected to a Context-Aware architecture and thanks to a VR system the patient can perform rehabilitation exercises in an interactive way. The integration of virtual reality technology in rehabilitation exercises provides an intensive, repetitive and task-oriented capacity to improve patient motivation and reduce work on medical professionals. One of the system highlights is the intelligent ability to generate new exercises, monitor the exercises performed by users in search of progress or possible problems and the dynamic modification of the exercises characteristics. The platform also allows the incorporation of commercial medical sensors capable of collecting valuable information for greater accuracy in the diagnosis and evolution of patients. A case study with real patients with promising results has been carried out.

Pancreatic exocrine insufficiency and cardiovascular risk in patients with chronic pancreatitis: A prospective, longitudinal cohort study.

BACKGROUND AND AIM: Previous studies have suggested that chronic pancreatitis (CP) is associated with increased risk of cardiovascular (CV) disease independently of other major risk factors. We evaluated the risk of CV events in a well-phenotyped cohort of patients with CP and its association with pancreatic exocrine insufficiency (PEI) among other CV risk factors. METHODS: This was a prospective, longitudinal cohort study of patients with CP, followed up at the Pancreas Unit of the University Hospital of Santiago de Compostela, Spain. RESULTS: Four hundred thirty patients were included (mean 47.8 ± 14.4 years of age, 79.1% male). Mean follow-up was 8.6 ± 4.6 years. CP etiology was toxic (alcohol and/or smoking) in 290 patients (67.4%). PEI and pancreatogenic diabetes mellitus (DM) were present in 29.3% and 29.5% of the patients, respectively. A total of 45 CV events was recorded (10.5%); 21 patients had a major CV event (stroke or myocardial infarction) and 27 developed clinically relevant peripheral arterial disease. A higher incidence of CV events was recorded in patients with PEI than in those without (incidence rate ratio 3.67, 95% confidence interval [CI] 1.92-7.24; P < 0.001). In the multivariate analysis, PEI without DM (OR 4.96; 95% CI 1.68 to 14.65), coexistence of PEI and DM (OR 6.54; 95% CI 2.71 to 15.77), arterial hypertension (OR 3.40; 95% CI 1.50 to 7.72), and smoking (OR 2.91, 95% CI 1.07 to 7.97) were independently associated with increased CV risk. CONCLUSIONS: Together with known major CV risk factors like smoking and hypertension, PEI is significantly associated with the risk of CV events in patients with CP.

Endoscopic ultrasound cytologic brushing vs endoscopic ultrasound - fine needle aspiration for cytological diagnosis of cystic pancreatic lesions. A multicenter, randomized open-label trial.

INTRODUCTION: the incidence of cystic pancreatic lesions (CPL) in the asymptomatic population is increasing. Achieving a preoperative diagnosis of CPL still remains a challenge. OBJECTIVES: to evaluate the diagnostic accuracy of the cytological diagnosis of CPL from samples obtained by cytology brush versus standard endoscopic ultrasound fine needle aspiration (EUS-FNA). METHODS: a multicenter, randomized, open-label trial was performed of EUS-cytology brush (EUS-EB) versus EUS-FNA for the cytological diagnosis of CPL. Patients that underwent EUS-FNA with a CPL > 15 mm were included and randomized into two groups: group I, EUS-EB; group II, EUS-FNA. The final diagnosis was based on the histological evaluation of surgical specimens and clinical parameters, imaging and a five year follow-up in non-operated patients. The main outcome was the diagnostic accuracy of both methods. Secondary outcomes were the diagnostic adequacy of specimens and the rate of adverse events. Data were compared using the Chi-squared test. An intention to treat (ITT) and per-protocol (PP) analysis were performed. RESULTS: sixty-five patients were included in the study, 31 in group I and 34 in group II. Three patients initially randomized to group I were changed to group II as it was impossible to obtain a sample using the brush. The mean size of the CPL was 28.2 mm (range 16-60 mm). The diagnostic accuracy of EUS-EB was not superior to EUS-FNA, neither in the ITT nor the PP analysis (44.8% vs 41.1%, p = 0.77 and 38.4% vs 45.9%, p = 0.55). CONCLUSIONS: EUS-EB does not improve the diagnostic accuracy of CPL in comparison with EUS-FNA.

Morphological and functional changes of chronic pancreatitis in patients with dyspepsia: A prospective, observational, cross-sectional study.

OBJECTIVE: Whether chronic pancreatitis (CP) may present with dyspepsia is controversial. We aimed at evaluating the frequency and risk factors of changes of CP in patients presenting with epigastric pain syndrome (EPS)-like symptoms. DESIGN: A prospective, observational, cross-sectional study was carried out in patients with EPS-like symptoms. Patients underwent endoscopic ultrasound (EUS) evaluation of the pancreas, and changes of CP were defined as the presence of five or more EUS criteria of the disease. In patients with 3 or 4 EUS criteria, magnetic resonance dynamic evaluation of the pancreas (MRI/sMRCP) and endoscopic pancreatic function test (ePFT) were carried out to confirm or exclude the presence of changes of CP. A multivariate logistic regression analysis was performed to evaluate factors associated with CP findings, and results are shown as odds ratio (OR) and 95% confidence interval (CI). RESULTS: 213 patients were included. Changes of CP were confirmed by EUS (≥5 criteria) in 18 patients (8.4%). Thirty-four patients had 3-4 EUS criteria, and changes of CP were confirmed in 27 of them by MRI/sMRCP and ePFT (12.7%). Morphological and functional findings of CP were then present in 45 patients (21.1%). Male gender (OR 2.97; 95%CI 1.39-6.37) and alcohol and tobacco consumption (OR 6.56; 95%CI 1.97-21.85) were associated with the presence of changes of CP. CONCLUSION: Morphological and functional changes of CP are frequent in patients with EPS-like symptoms. Whether these pancreatic changes explain EPS-like symptoms requires further investigation.

A Context-Aware Indoor Air Quality System for Sudden Infant Death Syndrome Prevention.

Context-aware monitoring systems designed for e-Health solutions and ambient assisted living (AAL) play an important role in today's personalized health-care services. The majority of these systems are intended for the monitoring of patients' vital signs by means of bio-sensors. At present, there are very few systems that monitor environmental conditions and air quality in the homes of users. A home's environmental conditions can have a significant influence on the state of the health of its residents. Monitoring the environment is the key to preventing possible diseases caused by conditions that do not favor health. This paper presents a context-aware system that monitors air quality to prevent a specific health problem at home. The aim of this system is to reduce the incidence of the Sudden Infant Death Syndrome, which is triggered mainly by environmental factors. In the conducted case study, the system monitored the state of the neonate and the quality of air while it was asleep. The designed proposal is characterized by its low cost and non-intrusive nature. The results are promising.

Increasing the Intensity over Time of an Electric-Assist Bike Based on the User and Route: The Bike Becomes the Gym.

Nowadays, many citizens have busy days that make finding time for physical activity difficult. Thus, it is important to provide citizens with tools that allow them to introduce physical activity into their lives as part of the day's routine. This article proposes an app for an electric pedal-assist-system (PAS) bicycle that increases the pedaling intensity so the bicyclist can achieve higher and higher levels of physical activity. The app includes personalized assist levels that have been adapted to the user's strength/ability and a profile of the route, segmented according to its slopes. Additionally, a social component motivates interaction and competition between users based on a scoring system that shows the level of their performances. To test the training module, a case study in three different European countries lasted four months and included nine people who traveled 551 routes. The electric PAS bicycle with the app that increases intensity of physical activity shows promise for increasing levels of physical activity as a regular part of the day.

Architecture to Embed Software Agents in Resource Constrained Internet of Things Devices.

Sensing systems in combination with treatment tools and intelligent information management are the basis on which the cities and urban environments of the future will be built. Progress in the research and development of these new and intelligent scenarios is essential to achieve the objectives of efficiency, integration, sustainability, and quality of life for people who live in cities. To achieve these objectives, it is essential to investigate the development of cheaper, more accurate, and smarter hardware devices, which will form the basis of the intelligent environments of the future. This article focuses on an approach based on intelligent multi-agent systems that are integrated into basic hardware devices for the Internet of Things (IoT). A multi-agent architecture is proposed for the fast, efficient, and intelligent management of the generated data. A layer of services adapted to the needs of the new intelligent environments is built on this architecture. With the aim of validating this architecture, a case study based on electric vehicles of the e-bike type is proposed.

Multi-Sensor Information Fusion for Optimizing Electric Bicycle Routes Using a Swarm Intelligence Algorithm.

The use of electric bikes (e-bikes) has grown in popularity, especially in large cities where overcrowding and traffic congestion are common. This paper proposes an intelligent engine management system for e-bikes which uses the information collected from sensors to optimize battery energy and time. The intelligent engine management system consists of a built-in network of sensors in the e-bike, which is used for multi-sensor data fusion; the collected data is analysed and fused and on the basis of this information the system can provide the user with optimal and personalized assistance. The user is given recommendations related to battery consumption, sensors, and other parameters associated with the route travelled, such as duration, speed, or variation in altitude. To provide a user with these recommendations, artificial neural networks are used to estimate speed and consumption for each of the segments of a route. These estimates are incorporated into evolutionary algorithms in order to make the optimizations. A comparative analysis of the results obtained has been conducted for when routes were travelled with and without the optimization system. From the experiments, it is evident that the use of an engine management system results in significant energy and time savings. Moreover, user satisfaction increases as the level of assistance adapts to user behavior and the characteristics of the route.

Accuracy of endoscopic ultrasound-guided tissue acquisition in the evaluation of lymph nodes enlargement in the absence of on-site pathologist.

AIM: To evaluate factors that influence the diagnostic accuracy of endoscopic ultrasound (EUS)-guided tissue acquisition for lymph node enlargement in the absence of an on-site pathologist. METHODS: A retrospective analysis of patients who underwent EUS-guided tissue acquisition for the pathological diagnosis of lymph node enlargement between April 2012 and June 2015 is reported. Tissue acquisition was performed with both cytology and biopsy needles of different calibers. The variables evaluated were lymph node location and size, number of passes and type of needle used. Final diagnosis was based on surgical histopathology or, in non-operated cases, on EUS-guided tissue acquisition and imaging assessment with a minimum clinical follow-up of 6 mo. RESULTS: During the study period, 168 lymph nodes with a median size of 20.3 mm (range 12.5-27) were sampled from 152 patients. Ninety lymph nodes (53.6%) were located at mediastinum, and 105 (62.5%) were acquired with biopsy needles. The final diagnosis was benign/reactive origin in 87 cases (51.8%), malignant in 65 cases (38.7%), and lymphoma in 16 cases (9.5%). The sensitivity, specificity, positive predictive value and negative predictive value for the detection of malignancy were 74.1%, 100%, 100% and 80.6%, respectively. The overall accuracy was 87.5% (95%CI: 81.7-91.7). No variables were independently associated with a correct final diagnosis according to the multivariate analysis. CONCLUSION: EUS-guided tissue acquisition is a highly accurate technique for assessing lymph node enlargement. None of the variables evaluated were associated with diagnostic accuracy.

Evaluation of the Risk of Relapse in Ulcerative Colitis According to the Degree of Mucosal Healing (Mayo 0 vs 1): A Longitudinal Cohort Study.

BACKGROUND AND AIMS: Mucosal healing in ulcerative colitis (UC) has become a common endpoint in most clinical trials and a relevant therapeutic goal in clinical practice. Despite important differences between endoscopic Mayo scores 0 and 1, both scores are considered as mucosal healing in most important trials. The aim of the present study was to evaluate the risk of relapse in UC patients according to the degree of mucosal healing (endoscopic Mayo scores of 0 and 1). METHODS: A prospective longitudinal cohort study was designed. All UC patients who presented with mucosal healing at colonoscopy were consecutively included. Mucosal healing was defined as an endoscopic Mayo score of 0 or 1. Clinical relapse was defined as the need for therapy to induce remission, any treatment escalation, hospitalization or colectomy. All clinical relapses were evaluated at months 6 and 12 after study entry. Results were subjected to unconditional stepwise logistic and Kaplan-Meier regression analysis. RESULTS: One hundred and eighty-seven consecutive UC patients (126 [67.3%] with Mayo score 0 and 61 [32.7%] with Mayo score 1) were included. Of patients with Mayo scores 0 and 1, 9.4 and 36.6% respectively presented a relapse during the first 6 months of follow-up (p < 0.001). The only factor independently associated with UC relapses in the multivariate analysis was an endoscopic Mayo score of 1 (odds ratio 6.27, 95% confidence interval 2.73-14.40, p < 0.001). CONCLUSIONS: Patients with an endoscopic Mayo score of 1 have a higher risk of relapse than those with a score of 0. The concept of mucosal healing should be limited to patients with an endoscopic Mayo score of 0.