Artificial intelligence (AI) is an epoch-making technology, among which the 2 most advanced parts are machine learning and deep learning algorithms that have been further developed by machine learning, and it has been partially applied to assist EUS diagnosis. AI-assisted EUS diagnosis has been reported to have great value in the diagnosis of pancreatic tumors and chronic pancreatitis, gastrointestinal stromal tumors, esophageal early cancer, biliary tract, and liver lesions. The application of AI in EUS diagnosis still has some urgent problems to be solved. First, the development of sensitive AI diagnostic tools requires a large amount of high-quality training data. Second, there is overfitting and bias in the current AI algorithms, leading to poor diagnostic reliability. Third, the value of AI still needs to be determined in prospective studies. Fourth, the ethical risks of AI need to be considered and avoided.

UNASSIGNED: Large Language Models (LLMs) play a crucial role in clinical information processing, showcasing robust generalization across diverse language tasks. However, existing LLMs, despite their significance, lack optimization for clinical applications, presenting challenges in terms of illusions and interpretability. The Retrieval-Augmented Generation (RAG) model addresses these issues by providing sources for answer generation, thereby reducing errors. This study explores the application of RAG technology in clinical gastroenterology to enhance knowledge generation on gastrointestinal diseases.
UNASSIGNED: We fine-tuned the embedding model using a corpus consisting of 25 guidelines on gastrointestinal diseases. The fine-tuned model exhibited an 18% improvement in hit rate compared to its base model, gte-base-zh. Moreover, it outperformed OpenAI\'s Embedding model by 20%. Employing the RAG framework with the llama-index, we developed a Chinese gastroenterology chatbot named \"GastroBot,\" which significantly improves answer accuracy and contextual relevance, minimizing errors and the risk of disseminating misleading information.
UNASSIGNED: When evaluating GastroBot using the RAGAS framework, we observed a context recall rate of 95%. The faithfulness to the source, stands at 93.73%. The relevance of answers exhibits a strong correlation, reaching 92.28%. These findings highlight the effectiveness of GastroBot in providing accurate and contextually relevant information about gastrointestinal diseases. During manual assessment of GastroBot, in comparison with other models, our GastroBot model delivers a substantial amount of valuable knowledge while ensuring the completeness and consistency of the results.
UNASSIGNED: Research findings suggest that incorporating the RAG method into clinical gastroenterology can enhance the accuracy and reliability of large language models. Serving as a practical implementation of this method, GastroBot has demonstrated significant enhancements in contextual comprehension and response quality. Continued exploration and refinement of the model are poised to drive forward clinical information processing and decision support in the gastroenterology field.

Curcumin (CCM) is a polyphenol compound extracted from the turmeric rhizome. It has various biological activities, including antibacterial, anti-inflammatory, anti-cancer, and antioxidant. Due to its diverse activities, it is often used by researchers to study the therapeutic effects on various diseases. However, its poor solubility leads to poor bioavailability, and it is necessary to increase the water solubility with the help of carriers to improve the therapeutic effect. Gastrointestinal disease is a major global health problem that continues to affect human health. In this review, we have summarized the possible mechanism and therapeutic effect of CCM in various gastrointestinal diseases, and the improvement in the curative effect of CCM with nanopreparation. Finally, we concluded that there have been many clinical trials of CCM in combination with other drugs for the treatment of gastrointestinal disease, but so far, few have used CCM nanomaterials for treatment. Although in vitro and preclinical experiments have shown that nanopreparations can improve the efficacy of CCM, there are still insufficient studies on the safety of carriers.

Recent research increasingly highlights a strong correlation between gut microbiota and the risk of gastrointestinal diseases. However, whether this relationship is causal or merely coincidental remains uncertain. To address this, a Mendelian randomization (MR) analysis was undertaken to explore the connections between gut microbiota and prevalent gastrointestinal diseases.
Genome-wide association study (GWAS) summary statistics for gut microbiota, encompassing a diverse range of 211 taxa (131 genera, 35 families, 20 orders, 16 classes, and 9 phyla), were sourced from the comprehensive MiBioGen study. Genetic associations with 22 gastrointestinal diseases were gathered from the UK Biobank, FinnGen study, and various extensive GWAS studies. MR analysis was meticulously conducted to assess the causal relationship between genetically predicted gut microbiota and these gastrointestinal diseases. To validate the reliability of our findings, sensitivity analyses and tests for heterogeneity were systematically performed.
The MR analysis yielded significant evidence for 251 causal relationships between genetically predicted gut microbiota and the risk of gastrointestinal diseases. This included 98 associations with upper gastrointestinal diseases, 81 with lower gastrointestinal diseases, 54 with hepatobiliary diseases, and 18 with pancreatic diseases. Notably, these associations were particularly evident in taxa belonging to the genera Ruminococcus and Eubacterium. Further sensitivity analyses reinforced the robustness of these results.
The findings of this study indicate a potential genetic predisposition linking gut microbiota to gastrointestinal diseases. These insights pave the way for designing future clinical trials focusing on microbiome-related interventions, including the use of microbiome-dependent metabolites, to potentially treat or manage gastrointestinal diseases and their associated risk factors.

Gastroscopy, a critical tool for the diagnosis of upper gastrointestinal diseases, has recently incorporated artificial intelligence (AI) technology to alleviate the challenges involved in endoscopic diagnosis of some lesions, thereby enhancing diagnostic accuracy. This narrative review covers the current status of research concerning various applications of AI technology to gastroscopy, then discusses future research directions. By providing this review, we hope to promote the integration of gastroscopy and AI technology, with long-term clinical applications that can assist patients.

A comprehensive overview of the associations between air pollution and the risk of gastrointestinal (GI) diseases has been lacking. We aimed to examine the relationships of long-term exposure to ambient particulate matter (PM) with aerodynamic diameter ≤2.5 μm (PM2.5), 2.5-10 μm (PMcoarse), ≤10 μm (PM10), nitrogen dioxide (NO2), and nitrogen oxides (NOx), with the risk of incident GI diseases, and to explore the interplay between air pollution and genetic susceptibility. A total of 465,703 participants free of GI diseases in the UK Biobank were included at baseline. Land use regression models were employed to calculate the residential air pollutants concentrations. Cox proportional hazard models were used to evaluate the associations of air pollutants with the risk of GI diseases. The dose-response relationships of air pollutants with the risk of GI diseases were evaluated by restricted cubic spline curves. We found that long-term exposure to ambient air pollutants was positively associated with the risk of peptic ulcer (PM2.5 : Q4 vs. Q1: hazard ratio (HR) 1.272, 95% confidence interval (CI) 1.179-1.372, NO2: 1.220, 1.131-1.316, and NOx: 1.277, 1.184-1.376) and chronic gastritis (PM2.5: 1.454, 1.309-1.616, PM10 : 1.232, 1.112-1.366, NO2: 1.456, 1.311-1.617, and NOx: 1.419, 1.280-1.574) after Bonferroni correction. Participants with high genetic risk and high air pollution exposure had the highest risk of peptic ulcer, compared to those with low genetic risk and low air pollution exposure (PM2.5: HR 1.558, 95%CI 1.384-1.754, NO2: 1.762, 1.395-2.227, and NOx: 1.575, 1.403-1.769). However, no significant additive or multiplicative interaction between air pollution and genetic risk was found. In conclusion, long-term exposure to ambient air pollutants was associated with increased risk of peptic ulcer and chronic gastritis.

In response to the pressing need for robust disease diagnosis from gastrointestinal tract (GIT) endoscopic images, we proposed FLATer, a fast, lightweight, and highly accurate transformer-based model. FLATer consists of a residual block, a vision transformer module, and a spatial attention block, which concurrently focuses on local features and global attention. It can leverage the capabilities of both convolutional neural networks (CNNs) and vision transformers (ViT). We decomposed the classification of endoscopic images into two subtasks: a binary classification to discern between normal and pathological images and a further multi-class classification to categorize images into specific diseases, namely ulcerative colitis, polyps, and esophagitis. FLATer has exhibited exceptional prowess in these tasks, achieving 96.4% accuracy in binary classification and 99.7% accuracy in ternary classification, surpassing most existing models. Notably, FLATer could maintain impressive performance when trained from scratch, underscoring its robustness. In addition to the high precision, FLATer boasted remarkable efficiency, reaching a notable throughput of 16.4k images per second, which positions FLATer as a compelling candidate for rapid disease identification in clinical practice.

UNASSIGNED: Several recent studies have shown an association between gut microbiota and gastrointestinal diseases. However, the causal relationship between gut microbiota and gastrointestinal disorders is unclear.
UNASSIGNED: We assessed causal relationships between gut microbiota and eight common gastrointestinal diseases using Mendelian randomization (MR) analyses. IVW results were considered primary results. Cochrane\'s Q and MR-Egger tests were used to test for heterogeneity and pleiotropy. Leave-one-out was used to test the stability of the MR results, and Bonferroni correction was used to test the strength of the causal relationship between exposure and outcome.
UNASSIGNED: MR analyses of 196 gut microbiota and eight common gastrointestinal disease phenotypes showed 62 flora and common gastrointestinal diseases with potential causal relationships. Among these potential causal relationships, after the Bonferroni-corrected test, significant causal relationships remained between Genus Oxalobacter and CD (OR = 1.29, 95% CI: 1.13-1.48, p = 2.5 × 10-4, q = 4.20 × 10-4), and between Family Clostridiaceae1 and IBS (OR = 0.9967, 95% CI: 0.9944-0.9991, p = 1.3 × 10-3, q = 1.56 × 10-3). Cochrane\'s Q-test showed no significant heterogeneity among the various single nucleotide polymorphisms (SNPs). In addition, no significant level of pleiotropy was found according to the MR-Egger.
UNASSIGNED: This study provides new insights into the mechanisms of gut microbiota-mediated gastrointestinal disorders and some guidance for targeting specific gut microbiota for treating gastrointestinal disorders.

To systematically evaluate the efficacy and safety of Weichang\'an pill (, WCA) combined with Western Medicine (WM) for the treatment of gastrointestinal diseases.
Eight databases, including China National Knowledge Infrastructure Database, Wanfang Data, China Science and Technology Journal Database, SinoMed, PubMed, Web of Science, Cochrane Library, and Embase, were searched for randomized controlled trials (RCTs) of WCA from inception to 30 September 2021. We independently screened the literature, extracted data, and then evaluated the bias risk, effectiveness, safety, and other indicators of the included articles.
A total of 33 RCTs were included in this study with 3368 patients. After analysis, it was found that WCA combined with WM could effectively prevent and treat antibiotic-associated gastrointestinal reaction, functional dyspepsia (FD), irritable bowel syndrome, rotavirus diarrhea (RVD), and ulcerative colitis (UC); no serious adverse reactions occurred. Moreover, compared with the control group, the experimental group showed significantly improved symptoms and some biochemical parameters.
WCA combined with WM for the treatment of gastrointestinal diseases had better clinical efficacy than the control group, without serious adverse reactions. Notably, in the treatment of FD, RVD, and UC, WCA improved clinical symptoms and biochemical indicator expression. Nevertheless, owing to the restricted quality and quantity of the literature, the results need to be further studied using high-quality RCTs.

OBJECTIVE: The associations between gastrointestinal diseases (GIs) and cardiovascular disease (CVD) were unclear. We conducted a prospective cohort study to explore their associations.
METHODS: This study included 330 751 individuals without baseline CVD from the UK Biobank cohort. Individuals with and without GIs were followed up until the ascertainment of incident CVDs, including coronary heart disease (CHD), cerebrovascular disease (CeVD), heart failure (HF), and peripheral artery disease (PAD). The diagnosis of diseases was confirmed with combination of the nationwide inpatient data, primary care data, and cancer registries. A multivariable Cox proportional hazard regression model was used to estimate the associations between GIs and the risk of incident CVD.
RESULTS: During a median follow-up of 11.8 years, 31 605 incident CVD cases were diagnosed. Individuals with GIs had an elevated risk of CVD (hazard ratio 1.37; 95% confidence interval 1.34-1.41, P < 0.001). Eleven out of 15 GIs were associated with an increased risk of CVD after Bonferroni-correction, including cirrhosis, non-alcoholic fatty liver disease, gastritis and duodenitis, irritable bowel syndrome, Barrett\'s esophagus, gastroesophageal reflux disease, peptic ulcer, celiac disease, diverticulum, appendicitis, and biliary disease. The associations were stronger among women, individuals aged ≤60 years, and those with body mass index ≥25 kg/m2.
CONCLUSIONS: This large-scale prospective cohort study revealed the associations of GIs with an increased risk of incident CVD, in particular CHD and PAD. These findings support the reinforced secondary CVD prevention among patients with gastrointestinal disorders.