Abstract Pancreatic cancer is among the leading causes of gastrointestinal cancer‐related death, with a dismal prognosis. Over 80% of pancreatic cancer patients present with advanced disease, making curative resection unfeasible. These patients are often presented with malignant biliary obstruction (MBO) and gastric outlet obstruction (GOO). In these cases, palliative management is aimed to alleviate symptoms, enhance quality of life, and facilitate subsequent chemotherapy. Currently, neoadjuvant chemotherapy is frequently used in both borderline resectable and resectable pancreatic cancer, necessitating effective biliary and gastrointestinal drainage in a growing number of patients. Traditionally, surgical bypass was the gold standard, performed via either a minimally invasive or open approach. However, notable progress has emerged in developing endoscopic techniques, such as endoscopic retrograde cholangiopancreatography (ERCP) stenting for MBO and endoscopic enteral stenting for GOO. While these procedures provide rapid symptom relief, they are associated with higher stent dysfunction rates and more frequent re‐intervention needs. When ERCP fails, percutaneous transhepatic biliary drainage is a widely accepted alternative for MBO. Endoscopic ultrasound (EUS)‐guided techniques, including EUS‐guided biliary drainage and EUS‐guided gastroenterostomy, have recently gained prominence. Emerging clinical data suggest that these methods may be superior, potentially becoming the preferred first‐line palliative treatment for unresectable pancreatic cancer. This review will summarize the current evidence on managing MBO and GOO in patients with pancreatic cancer.
Surgery, Diseases of the digestive system. Gastroenterology
Image segmentation plays a vital role in the medical field by isolating organs or regions of interest from surrounding areas. Traditionally, segmentation models are trained on a specific organ or a disease, limiting their ability to handle other organs and diseases. At present, few advanced models can perform multi-organ or multi-disease segmentation, offering greater flexibility. Also, recently, prompt-based image segmentation has gained attention as a more flexible approach. It allows models to segment areas based on user-provided prompts. Despite these advances, there has been no dedicated work on prompt-based interactive multi-organ and multi-disease segmentation, especially for Chest X-rays. This work presents two main contributions: first, generating doodle prompts by medical experts of a collection of datasets from multiple sources with 23 classes, including 6 organs and 17 diseases, specifically designed for prompt-based Chest X-ray segmentation. Second, we introduce Prompt2SegCXR, a lightweight model for accurately segmenting multiple organs and diseases from Chest X-rays. The model incorporates multi-stage feature fusion, enabling it to combine features from various network layers for better spatial and semantic understanding, enhancing segmentation accuracy. Compared to existing pre-trained models for prompt-based image segmentation, our model scores well, providing a reliable solution for segmenting Chest X-rays based on user prompts.
INTRODUCTION: Gastrointestinal (GI) symptoms and weight loss develop during and after acute pancreatitis (AP), but remain understudied. In this prospective, multicenter study, we aim to assess GI symptom burden and weight loss and their correlation with exocrine function up to 12 months post-AP. METHODS: GI symptom burden, anthropometrics, and exocrine pancreatic function were systematically measured in adults (≥18 years) with AP at predefined intervals: hospitalization (enrollment), 3 months, and 12 months post-AP. Symptoms were evaluated using a 15-item tracker, including abdominal symptoms, stool characteristics, and activities of daily living, higher scores indicating greater symptom burden (range 0–45). Exocrine function was assessed with fecal elastase-1 (FE-1) levels. RESULTS: GI symptoms were collected in 97 participants with 12-month follow-up. The median (interquartile range) GI-symptom score was 7 (3–12) with 55 participants (57%) experiencing at least one symptom frequently (often or almost always). In multivariable linear regression, younger age, lower Charlson Comorbidity Index, smoking, recurrent AP, and alcoholic or idiopathic etiologies were associated with significantly higher GI-symptom burden at 12 months. A significant negative correlation was found between GI symptoms and FE-1 levels during hospitalization (ρ = −0.288; P = 0.015) and at 12 months (ρ = −0.219; P = 0.046). Eighteen participants (18.6%) lost ≥10% body weight between hospitalization and 12 months, and had significantly lower median FE-1 levels at 12 months compared with the group without weight loss (166 vs 332 µg/g, P = 0.016). DISCUSSION: This is the first study to prospectively assess GI-symptom burden and exocrine function post-AP. Lower exocrine pancreatic function at 12 months was associated with increased symptom burden and weight loss. These findings support further investigations to define and improve patient-reported outcomes post-AP. This study is registered with ClinicalTrials.gov, NCT03063398.
Maria E. Barbian, Joshua A. Owens, Crystal R. Naudin
et al.
ABSTRACTThe diet during pregnancy, or antenatal diet, influences the offspring’s intestinal health. We previously showed that antenatal butyrate supplementation reduces injury in adult murine offspring with dextran sulfate sodium (DSS)-induced colitis. Potential modulators of butyrate levels in the intestine include a high fiber diet or dietary supplementation with probiotics. To test this, we supplemented the diet of pregnant mice with high fiber, or with the probiotic bacteria Lactococcus lactis subspecies cremoris or Lactobacillus rhamnosus GG. We then induced chronic colitis with DSS in their adult offspring. We demonstrate that a high fiber antenatal diet, or supplementation with Lactococcus lactis subspecies cremoris during pregnancy diminished the injury from DSS-induced colitis in offspring. These data are evidence that antenatal dietary interventions impact offspring gut health and define the antenatal diet as a therapeutic modality to enhance offspring intestinal health.
Diseases of the digestive system. Gastroenterology
Kashif Asghar, Shaarif Bashir, Muhammad Hassan
et al.
Abstract Background Hepatocellular carcinoma (HCC) is a highly aggressive and rapidly progressing form of cancer with a poor prognosis. Recent advances in the management of HCC focused on the novel immunotherapeutic modalities for patients with advanced disease. PD-L1 has emerged as a promising immunotherapeutic approach for HCC. The evaluation of PD-L1 expression aids in identifying patients who can derive maximum benefits from these therapies. This study aims to examine and compare the expression of PD-L1 using two clones (22C3 and 28-8) in HCC patients. Methods Forty-six patients with HCC were selected between 2005 and 2022 from the Shaukat Khanum Memorial Cancer Hospital and Research Centre (SKMCH&RC) in Lahore, Pakistan. The patients' formalin-fixed paraffin-embedded (FFPE) tissue samples were retrieved from the department of pathology to conduct immunohistochemical analysis. Moreover, the clinicopathological data of these patients were gathered from the hospital information system (HIS). To assess the relationship between variables, bivariate analysis was carried out using either the chi-square test or Fisher exact test when necessary. Results Among the 46 tissue specimens analyzed, the presence of clone 22C3 was detected in 20 HCC patients, with 10 patients showing high expression (21.7%) and another 10 patients showing low expression (21.7%). 22C3 expression was not observed in 26 patients (56.5%). On the other hand, clone 28-8 was expressed in 10 patients, all of whom exhibited low expression (21.7%), while no expression of clone 28-8 was observed in 36 patients (78.3%). An association was found between the expression of 22C3 and 28-8 PD-L1 clones (p-value 0.01). Furthermore, upon closer examination, it was revealed that 12 cases exhibited positive results for 22C3 but negative results for 28-8. Interestingly, two cases displayed positive results for 28-8 but negative results for 22C3. Conclusion We obserevd that the PD-L1 clones, 22C3 and 28-8, are comparable. If PD-L1 expression using 22C3 is negative, considering the use of 28-8 for evaluating expression in HCC patients may be beneficial. However, further validation in a larger cohort is necessary.
Surgery, Diseases of the digestive system. Gastroenterology
A new simulation technique to obtain the synchronized steady-state solutions existing in coupled oscillator systems is presented. The technique departs from a semi-analytical formulation presented in previous works. It extends the model of the admittance function describing each individual oscillator to a piecewise linear one. This provides a global formulation of the coupled system, considering the whole characteristic of each voltage-controlled oscillator (VCO) in the array. In comparison with the previous local formulation, the new formulation significantly improves the accuracy in the prediction of the system synchronization ranges. The technique has been tested by comparison with computationally demanding circuit-level Harmonic Balance simulations in an array of Van der Pol-type oscillators and then applied to a coupled system of FET based oscillators at 5 GHz, with very good agreement with measurements.
Maxim Rubchinsky, Ella Rabinovich, Adi Shraibman
et al.
We present a novel approach to automating the identification of risk factors for diseases from medical literature, leveraging pre-trained models in the bio-medical domain, while tuning them for the specific task. Faced with the challenges of the diverse and unstructured nature of medical articles, our study introduces a multi-step system to first identify relevant articles, then classify them based on the presence of risk factor discussions and, finally, extract specific risk factor information for a disease through a question-answering model. Our contributions include the development of a comprehensive pipeline for the automated extraction of risk factors and the compilation of several datasets, which can serve as valuable resources for further research in this area. These datasets encompass a wide range of diseases, as well as their associated risk factors, meticulously identified and validated through a fine-grained evaluation scheme. We conducted both automatic and thorough manual evaluation, demonstrating encouraging results. We also highlight the importance of improving models and expanding dataset comprehensiveness to keep pace with the rapidly evolving field of medical research.
UAVs emerge as the optimal carriers for visual weed iden?tification and integrated pest and disease management in crops. How?ever, the absence of specialized datasets impedes the advancement of model development in this domain. To address this, we have developed the Pests and Diseases Tree dataset (PDT dataset). PDT dataset repre?sents the first high-precision UAV-based dataset for targeted detection of tree pests and diseases, which is collected in real-world operational environments and aims to fill the gap in available datasets for this field. Moreover, by aggregating public datasets and network data, we further introduced the Common Weed and Crop dataset (CWC dataset) to ad?dress the challenge of inadequate classification capabilities of test models within datasets for this field. Finally, we propose the YOLO-Dense Pest (YOLO-DP) model for high-precision object detection of weed, pest, and disease crop images. We re-evaluate the state-of-the-art detection models with our proposed PDT dataset and CWC dataset, showing the completeness of the dataset and the effectiveness of the YOLO-DP. The proposed PDT dataset, CWC dataset, and YOLO-DP model are pre?sented at https://github.com/RuiXing123/PDT_CWC_YOLO-DP.
Recent advances in prototypical learning have shown remarkable potential to provide useful decision interpretations associating activation maps and predictions with class-specific training prototypes. Such prototypical learning has been well-studied for various single-label diseases, but for quite relevant and more challenging multi-label diagnosis, where multiple diseases are often concurrent within an image, existing prototypical learning models struggle to obtain meaningful activation maps and effective class prototypes due to the entanglement of the multiple diseases. In this paper, we present a novel Cross- and Intra-image Prototypical Learning (CIPL) framework, for accurate multi-label disease diagnosis and interpretation from medical images. CIPL takes advantage of common cross-image semantics to disentangle the multiple diseases when learning the prototypes, allowing a comprehensive understanding of complicated pathological lesions. Furthermore, we propose a new two-level alignment-based regularisation strategy that effectively leverages consistent intra-image information to enhance interpretation robustness and predictive performance. Extensive experiments show that our CIPL attains the state-of-the-art (SOTA) classification accuracy in two public multi-label benchmarks of disease diagnosis: thoracic radiography and fundus images. Quantitative interpretability results show that CIPL also has superiority in weakly-supervised thoracic disease localisation over other leading saliency- and prototype-based explanation methods.
Akeem Temitope Otapo, Alice Othmani, Ghazaleh Khodabandelou
et al.
The integration of Artificial Intelligence (AI) and the Internet of Medical Things (IoMT) in healthcare, through Machine Learning (ML) and Deep Learning (DL) techniques, has advanced the prediction and diagnosis of chronic diseases. AI-driven models such as XGBoost, Random Forest, CNNs, and LSTM RNNs have achieved over 98\% accuracy in predicting heart disease, chronic kidney disease (CKD), Alzheimer's disease, and lung cancer, using datasets from platforms like Kaggle, UCI, private institutions, and real-time IoMT sources. However, challenges persist due to variations in data quality, patient demographics, and formats from different hospitals and research sources. The incorporation of IoMT data, which is vast and heterogeneous, adds complexities in ensuring interoperability and security to protect patient privacy. AI models often struggle with overfitting, performing well in controlled environments but less effectively in real-world clinical settings. Moreover, multi-morbidity scenarios especially for rare diseases like dementia, stroke, and cancers remain insufficiently addressed. Future research should focus on data standardization and advanced preprocessing techniques to improve data quality and interoperability. Transfer learning and ensemble methods are crucial for improving model generalizability across clinical settings. Additionally, the exploration of disease interactions and the development of predictive models for chronic illness intersections is needed. Creating standardized frameworks and open-source tools for integrating federated learning, blockchain, and differential privacy into IoMT systems will also ensure robust data privacy and security.
Mirsaeed Abdollahi, Ali Jafarizadeh, Amirhosein Ghafouri Asbagh
et al.
Background: Cardiovascular diseases (CVDs) are the leading cause of death globally. The use of artificial intelligence (AI) methods - in particular, deep learning (DL) - has been on the rise lately for the analysis of different CVD-related topics. The use of fundus images and optical coherence tomography angiography (OCTA) in the diagnosis of retinal diseases has also been extensively studied. To better understand heart function and anticipate changes based on microvascular characteristics and function, researchers are currently exploring the integration of AI with non-invasive retinal scanning. There is great potential to reduce the number of cardiovascular events and the financial strain on healthcare systems by utilizing AI-assisted early detection and prediction of cardiovascular diseases on a large scale. Method: A comprehensive search was conducted across various databases, including PubMed, Medline, Google Scholar, Scopus, Web of Sciences, IEEE Xplore, and ACM Digital Library, using specific keywords related to cardiovascular diseases and artificial intelligence. Results: The study included 87 English-language publications selected for relevance, and additional references were considered. This paper provides an overview of the recent developments and difficulties in using artificial intelligence and retinal imaging to diagnose cardiovascular diseases. It provides insights for further exploration in this field. Conclusion: Researchers are trying to develop precise disease prognosis patterns in response to the aging population and the growing global burden of CVD. AI and deep learning are revolutionizing healthcare by potentially diagnosing multiple CVDs from a single retinal image. However, swifter adoption of these technologies in healthcare systems is required.
Alyssa M. Vanderbeek, Anna A. Vidovszky, Jessica L. Ross
et al.
A crucial task for a randomized controlled trial (RCT) is to specify a statistical method that can yield an efficient estimator and powerful test for the treatment effect. A novel and effective strategy to obtain efficient and powerful treatment effect inferences is to incorporate predictions from generative artificial intelligence (AI) algorithms into covariate adjustment for the regression analysis of a RCT. Training a generative AI algorithm on historical control data enables one to construct a digital twin generator (DTG) for RCT participants, which utilizes a participant's baseline covariates to generate a probability distribution for their potential control outcome. Summaries of the probability distribution from the DTG are highly predictive of the trial outcome, and adjusting for these features via regression can thus improve the quality of treatment effect inferences, while satisfying regulatory guidelines on statistical analyses, for a RCT. However, a critical assumption in this strategy is homoskedasticity, or constant variance of the outcome conditional on the covariates. In the case of heteroskedasticity, existing covariate adjustment methods yield inefficient estimators and underpowered tests. We propose to address heteroskedasticity via a weighted prognostic covariate adjustment methodology (Weighted PROCOVA) that adjusts for both the mean and variance of the regression model using information obtained from the DTG. We prove that our method yields unbiased treatment effect estimators, and demonstrate via comprehensive simulation studies and case studies from Alzheimer's disease that it can reduce the variance of the treatment effect estimator, maintain the Type I error rate, and increase the power of the test for the treatment effect from 80% to 85%~90% when the variances from the DTG can explain 5%~10% of the variation in the RCT participants' outcomes.