Abstract Background and aims Perinuclear anti-neutrophil cytoplasmic antibody(p-ANCA) positivity may indicate poor response to infliximab (IFX) in ulcerative colitis (UC). Nevertheless, there has been limited research on the effect of proteinase 3 anti-neutrophil cytoplasmic antibody (PR3-ANCA) in UC patients treated with IFX and vedolizumab (VDZ). This study aimed to investigate the short-term efficacy of PR3-ANCA in patients with moderate-to-severe active UC. Methods A total of 191 patients with moderate to severe active UC were enrolled from January 2021 to January 2024 in three centers in this retrospective, multicenter, real-world, case-control study. Patients with PR3-ANCA were allocated to two groups based on the biologics regimen (IFX or VDZ). Additionally, UC patients without positive PR3-ANCA, who were matched for baseline covariates including age, sex, BMI, disease duration, disease location, Mayo endoscopic subscore(MES), and prior advanced therapies, were selected at a ratio of 1:3. Clinical remission (CRm) and response (CRs), and endoscopic response (ERs) and remission(ERm) at week 22 were the endpoints. Results Compared to UC patients with negative PR3-ANCA, those with positive PR3-ANCA had lower rates of CRm (47.44% vs. 23.08%, P = 0.029), ERs (57.69% vs. 34.62%, P = 0.041), and ERm (39.74% vs. 11.54%, P = 0.008), but similar rates of CRs (69.23% vs. 65.38%, P = 0.715). However, there are no significant differences in rates of CRm (30.00% vs. 29.82%, P = 0.986), CRs (63.33% vs. 63.16%, P = 0.987), ERs (33.33% vs. 35.09%, P = 0.870), and ERm (20.00% vs. 21.05%, P = 0.908) between VDZ-treated patients with positive PR3-ANCA and negative. Additionally, compared to VDZ-treated patients, those treated with IFX had similar rates in CRm (30.00% vs. 23.08%, P = 0.560), CRs (63.33% vs. 65.38%, P = 0.873), ERs (33.33% vs. 34.62%, P = 0.920), and ERm (20.00% vs. 11.54%, P = 0.481). Rates in CRm (47.44% vs. 29.82%, P = 0.039), ERs (57.69% vs. 35.09%, P = 0.009), and ERm (39.74% vs. 21.05%, P = 0.021) in IFX-treated patients with negative PR3-ANCA were significantly higher than those in the VDZ-treated patients, but CRs was similar (69.23% vs. 63.16%, P = 0.460). Conclusions Positive PR3-ANCA affects the efficacy of IFX rather than VDZ in patients with moderate to severe active UC. UC patients with positive PR3-ANCA results may benefit from the exploration of new treatment strategies.
Diseases of the digestive system. Gastroenterology
Alzheimer's disease (AD) presents a complex, multifaceted challenge to patients, caregivers, and the healthcare system, necessitating integrated and dynamic support solutions. While artificial intelligence (AI) offers promising avenues for intervention, current applications are often siloed, addressing singular aspects of the disease such as diagnostics or caregiver support without systemic integration. This paper proposes a novel methodological framework for a comprehensive, multi-agent system (MAS) designed for holistic Alzheimer's disease management. The objective is to detail the architecture of a collaborative ecosystem of specialized AI agents, each engineered to address a distinct challenge in the AD care continuum, from caregiver support and multimodal data analysis to automated research and clinical data interpretation. The proposed framework is composed of eight specialized, interoperable agents. These agents are categorized by function: (1) Caregiver and Patient Support, (2) Data Analysis and Research, and (3) Advanced Multimodal Workflows. The methodology details the technical architecture of each agent, leveraging a suite of advanced technologies including large language models (LLMs) such as GPT-4o and Gemini, multi-agent orchestration frameworks, Retrieval-Augmented Generation (RAG) for evidence-grounded responses, and specialized tools for web scraping, multimodal data processing, and in-memory database querying. This paper presents a detailed architectural blueprint for an integrated AI ecosystem for AD care. By moving beyond single-purpose tools to a collaborative, multi-agent paradigm, this framework establishes a foundation for developing more adaptive, personalized, and proactive solutions. This methodological approach aims to pave the way for future systems capable of synthesizing diverse data streams to improve patient outcomes and reduce caregiver burden.
K2-Think is a reasoning system that achieves state-of-the-art performance with a 32B parameter model, matching or surpassing much larger models like GPT-OSS 120B and DeepSeek v3.1. Built on the Qwen2.5 base model, our system shows that smaller models can compete at the highest levels by combining advanced post-training and test-time computation techniques. The approach is based on six key technical pillars: Long Chain-of-thought Supervised Finetuning, Reinforcement Learning with Verifiable Rewards (RLVR), Agentic planning prior to reasoning, Test-time Scaling, Speculative Decoding, and Inference-optimized Hardware, all using publicly available open-source datasets. K2-Think excels in mathematical reasoning, achieving state-of-the-art scores on public benchmarks for open-source models, while also performing strongly in other areas such as Code and Science. Our results confirm that a more parameter-efficient model like K2-Think 32B can compete with state-of-the-art systems through an integrated post-training recipe that includes long chain-of-thought training and strategic inference-time enhancements, making open-source reasoning systems more accessible and affordable. K2-Think is freely available at k2think.ai, offering best-in-class inference speeds of over 2,000 tokens per second per request via the Cerebras Wafer-Scale Engine.
Masayuki Shimoyama, Hiroyoshi Iwagami, Kosuke Minaga
et al.
Abstract Cronkhite–Canada syndrome (CCS) can be difficult to diagnose. To diagnose CCS, it is important to perform endoscopic examination for patients with chronic diarrhea, check for the presence or absence of polyposis, and evaluate inflammation in the mucosa between the polyps. This study reported seven cases of CCS. The age of the patients, which included four men and three women, ranged 48–72 years, and all patients were Asian. The most common symptom among these patients was chronic diarrhea. Three of the patients had rectal cancer. In two patients, the lesions were detected at an early stage and resected via endoscopic treatment. CCS is associated with a high risk of malignant gastrointestinal lesions, especially rectal cancers, and periodic surveillance endoscopy and careful observation are required.
Diseases of the digestive system. Gastroenterology
Bibandhan Poudyal, David Soriano Panõs, Gourab Ghoshal
Non-pharmaceutical interventions (NPIs) aimed at limiting human mobility have demonstrated success in curbing the transmission of airborne diseases. However, their effectiveness in managing vector-borne diseases remains less clear. In this study, we introduce a framework that integrates mobility data with vulnerability matrices to evaluate the differential impacts of mobility-based NPIs on both airborne and vector-borne pathogens. Focusing on the city of Santiago de Cali in Colombia, our analysis illustrates how mobility-based policies previously proposed to contain airborne disease can make cities more prone to the spread of vector-borne diseases. By proposing a simplified synthetic model, we explain the limitations of the latter policies and exploit the synergies between both types of diseases to find new interventions reshaping the mobility network for their simultaneous control. Our results thus offer valuable insights into the epidemiological trade-offs of concurrent disease management, providing a foundation for the design and assessment of targeted interventions that reshape human mobility.
The emerging research shows that lncRNA has crucial research value in a series of complex human diseases. Therefore, the accurate identification of lncRNA-disease associations (LDAs) is very important for the warning and treatment of diseases. However, most of the existing methods have limitations in identifying nonlinear LDAs, and it remains a huge challenge to predict new LDAs. In this paper, a deep learning model based on a heterogeneous network and convolutional neural network (CNN) is proposed for lncRNA-disease association prediction, named HCNNLDA. The heterogeneous network containing the lncRNA, disease, and miRNA nodes, is constructed firstly. The embedding matrix of a lncRNA-disease node pair is constructed according to various biological premises about lncRNAs, diseases, and miRNAs. Then, the low-dimensional feature representation is fully learned by the convolutional neural network. In the end, the XGBoot classifier model is trained to predict the potential LDAs. HCNNLDA obtains a high AUC value of 0.9752 and AUPR of 0.9740 under the 5-fold cross-validation. The experimental results show that the proposed model has better performance than that of several latest prediction models. Meanwhile, the effectiveness of HCNNLDA in identifying novel LDAs is further demonstrated by case studies of three diseases. To sum up, HCNNLDA is a feasible calculation model to predict LDAs.
Umaima Rahman, Abhishek Basu, Muhammad Uzair Khattak
et al.
This study explores the concept of cross-disease transferability (XDT) in medical imaging, focusing on the potential of binary classifiers trained on one disease to perform zero-shot classification on another disease affecting the same organ. Utilizing chest X-rays (CXR) as the primary modality, we investigate whether a model trained on one pulmonary disease can make predictions about another novel pulmonary disease, a scenario with significant implications for medical settings with limited data on emerging diseases. The XDT framework leverages the embedding space of a vision encoder, which, through kernel transformation, aids in distinguishing between diseased and non-diseased classes in the latent space. This capability is especially beneficial in resource-limited environments or in regions with low prevalence of certain diseases, where conventional diagnostic practices may fail. However, the XDT framework is currently limited to binary classification, determining only the presence or absence of a disease rather than differentiating among multiple diseases. This limitation underscores the supplementary role of XDT to traditional diagnostic tests in clinical settings. Furthermore, results show that XDT-CXR as a framework is able to make better predictions compared to other zero-shot learning (ZSL) baselines.
Kohei Iwano, Shogo Shibuya, Satoshi Kagiwada
et al.
Recently, object detection methods (OD; e.g., YOLO-based models) have been widely utilized in plant disease diagnosis. These methods demonstrate robustness to distance variations and excel at detecting small lesions compared to classification methods (CL; e.g., CNN models). However, there are issues such as low diagnostic performance for hard-to-detect diseases and high labeling costs. Additionally, since healthy cases cannot be explicitly trained, there is a risk of false positives. We propose the Hierarchical object detection and recognition framework (HODRF), a sophisticated and highly integrated two-stage system that combines the strengths of both OD and CL for plant disease diagnosis. In the first stage, HODRF uses OD to identify regions of interest (ROIs) without specifying the disease. In the second stage, CL diagnoses diseases surrounding the ROIs. HODRF offers several advantages: (1) Since OD detects only one type of ROI, HODRF can detect diseases with limited training images by leveraging its ability to identify other lesions. (2) While OD over-detects healthy cases, HODRF significantly reduces these errors by using CL in the second stage. (3) CL's accuracy improves in HODRF as it identifies diagnostic targets given as ROIs, making it less vulnerable to size changes. (4) HODRF benefits from CL's lower annotation costs, allowing it to learn from a larger number of images. We implemented HODRF using YOLOv7 for OD and EfficientNetV2 for CL and evaluated its performance on a large-scale dataset (4 crops, 20 diseased and healthy classes, 281K images). HODRF outperformed YOLOv7 alone by 5.8 to 21.5 points on healthy data and 0.6 to 7.5 points on macro F1 scores, and it improved macro F1 by 1.1 to 7.2 points over EfficientNetV2.
Mohammed Abdullah Al Shuhoumi, Abdulrahman Al Mhrooqi, Azza Al Rashdi
et al.
Leclercia adecarboxylata is a recently acknowledged emerging pathogen. It is a member of the Enterobacterals family, formerly thought to be a member of the genus Escherichia. Isolation was reported from various animal and environmental specimens. However, it rarely causes infection in humans, and the true frequency is unknown or underestimated. Leclercia adecarboxylata showed an ascending resistance grade from pan-sensitive to Carbapenem-resistant due to its ability to produce and harbour hydrolysing enzymes that challenge daily clinical practices. In our report, the isolate was misidentified as Citrobacter koseri by Analytical Profile Index for Enterobacterals (API E), and as Pantoea species by Vitek 2 but confirmed by matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) and 16S ribosomal RNA analysis as Leclercia adecarboxylata. Conventional PCR revealed the presence of two populations of resistance genes, VIM-1 and OXA-48. Herein, a report of the first clinical emergence of Leclercia adecarboxylata producing VIM-1 in a rectal swab of a 63-year-old non-immunocompromised female with acute intracerebral haemorrhage.
Diseases of the digestive system. Gastroenterology, Microbiology
Keqiang Chen, John McCulloch, Rodrigo Das Neves
et al.
Abstract Background Formyl peptide receptor 2 (Fpr2) plays a crucial role in colon homeostasis and microbiota balance. Commensal E. coli is known to promote the regeneration of damaged colon epithelial cells. The aim of the study was to investigate the connection between E. coli and Fpr2 in the recovery of colon epithelial cells. Results The deficiency of Fpr2 was associated with impaired integrity of the colon mucosa and an imbalance of microbiota, characterized by the enrichment of Proteobacteria in the colon. Two serotypes of E. coli, O22:H8 and O91:H21, were identified in the mouse colon through complete genome sequencing. E. coli O22:H8 was found to be prevalent in the gut of mice and exhibited lower virulence compared to O91:H21. Germ-free (GF) mice that were pre-orally inoculated with E. coli O22:H8 showed reduced susceptibility to chemically induced colitis, increased proliferation of epithelial cells, and improved mouse survival. Following infection with E. coli O22:H8, the expression of Fpr2 in colon epithelial cells was upregulated, and the products derived from E. coli O22:H8 induced migration and proliferation of colon epithelial cells through Fpr2. Fpr2 deficiency increased susceptibility to chemically induced colitis, delayed the repair of damaged colon epithelial cells, and heightened inflammatory responses. Additionally, the population of E. coli was observed to increase in the colons of Fpr2 −/− mice with colitis. Conclusion Commensal E. coli O22:H8 stimulated the upregulation of Fpr2 expression in colon epithelial cells, and the products from E. coli induced migration and proliferation of colon epithelial cells through Fpr2. Fpr2 deficiency led to an increased E. coli population in the colon and delayed recovery of damaged colon epithelial cells in mice with colitis. Therefore, Fpr2 is essential for the effects of commensal E. coli on colon epithelial cell recovery.
Diseases of the digestive system. Gastroenterology
The incidence rate of voice diseases is increasing year by year. The use of software for remote diagnosis is a technical development trend and has important practical value. Among voice diseases, common diseases that cause hoarseness include spasmodic dysphonia, vocal cord paralysis, vocal nodule, and vocal cord polyp. This paper presents a voice disease detection method that can be applied in a wide range of clinical. We cooperated with Xiangya Hospital of Central South University to collect voice samples from sixty-one different patients. The Mel Frequency Cepstrum Coefficient (MFCC) parameters are extracted as input features to describe the voice in the form of data. An innovative model combining MFCC parameters and single convolution layer CNN is proposed for fast calculation and classification. The highest accuracy we achieved was 92%, it is fully ahead of the original research results and internationally advanced. And we use Advanced Voice Function Assessment Databases (AVFAD) to evaluate the generalization ability of the method we proposed, which achieved an accuracy rate of 98%. Experiments on clinical and standard datasets show that for the pathological detection of voice diseases, our method has greatly improved in accuracy and computational efficiency.
Farhan Tanvir, Khaled Mohammed Saifuddin, Tanvir Hossain
et al.
Modeling the interactions between drugs, targets, and diseases is paramount in drug discovery and has significant implications for precision medicine and personalized treatments. Current approaches frequently consider drug-target or drug-disease interactions individually, ignoring the interdependencies among all three entities. Within human metabolic systems, drugs interact with protein targets in cells, influencing target activities and subsequently impacting biological pathways to promote healthy functions and treat diseases. Moving beyond binary relationships and exploring tighter triple relationships is essential to understanding drugs' mechanism of action (MoAs). Moreover, identifying the heterogeneity of drugs, targets, and diseases, along with their distinct characteristics, is critical to model these complex interactions appropriately. To address these challenges, we effectively model the interconnectedness of all entities in a heterogeneous graph and develop a novel Heterogeneous Graph Triplet Attention Network (\texttt{HeTriNet}). \texttt{HeTriNet} introduces a novel triplet attention mechanism within this heterogeneous graph structure. Beyond pairwise attention as the importance of an entity for the other one, we define triplet attention to model the importance of pairs for entities in the drug-target-disease triplet prediction problem. Experimental results on real-world datasets show that \texttt{HeTriNet} outperforms several baselines, demonstrating its remarkable proficiency in uncovering novel drug-target-disease relationships.
N. B. Gubergrits, N. V. Byelyayeva, K. Y. Linevska
et al.
Georgiy Yosypovych Burchynsky (1908 — 1993) — Doctor of Medical Sciences, Professor, Honored Scientist of Ukraine, and laureate of the State Prize of Ukraine. G. Y. Burchynsky, throughout his life, was brought up on the traditions of the Kyiv therapeutic school. A close relationship with the Kyiv therapeutic school largely determined his personality as a doctor, teacher, scientist, and head of the department. In the years 1954 — 1962, Georgiy Yosypovych was the head of the Department of Therapy at the School of Dentistry. Since 1962, he had been the head of the Department of Faculty Therapy at the Kyiv Medical Institute for 24 years. G. Y. Burchynsky paid much attention to the study of pulmonary pathology. Based on the research materials, the monograph «Suppurative processes in the lungs» was issued in 1950. In particular, G. Y. Burchynsky developed a pathogenetic classification of pulmonary suppurations. One of the first in Ukraine, he applied the technique of endobronchial administration of antibiotics, He developed and introduced into practice the technique of zonal, or local, instillation using a bronchoscope. Gastrointestinal diseases have always been in the focus of Kyiv therapeutic school. G. Y. Burchynsky paid special attention attention to the problems of peptic ulcers. As a result, new data were obtained about this disease, which is outwardly clear but inwardly mysterious. G. Y. Burchynsky and his colleagues did a detailed study on the course of peptic ulcers, even during wartime. They looked at the etiology, pathogenesis, changes in the ultrastructure of the gastric mucosa, general changes, and questions about pathogenetic therapy for this disease. Experimental studies on the model of reproduction of a hypothalamic ulcer, as well as the results of studying the ultrastructure of gastroduodenal mucosa, confirmed the importance of the disturbances of nervous trophism. An experimental study on the pharmacodynamics of anticholinergics, which suppress cholinergic stimulation of the stomach and duodenum, showed that they can be used in clinical practice as a way to treat peptic ulcer disease. Under the supervision of G. Y. Burchynsky, two doctoral dissertations on the problem of peptic ulcers were defended at the department. Observations and results of the studies, performed by Georgiy Yosypovych and his colleagues, are reflected in the papers and monographs, such as “Peptic Ulcer,” “Clinical Gastroenterology,” and the relevant chapters of multivolume guidelines and the Big Medical Encyclopedia.
Abstract Malignant gastrointestinal neuroectodermal tumors (GNETs) are rare malignant mesenchymal neoplasms. To our knowledge, only 99 cases have been reported worldwide. The tumor has an aggressive malignancy, with a rapid progression. The histological features of GNET overlap with those of clear cell sarcoma, which contain Ewing sarcoma breakpoint region 1 mutation. GNETs lack melanocyte‐specific markers, while clear cell sarcoma exhibits melanocytic differentiation. Various symptoms have been reported previously, and the most reported lesion is in the small bowel. The patient was a 69‐year‐old man who presented with abdominal pain and vomiting. Computed tomography revealed a nodule in the small bowel, which induced small intestinal obstruction. Enteroscopic images revealed a submucosal tumor. Surgery was performed, and the patient was diagnosed with GNET. Only two patients whose primary lesions were in the small intestine, including the patient in this report, have undergone enteroscopy before surgery. This is a rare case of GNET in which a patient underwent enteroscopy before surgical treatment.
Diseases of the digestive system. Gastroenterology