Medical artificial intelligence (AI) systems frequently lack systematic domain expertise integration, potentially compromising diagnostic reliability. This study presents an ontology-based framework for bone disease diagnosis, developed in collaboration with Ho Chi Minh City Hospital for Traumatology and Orthopedics. The framework introduces three theoretical contributions: (1) a hierarchical neural network architecture guided by bone disease ontology for segmentation-classification tasks, incorporating Visual Language Models (VLMs) through prompts, (2) an ontology-enhanced Visual Question Answering (VQA) system for clinical reasoning, and (3) a multimodal deep learning model that integrates imaging, clinical, and laboratory data through ontological relationships. The methodology maintains clinical interpretability through systematic knowledge digitization, standardized medical terminology mapping, and modular architecture design. The framework demonstrates potential for extension beyond bone diseases through its standardized structure and reusable components. While theoretical foundations are established, experimental validation remains pending due to current dataset and computational resource limitations. Future work will focus on expanding the clinical dataset and conducting comprehensive system validation.
Aniketh Garikaparthi, Manasi Patwardhan, Lovekesh Vig
et al.
The rapid advancement in capabilities of large language models (LLMs) raises a pivotal question: How can LLMs accelerate scientific discovery? This work tackles the crucial first stage of research, generating novel hypotheses. While recent work on automated hypothesis generation focuses on multi-agent frameworks and extending test-time compute, none of the approaches effectively incorporate transparency and steerability through a synergistic Human-in-the-loop (HITL) approach. To address this gap, we introduce IRIS: Interactive Research Ideation System, an open-source platform designed for researchers to leverage LLM-assisted scientific ideation. IRIS incorporates innovative features to enhance ideation, including adaptive test-time compute expansion via Monte Carlo Tree Search (MCTS), fine-grained feedback mechanism, and query-based literature synthesis. Designed to empower researchers with greater control and insight throughout the ideation process. We additionally conduct a user study with researchers across diverse disciplines, validating the effectiveness of our system in enhancing ideation. We open-source our code at https://github.com/Anikethh/IRIS-Interactive-Research-Ideation-System
Modeling disease progression through multiple stages is critical for clinical decision-making for chronic diseases, e.g., cancer, diabetes, chronic kidney diseases, and so on. Existing approaches often model the disease progression as a uniform trajectory pattern at the population level. However, chronic diseases are highly heterogeneous and often have multiple progression patterns depending on a patient's individual genetics and environmental effects due to lifestyles. We propose a personalized disease progression model to jointly learn the heterogeneous progression patterns and groups of genetic profiles. In particular, an end-to-end pipeline is designed to simultaneously infer the characteristics of patients from genetic markers using a variational autoencoder and how it drives the disease progressions using an RNN-based state-space model based on clinical observations. Our proposed model shows improvement on real-world and synthetic clinical data.
Jorge Iranzo-Sánchez, Javier Iranzo-Sánchez, Adrià Giménez
et al.
This work describes the participation of the MLLP-VRAIN research group in the shared task of the IWSLT 2025 Simultaneous Speech Translation track. Our submission addresses the unique challenges of real-time translation of long-form speech by developing a modular cascade system that adapts strong pre-trained models to streaming scenarios. We combine Whisper Large-V3-Turbo for ASR with the multilingual NLLB-3.3B model for MT, implementing lightweight adaptation techniques rather than training new end-to-end models from scratch. Our approach employs document-level adaptation with prefix training to enhance the MT model's ability to handle incomplete inputs, while incorporating adaptive emission policies including a wait-$k$ strategy and RALCP for managing the translation stream. Specialized buffer management techniques and segmentation strategies ensure coherent translations across long audio sequences. Experimental results on the ACL60/60 dataset demonstrate that our system achieves a favorable balance between translation quality and latency, with a BLEU score of 31.96 and non-computational-aware StreamLAAL latency of 2.94 seconds. Our final model achieves a preliminary score on the official test set (IWSLT25Instruct) of 29.8 BLEU. Our work demonstrates that carefully adapted pre-trained components can create effective simultaneous translation systems for long-form content without requiring extensive in-domain parallel data or specialized end-to-end training.
Introduction Artificial intelligence is already widely utilized in gastroenterology. This study aims to comprehensively evaluate the research hotspots and development trends within the field of AI in gastroenterology by employing bibliometric techniques to scrutinize geographical distribution, authorship, affiliated institutions, keyword usage, references, and other pertinent data contained within relevant publications. Methods This investigation compiled all pertinent publications related to artificial intelligence in the context of gastrointestinal polyps and digestive endoscopy from 2003 to 2023 within the Web of Science Core Collection database. Furthermore, the study harnessed the tools CiteSpace, VOSviewer, GraphPad Prism and Scimago Graphica for visual data analysis. The study retrieved a total of 2,394 documents in the field of AI in digestive endoscopy and 628 documents specifically related to AI in digestive tract polyps. Results The United States and China are the primary contributors to research in both fields. Since 2019, studies on AI for digestive tract polyps have constituted approximately 25% of the total AI digestive endoscopy studies annually. Six of the top 10 most-cited studies in AI digestive endoscopy also rank among the top 10 most-cited studies in AI for gastrointestinal polyps. Additionally, the number of studies on AI-assisted polyp segmentation is growing the fastest, with significant increases in AI-assisted polyp diagnosis and real-time systems beginning after 2020. Discussion The application of AI in gastroenterology has garnered increasing attention. As theoretical advancements in AI for gastroenterology have progressed, real-time diagnosis and detection of gastrointestinal diseases have become feasible in recent years, highlighting the promising potential of AI in this field.
Mira Thing, Mikkel Parsberg Werge, Nina Kimer
et al.
Abstract Background Alterations in the production of short-chain fatty acids (SCFAs) may reflect disturbances in the gut microbiota and have been linked to metabolic dysfunction-associated steatotic liver disease (MASLD). We assessed plasma SCFAs in patients with MASLD and healthy controls. Methods Fasting venous blood samples were collected and eight SCFAs were measured using gas chromatography-tandem mass spectrometry (GC-MS/MS). Relative between-group differences in circulating SCFA concentrations were estimated by linear regression, and the relation between SCFA concentrations, MASLD, and fibrosis severity was investigated using logistic regression. Results The study includes 100 patients with MASLD (51% with mild/no fibrosis and 49% with significant fibrosis) and 50 healthy controls. Compared with healthy controls, MASLD patients had higher plasma concentrations of propionate (21.8%, 95% CI 3.33 to 43.6, p = 0.02), formate (21.9%, 95% CI 6.99 to 38.9, p = 0.003), valerate (35.7%, 95% CI 4.53 to 76.2, p = 0.02), and α-methylbutyrate (16.2%, 95% CI 3.66 to 30.3, p = 0.01) but lower plasma acetate concentrations (− 30.0%, 95% CI − 40.4 to − 17.9, p < 0.001). Among patients with MASLD, significant fibrosis was positively associated with propionate (p = 0.02), butyrate (p = 0.03), valerate (p = 0.03), and α-methylbutyrate (p = 0.02). Six of eight SCFAs were significantly increased in F4 fibrosis. Conclusions In the present study, SCFAs were associated with MASLD and fibrosis severity, but further research is needed to elucidate the potential mechanisms underlying our observations and to assess the possible benefit of therapies modulating gut microbiota.
Diseases of the digestive system. Gastroenterology
Objective: Our objective is to develop and validate TrajVis, an interactive tool that assists clinicians in using artificial intelligence (AI) models to leverage patients' longitudinal electronic medical records (EMR) for personalized precision management of chronic disease progression. Methods: We first perform requirement analysis with clinicians and data scientists to determine the visual analytics tasks of the TrajVis system as well as its design and functionalities. A graph AI model for chronic kidney disease (CKD) trajectory inference named DEPOT is used for system development and demonstration. TrajVis is implemented as a full-stack web application with synthetic EMR data derived from the Atrium Health Wake Forest Baptist Translational Data Warehouse and the Indiana Network for Patient Care research database. A case study with a nephrologist and a user experience survey of clinicians and data scientists are conducted to evaluate the TrajVis system. Results: The TrajVis clinical information system is composed of four panels: the Patient View for demographic and clinical information, the Trajectory View to visualize the DEPOT-derived CKD trajectories in latent space, the Clinical Indicator View to elucidate longitudinal patterns of clinical features and interpret DEPOT predictions, and the Analysis View to demonstrate personal CKD progression trajectories. System evaluations suggest that TrajVis supports clinicians in summarizing clinical data, identifying individualized risk predictors, and visualizing patient disease progression trajectories, overcoming the barriers of AI implementation in healthcare. Conclusion: TrajVis bridges the gap between the fast-growing AI/ML modeling and the clinical use of such models for personalized and precision management of chronic diseases.
The rising prevalence of vision-threatening retinal diseases poses a significant burden on the global healthcare systems. Deep learning (DL) offers a promising solution for automatic disease screening but demands substantial data. Collecting and labeling large volumes of ophthalmic images across various modalities encounters several real-world challenges, especially for rare diseases. Here, we introduce EyeDiff, a text-to-image model designed to generate multimodal ophthalmic images from natural language prompts and evaluate its applicability in diagnosing common and rare diseases. EyeDiff is trained on eight large-scale datasets using the advanced latent diffusion model, covering 14 ophthalmic image modalities and over 80 ocular diseases, and is adapted to ten multi-country external datasets. The generated images accurately capture essential lesional characteristics, achieving high alignment with text prompts as evaluated by objective metrics and human experts. Furthermore, integrating generated images significantly enhances the accuracy of detecting minority classes and rare eye diseases, surpassing traditional oversampling methods in addressing data imbalance. EyeDiff effectively tackles the issue of data imbalance and insufficiency typically encountered in rare diseases and addresses the challenges of collecting large-scale annotated images, offering a transformative solution to enhance the development of expert-level diseases diagnosis models in ophthalmic field.
Catarina Botelho, Alberto Abad, Tanja Schultz
et al.
Speech is a rich biomarker that encodes substantial information about the health of a speaker, and thus it has been proposed for the detection of numerous diseases, achieving promising results. However, questions remain about what the models trained for the automatic detection of these diseases are actually learning and the basis for their predictions, which can significantly impact patients' lives. This work advocates for an interpretable health model, suitable for detecting several diseases, motivated by the observation that speech-affecting disorders often have overlapping effects on speech signals. A framework is presented that first defines "reference speech" and then leverages this definition for disease detection. Reference speech is characterized through reference intervals, i.e., the typical values of clinically meaningful acoustic and linguistic features derived from a reference population. This novel approach in the field of speech as a biomarker is inspired by the use of reference intervals in clinical laboratory science. Deviations of new speakers from this reference model are quantified and used as input to detect Alzheimer's and Parkinson's disease. The classification strategy explored is based on Neural Additive Models, a type of glass-box neural network, which enables interpretability. The proposed framework for reference speech characterization and disease detection is designed to support the medical community by providing clinically meaningful explanations that can serve as a valuable second opinion.
Rare diseases pose significant challenges in diagnosis and treatment due to their low prevalence and heterogeneous clinical presentations. Unstructured clinical notes contain valuable information for identifying rare diseases, but manual curation is time-consuming and prone to subjectivity. This study aims to develop a hybrid approach combining dictionary-based natural language processing (NLP) tools with large language models (LLMs) to improve rare disease identification from unstructured clinical reports. We propose a novel hybrid framework that integrates the Orphanet Rare Disease Ontology (ORDO) and the Unified Medical Language System (UMLS) to create a comprehensive rare disease vocabulary. The proposed hybrid approach demonstrates superior performance compared to traditional NLP systems and standalone LLMs. Notably, the approach uncovers a significant number of potential rare disease cases not documented in structured diagnostic records, highlighting its ability to identify previously unrecognized patients.
Mateusz Daniol, Daria Hemmerling, Jakub Sikora
et al.
Parkinson's disease ranks as the second most prevalent neurodegenerative disorder globally. This research aims to develop a system leveraging Mixed Reality capabilities for tracking and assessing eye movements. In this paper, we present a medical scenario and outline the development of an application designed to capture eye-tracking signals through Mixed Reality technology for the evaluation of neurodegenerative diseases. Additionally, we introduce a pipeline for extracting clinically relevant features from eye-gaze analysis, describing the capabilities of the proposed system from a medical perspective. The study involved a cohort of healthy control individuals and patients suffering from Parkinson's disease, showcasing the feasibility and potential of the proposed technology for non-intrusive monitoring of eye movement patterns for the diagnosis of neurodegenerative diseases. Clinical relevance - Developing a non-invasive biomarker for Parkinson's disease is urgently needed to accurately detect the disease's onset. This would allow for the timely introduction of neuroprotective treatment at the earliest stage and enable the continuous monitoring of intervention outcomes. The ability to detect subtle changes in eye movements allows for early diagnosis, offering a critical window for intervention before more pronounced symptoms emerge. Eye tracking provides objective and quantifiable biomarkers, ensuring reliable assessments of disease progression and cognitive function. The eye gaze analysis using Mixed Reality glasses is wireless, facilitating convenient assessments in both home and hospital settings. The approach offers the advantage of utilizing hardware that requires no additional specialized attachments, enabling examinations through personal eyewear.
Recent advancements in artificial intelligence (AI), especially large language models (LLMs), have significantly advanced healthcare applications and demonstrated potentials in intelligent medical treatment. However, there are conspicuous challenges such as vast data volumes and inconsistent symptom characterization standards, preventing full integration of healthcare AI systems with individual patients' needs. To promote professional and personalized healthcare, we propose an innovative framework, Heath-LLM, which combines large-scale feature extraction and medical knowledge trade-off scoring. Compared to traditional health management applications, our system has three main advantages: (1) It integrates health reports and medical knowledge into a large model to ask relevant questions to large language model for disease prediction; (2) It leverages a retrieval augmented generation (RAG) mechanism to enhance feature extraction; (3) It incorporates a semi-automated feature updating framework that can merge and delete features to improve accuracy of disease prediction. We experiment on a large number of health reports to assess the effectiveness of Health-LLM system. The results indicate that the proposed system surpasses the existing ones and has the potential to significantly advance disease prediction and personalized health management.
Abstract: The stomach is a critical organ within the human digestive system, and gastric diseases represent significant health concerns often underestimated by the public. Factors such as poor dietary habits, stress, and bacterial infections contribute to these ailments, whose initial symptoms can easily be misinterpreted due to their similarity with other gastrointestinal disorders. The knowledge gap exists in the diagnostic challenges faced by both patients and healthcare professionals, necessitating the development of improved diagnostic tools. This study aims to enhance the diagnostic process for gastric diseases through the implementation of an expert system utilizing the Fuzzy Tsukamoto method. By employing questionnaires and expert interviews to gather data on symptoms, we develop a comprehensive fuzzy inference system. Results indicate that the system accurately classifies stomach ailments based on user-reported symptoms, facilitating early diagnosis and treatment. The novelty of this research lies in the application of the Fuzzy Tsukamoto method, which allows for nuanced symptom analysis and inference, providing a more accessible means for the general public to identify potential gastric diseases. Furthermore, the system design includes flowcharts, data flow diagrams, and entity relationship diagrams to ensure a user-friendly interface. The implications of this study are significant, as it offers a robust tool for early detection of gastric diseases, thereby potentially improving patient outcomes and reducing healthcare costs associated with late-stage interventions. This expert system not only assists in diagnosing gastric conditions but also serves as a valuable resource for enhancing the understanding of symptomology in gastroenterology.
Chronic atrophic gastritis (CAG) is an underdiagnosed condition characterised by translational features going beyond the strict field of gastroenterology as it may manifest itself by a variable spectrum of gastric and extra-gastric symptoms and signs. It is relatively common among older adults in different parts of the world, but large variations exist. Helicobacter pylori-related CAG [multifocal] and autoimmune CAG (corpus-restricted) are apparently two different diseases, but they display overlapping features. Patients with cobalamin and/or iron deficiency anaemia or autoimmune disorders, including autoimmune thyroiditis and type 1 diabetes mellitus, should be offered screening for CAG. Pepsinogens, gastrin-17, and anti-H. pylori antibodies serum assays seem to be reliable non-invasive screening tools for the presence of CAG, helpful to identify individuals to refer to gastroscopy with five standard gastric biopsies in order to obtain histological confirmation of diagnosis. Patients with CAG are at increased risk of developing gastric cancer, and they should be estimated with histological staging systems (OLGA or OLGIM). H. pylori eradication may be beneficial by modifying the natural history of atrophy, but not that of intestinal metaplasia. Patients with advanced stages of CAG (Stage III/IV OLGA or OLGIM) should undergo endoscopic surveillance every three years, those with autoimmune CAG every three-five years. In patients with CAG, a screening for autoimmune thyroid disease and micronutrient deficiencies, including iron and vitamin B12, should be performed. The optimal treatment for dyspeptic symptoms in patients with CAG remains to be defined. Proton pump inhibitors are not indicated in hypochlorhydric CAG patients.