Search Results (129)

Background: Drug-coated balloons (DCBs) have emerged as a “leave-nothing-behind” strategy in percutaneous coronary intervention (PCI), with potential advantages over drug-eluting stents (DES) in selected patients with acute coronary syndrome (ACS). Methods: We performed a narrative review of randomized controlled trials, registries, and meta-analyses evaluating DCB therapy in ACS, including PEPCAD NSTEMI, REVELATION, BASKET-SMALL 2, AGENT IDE, REC-CAGEFREE I/II, and the ongoing TRANSFORM II trial. Articles were identified through searches of PubMed/MEDLINE, Embase, Scopus, Web of Science, and Cochrane CENTRAL covering January 2005 to February 2026. Results: Across published studies, DCBs have shown outcomes that are non-inferior to those of DES in selected ACS subsets, together with a lower risk of major bleeding attributable to shorter dual antiplatelet therapy (DAPT) requirements. Advances in intravascular imaging and lesion preparation, alongside emerging applications of artificial intelligence (AI) and robotic-assisted PCI, may further improve DCB performance, although evidence specific to DCB use in ACS remains limited for these adjunctive technologies. Conclusions: DCBs are a reasonable alternative to DES in selected patients with ACS, particularly those at high bleeding risk or with lesion subsets in which DES perform less well (small vessels, in-stent restenosis, bifurcations, diffuse disease). Adequately powered randomized trials with long-term follow-up are required before broader recommendations can be made. Full article

Large language models (LLMs) are increasingly being used in education, yet their correctness alone does not capture the quality, reliability, or pedagogical validity of their problem-solving behavior, especially in mathematics, where multi-step logic, symbolic reasoning, and conceptual clarity are critical. Conventional evaluation methods largely focus on final answer accuracy and overlook the reasoning process. To address this gap, we introduce a novel interpretability framework for analyzing LLM-generated solutions using undergraduate calculus problems as a representative domain. Our approach combines reasoning flow extraction and decomposing solutions into semantically labeled operations and concepts with prompt ablation analysis to assess input salience and output stability. Using structured metrics such as reasoning complexity, phrase sensitivity, and robustness, we evaluated the model behavior on real Calculus I–III university exams and compared it with the performances of students enrolled in the courses. Our findings revealed that LLMs often produce syntactically fluent yet conceptually flawed solutions with reasoning patterns sensitive to prompt phrasing and input variation. This framework enables a fine-grained diagnosis of reasoning failures, supports curriculum alignment, and informs the design of interpretable AI-assisted feedback tools. The framework was evaluated on Gemma 3, an open-access large language model, across zero-shot, retrieval-augmented generation, and contextual retrieval configurations, using nine real undergraduate calculus examinations from three course levels. To our knowledge, this is the first paper to apply a combined reasoning flow decomposition and prompt ablation framework to real undergraduate calculus examinations, benchmarked against actual student cohort performance, laying the foundation for the transparent and responsible deployment of AI in STEM learning environments. Full article

The emergence of artificial intelligence (AI) tools, particularly generative models, in the last five years has fundamentally transformed the framework and methodologies of learning in higher education. Students are integrating AI for producing new ideas, assisted and personalized search, academic writing, advanced data analysis, and personalized learning. For this reason, an update of the theoretical and conceptual framework regarding the adoption of technologies in the educational environment is required. Based on traditional Technology Acceptance Model/Unified Theory of Acceptance and Use of Technology (TAM/UTAUT) models, we propose a new Partial Least Squares Structural Equation Modeling (PLS-SEM) model developed for the context of AI in higher education. The novelty of the model lies in the integration of the mediating relationship through trust (trust in AI outputs, TAIO) between perceived academic integrity risk (PAIR) and behavioral intention to use (BI), while anchoring perceived learning utility (PUL) and perceived effort expectancy (PEE) in AI literacy-specific self-efficacy (AILSE). The model is tested using a sample of 339 higher education students from economics and computer science specializations and validated using the R environment and the SEMinR package as specific software tools. Our proposed research hypotheses consider six reflective latent constructs and a mediating relationship, which we analyze using validated PLS-SEM techniques. All items included in the model constructs are formulated for use in university educational contexts and are adapted to specific AI tools for learning in the university environment. Full article

Transitioning toward efficient and digital industrial design requires preliminary tools that support early decision-making in plant layout studies. This qualitative and exploratory study analyzes an Artificial Intelligence (AI)-assisted and Augmented Reality (AR)-supported workflow within the Systematic Layout Planning (SLP) framework for the preliminary spatial evaluation of a cosmetic emulsion production plant. The study was developed as a case study based on a previously reported layout for obtaining cosmetic emulsions from Amazonian oils. A top-view layout was examined through structured prompts aligned with SLP criteria, including product journey, activity relationships, relational diagrams, and space requirements. ChatGPT was used only as a qualitative reasoning assistant, without optimization, prediction, mathematical modeling, or algorithmic functions. After the AI-assisted review, the refined layout was represented in three dimensions and visualized through AR in a real environment. The results identified potential improvements related to operational flow, traceability, critical area relationships, and spatial organization. AR-assisted visualization provided preliminary visual evidence of compatibility between the refined layout and the selected site, supporting an early review of circulation, access, and volumetric behavior. The sequential integration of SLP, AI, and AR is proposed as an exploratory workflow for early-stage layout evaluation, pending future quantitative validation studies and expert technical review. Full article

Nowadays, Python is very popular as the first programming language for novices, including high school students, to learn due to its short code features with rich libraries. Thus, it is important to provide a learning environment supporting studies starting from the fundamentals, since students have no knowledge on how a program runs on a computer. Previously, we have developed a web-based programming learning assistant system (PLAS) to allow the self-study of major programming languages, including Python, by university students. It offers several types of exercise problems that have different learning goals and levels for step-by-step study. Any student answer is automatically marked at the answer interface for quick feedback. However, PLAS has not implemented functions to assist the learning needs of high school-level students. In this paper, we propose a novice-friendly answer interface for a Python programming learning assistant system (PyPLAS) that introduces a code behavior visualization and an AI assistant with learning logs. The visualization allows learners to observe the changes in variable states and the control flow. The assistant provides multi-level hints during learning and reflective feedback after it by analyzing the logs based on engagement, reasoning strategies, learning pace, and tool usage. For evaluation, we implemented the proposed interface using Python Flask for the web platform and Ollama as a locally deployed AI model. A pilot application was conducted with high school students solving introductory Python exercises in PyPLAS. The results showed high task completion, positive questionnaire responses toward embedded visualization and interface usability, and teacher-observed usefulness of the four-dimensional learning analytics for interpreting learner behaviors. These findings provide preliminary evidence for the feasibility and practical value of the proposed interface, while larger controlled studies are required to validate its instructional effectiveness. Full article

Telemedicine has become a routine component of healthcare delivery, creating a need for dedicated undergraduate training in teleconsultation-specific competencies. Although artificial intelligence (AI)-assisted educational systems have been proposed as scalable tools to support teleconsultation training, the evidence remains fragmented, and their educational role is not yet clearly defined. Objective: To map and critically synthesize empirical evidence on AI-assisted teleconsultation training systems used in undergraduate medical education, with attention to skill domains, system capabilities, and implementation considerations. Methods: A structured narrative review with transparent search and study selection procedures was conducted. Literature published between January 2019 and December 2025 was identified through searches of major bibliographic databases and supplementary semantic and citation-based sources. Studies involving undergraduate medical students and evaluating AI-assisted interventions targeting teleconsultation-related skills were included. Results: Eight empirical full-text studies met the final eligibility criteria and were included in the structured narrative synthesis. Across the included studies, AI-assisted systems tended to show favorable patterns in structured domains such as verbal communication, history-taking, and selected aspects of early clinical reasoning during virtual consultations. Evidence regarding nonverbal communication and empathic or relational skills was more limited and methodologically heterogeneous, and human-based simulation remained important in these domains. Students generally reported favorable perceptions of usability, accessibility, and psychological safety, although satisfaction and perceived realism were not uniformly superior to human-based approaches. AI-assisted systems also appeared scalable and potentially cost-efficient, particularly as preparatory or supplementary training modalities. Conclusions: Current evidence suggests that AI-assisted teleconsultation training systems may be useful as preparatory and supportive tools in undergraduate medical education, particularly for structured and repeatable components of remote consultation practice. However, the evidence base remains limited and heterogeneous, and these systems do not replace human-led training for relational, nonverbal, and context-sensitive competencies. Their educational value appears greatest within blended training models that align platform capabilities with specific teleconsultation skills. Full article

Structured radiology reporting can improve clinical decision support by standardizing clinical findings into hierarchical formats. However, thousands of questions in structured report templates about clinical findings are prohibitively time-consuming, which can limit clinical adoption. Furthermore, early medical VQA datasets primarily focused on free-text and independent question–answer pairs while a recent dataset, Rad-ReStruct, introduced a hierarchical VQA, but the accompanying model still relies heavily on flattened embedding representations and single-path text–image fusion mechanisms that inadequately handle complex hierarchical dependencies in responses. In this paper, we propose DPA-HiVQA (Dual-Path Cross-Attention for Hierarchical VQA), addressing these limitations through two key contributions: (1) multi-scale image embedding representing global semantic embeddings with patch-level spatial features from domain-specific BioViL encoder; (2) dual-path cross-attention mechanism enabling simultaneous holistic semantic understanding and fine-grained spatial reasoning. Evaluated on the Rad-ReStruct benchmark, the model substantially outperforms the established benchmark baseline with an overall F1-score and Level 3 F1-score improvement by 21.2% and 31.9%, respectively. The proposed model demonstrates that dual-path cross-attention architectures can effectively connect holistic semantic understanding and fine-grained spatial detail, paving the way for practical AI-assisted structured reporting systems that reduce radiologist burden while maintaining diagnostic accuracy. Full article

In recent years, Large Language Models (LLMs) have demonstrated strong capabilities in contextual reasoning and knowledge retrieval. However, their application in industrial domains is limited by concerns regarding data security, reliance on cloud infrastructure, and high operational costs. To address these challenges, this study proposes the use of the Model Context Protocol (MCP) as a middleware framework that enables the deployment of offline-operable Small Language Models (SLMs) for industrial data processing. MCP facilitates structured interaction between SLMs and external resources (e.g., databases, APIs, and processors), allowing secure and controlled data access without exposing proprietary systems. As illustrated in the proposed framework, user input is first processed by the SLM (Qwen-7B) for intent determination. When external data is required, MCP coordinates the invocation of relevant resources and integrates the returned results into the model. The SLM then generates the final response. This approach enables SLMs to perform local computation for contextual analysis and decision support while maintaining low computational requirements and full data locality. The proposed system eliminates dependence on cloud-based LLM services and enhances security and cost efficiency. Experimental results demonstrate that the MCP-based architecture provides a practical and effective solution for deploying intelligent assistants in industrial environments without relying on large-scale external AI services. Full article

Professional education increasingly requires graduates to make decisions in complex systems marked by multiple stakeholders, feedback, delays, uncertainty, and unintended consequences, yet systems thinking is still often taught as a set of disconnected tools rather than as an integrated professional practice. This conceptual paper adopts an integrative theory-building approach to develop a unified architecture for systems thinking in professional education, drawing purposively on systems traditions, practice-based learning, assessment scholarship, and emerging work on generative artificial intelligence (GenAI). The paper proposes four iterative practices (sensemaking and boundary setting, co-modelling and causal representation, intervention reasoning, and meta-learning) as the core architecture for learning systems thinking in professional contexts. It further translates this architecture into indicative implications for curriculum sequencing, authentic tasks, and assessment, while positioning GenAI as a cross-cutting support/risk layer that can assist iteration and critique but also introduce predictable risks such as fabricated causal links, overreliance, and false mastery. To address these risks, the paper outlines governance conditions based on traceability, uncertainty checks, stakeholder validation, and process-based assessment. Overall, the framework provides a design-oriented basis for teaching, assessing, and governing systems thinking in contemporary professional education and a foundation for future empirical testing. Full article

The integration of Geographic Information Systems (GISs) with hydrologic science has evolved over seven decades from manual catchment delineation and output visualization to AI-native spatial water intelligence, reshaping how the water cycle is observed, modeled, and managed. This review explores that evolution, from the progressively tightening coupling between GIS software and hydrologic models to an AI-assisted future in which the line between these two fields blurs and eventually dissolves completely. The evolution of GISs in hydrology is traced through four eras, stratified as: (1) the formalization of governing equations and digital terrain representations (1950–1985); (2) the initial GIS–model coupling era and the rise in watershed simulation (1985–2000); (3) open source and the start of the open data deluge (2000–2015); and (4) machine learning and cloud-native computing (2015–present). A four-level vision for the role of artificial intelligence in the next generation of spatial hydrology is then articulated, from AI-assisted GIS operation to spatially aware AI water intelligence that reasons directly over geospatial data without requiring a traditional GIS or simulation software as an intermediary. Broader limitations and challenges are also discussed. Full article

Modern machine tools are safety-critical mechatronic systems, yet shop floor maintenance from abnormal events still relies heavily on scarce expert know-how and time-consuming manual searches across heterogeneous controller documentation. This paper presents an on-premise multimodal AI assistant. It integrates large language models with retrieval augmented generation and real-time machine signals to support operator-in-the-loop fault diagnosis. The proposed system provides three tightly coupled functions: (1) alarm-grounded guidance, which answers controller alarms and recommends corrective actions by grounding generation on manuals, maintenance procedures, and historical alarm cases; (2) parameter-aware reasoning, which injects live process and health indicators (e.g., spindle temperature, vibration, and axis states) into the reasoning context through an industrial data pipeline, enabling context specific troubleshooting; and (3) vision enabled support, which retrieves similar visual cases and generates concise visual instructions when text alone is insufficient. The assistant is deployed within an intranet environment to satisfy industrial security and privacy requirements and is orchestrated via lightweight tool calling for seamless integration with existing shop floor systems. Experiments on real machine tool alarm scenarios demonstrate that the proposed system achieves 82% answer correctness for alarm Q&A and improves response consistency and time-to-resolution compared with baseline keyword search and template-based guidance. The results suggest that grounded, multimodal chatbot assistants can act as practical AI-based feedback and decision support mechanisms for mechatronic production equipment, bridging human skill gaps while enhancing reliability and maintainability. Full article

The analysis of brain data through electroencephalography (EEG) has become essential in neuroscience, affective computing, and brain–computer interfaces. Recent work associates EEG features with artificial neurotransmitter models, simulating emotions and rational–emotional decision-making using complexity theory. However, current methods face limitations: (1) linear temporal representations lacking memory and anticipation, (2) limited contextual adaptation, (3) difficulty with paradoxical affective states, and (4) absence of ethical reasoning in decision-making. We present a framework based on Sophimatics, using complex time ($t=t_{real}+i\cdot t_{imag}\in \mathbb{C}$) where $t_{real}$ represents chronology and $t_{imag}$ encodes experiential dimensions including memory depth and anticipatory imagination. The Super Time Cognitive Neural Network (STCNN) architecture enables the parallel processing of objective time sequences and subjective cognitive experiences. Our Sophimatics-assisted EEG analysis achieves: (1) two-dimensional temporal coherence integrating past experiences and future projections, (2) context-sensitive adaptation via ontological knowledge graphs, (3) interpretable symbolic reasoning compatible with clinical psychology, (4) mechanisms for resolving affective paradoxes, and (5) ethical constraints ensuring value-based decision-making. Across three case studies (emotion recognition, meditation-induced transitions, and brain–computer interface decision support), integrated Sophimatics models outperform traditional machine learning (15–22% accuracy improvement) and complexity theory models (8–14% improvement), while offering greater cognitive richness and immunity to incomplete data. Results establish a post-generative AI framework with computational wisdom: relationally interactive, ethically informed, and temporally consistent with human cognitive and affective life. The framework outlines paths toward next-generation neuromorphic systems achieving genuine understanding beyond pattern recognition. Full article

The safe integration of Large Language Models in clinical environments requires strict adherence to verified medical evidence. As part of the PARROT AI project, this study provides a systematic evaluation of how prompting strategies affect the reliability of Retrieval-Augmented Generation (RAG) pipelines using the MedQA USMLE benchmark ($N=500$). Four prompting strategies were examined: Baseline (zero-shot), Neutral, Expert Chain-of-Thought (Expert-CoT) with structured clinical reasoning, and StrictCitations with mandatory evidence grounding. The experiments covered six modern model architectures: Command R (35B), Gemma 2 (9B and 27B), Llama 3.1 (8B), Mistral Nemo (12B), and Qwen 2.5 (14B). Evaluation was conducted using the Deterministic RAG Evaluator, providing an objective assessment of grounding through the Unsupported Sentence Ratio (USR) based on TF-IDF and cosine similarity. The results indicate that structured reasoning in the Expert-CoT strategy significantly increases USR values (reaching 95–100%), as models prioritize internal diagnostic logic over verbatim context. In contrast, the StrictCitations strategy, while maintaining high USR due to the conservative evaluation threshold, achieves the highest level of verifiable grounding and source adherence. The analysis identifies a statistically significant Verbosity Signal ($r=0.81,p<0.001$), where increased response length serves as a proxy for model uncertainty and parametric leakage, a pattern particularly prominent in Llama 3.1 and Gemma 2. Overall, the findings demonstrate that prompting strategy selection is as critical for clinical reliability as model architecture. This work delivers a reproducible framework for the development of trustworthy medical AI assistants and highlights citation-enforced prompting as a vital mechanism for improving clinical safety. Full article

To address the efficiency and cost limitations of traditional manual cataloging, this study proposes a large language model-driven automated cataloging workflow in which the Metadata Extraction Agent (MEA), Description Cataloging Agent (DCA), Subject Analysis & Indexing Agent (SAIA), and Quality Control Agent (QCA) collaborate to perform cataloging tasks. Experiments are conducted using a dataset of over 33,000 CNMARC bibliographic records from a University Library, together with data from the Chinese Library Classification (5th edition). Meanwhile, the agent-based workflow framework directly employs large language models without additional enhancement techniques, thereby providing a useful experimental benchmark for evaluating future AI-assisted cataloging systems. The results show that the framework performs well in metadata recognition, bibliographic description, and macro-level classification tasks, and can relatively stably generate standardized records. However, limitations remain in fine-grained semantic indexing and the interpretation of complex contexts. Therefore, in light of the capability limitations revealed by the experimental results, the study argues that fully automated end-to-end cataloging relying solely on generative AI is not yet entirely feasible. Future improvements should integrate techniques such as retrieval-augmented generation, supervised fine-tuning, and structured reasoning prompts, while establishing traceable mechanisms to enhance the reliability of intelligent cataloging. Full article

Artificial intelligence is already being used in the administration of Justice, with various applications assisting judges in resolving cases. In particular, in criminal Justice, these applications include predictive Justice and decision-making assistance through the assessment of facts, as well as the classification of criminals into risk groups. This article examines the current regulatory and ethical framework (AI Act, Council of Europe Convention on AI, CEPEJ Ethical Charter, UNESCO and OECD principles) and develops a regulatory approach to the use of AI systems by judges and prosecutors. The methodology is based on a doctrinal analysis of international, EU, and professional ethical literature, as well as on a synthesis of principles of judicial conduct (Bangalore Principles, Magna Carta of Judges). To strike a balance between the rules of governing system use and judicial ethics, the article proposes a consistent framework of ethical principles (legitimacy, transparency, accountability, integrity, human oversight, prohibition of discrimination) and introduces a practical “line of reasoning” with key questions that judges should consider before and during the use of intelligent tools (risks, bias, proportionality, understanding of the algorithm, and impact on judicial judgment). The article concludes that AI may improve the efficiency of the justice system only when included inside a strong ethical framework and specialized training, guaranteeing that final judicial decisions remain solely human and fully aligned with the rule of law. Full article