Cloud-Driven Data Engineering: Multi-Layered Architecture for Semantic Interoperability in Healthcare

Medical information systems are in perpetual evolution which makes them different from each other in each hospital. These different systems compose a heterogeneous, distributed system with high complexity. Thus interoperability of medical information systems is one of the main challenges of the IT society. Semantic interoperability in healthcare is especially important when all the varying types of data need to interact. A lot of works tried to solve even partially this problem of interoperability. This paper highlights the most relevant of them and presents a comparative study between new technologies and research trends to resolve heterogeneity issues of medical information systems.

Artificial intelligence (AI) in healthcare analytics represents a transformative force with the potential to revolutionize clinical decision-making, operational efficiency, and patient-centered care. While its applications in precision medicine, predictive modeling, and administrative optimization are promising, the integration of AI also raises critical ethical, governance, and trust-related concerns. This paper explores the evolution, use cases, and associated challenges of AI in healthcare analytics, emphasizing the dual-use nature of these technologies. Drawing on agency theory and moral responsibility theory, the study highlights the shared responsibilities of developers, healthcare institutions, regulators, and patients in ensuring equitable, transparent, and accountable AI deployment. It proposes a multi-pronged strategy combining technical safeguards, regulatory oversight, and ethical capacity-building to align AI innovation with public interest. Through this comprehensive analysis, the paper offers guidance for ethically sustainable integration of AI in healthcare systems while preserving human dignity and social trust.

Semantic Mapping of Component Framework Interface Ontologies for Interoperability of Vehicle Applications

Ontology similarity calculation and ontology mapping are important research topics in information retrieval. By learning optimization similarity function, we propose the new algorithm for ontology similarity measure and ontology mapping. The stability of ontology algorithms is studied by adopting a strategy which adjusts the sample set by deleting one or two element from it. Relationship between uniform loss stability and uniform score stability is investigated. A sufficient condition for uniform score stability is given. The result of our work shows that if for any (v,v') ∈ V × V, a kernel function K((v,v'), (v,v')) has a limited upper bound, then the ontology algorithm which minimizes the regularization empirical l-error will have good uniform score stability. Also, two experiments results show that the proposed algorithm has high accuracy and efficiency for similarity calculation and ontology mapping. Index Terms—Ontology, similarity calculation, ontology mapping.

Integrating Artificial Intelligence Techniques in Medical Bacteriology is a scientific research paper that explores the transformative role of artificial intelligence (AI) in enhancing diagnostic and therapeutic practices within the field of bacteriology. As AI technologies increasingly permeate healthcare, this study provides a comprehensive analysis of how machine learning (ML) and deep learning algorithms can significantly improve the accuracy and timeliness of bacterial pathogen detection and antibiotic resistance management, marking a notable advancement in laboratory medicine.[1-][2] The research emphasizes the potential of AI to streamline workflows and enhance operational efficiency in medical bacteriology. By automating processes such as error detection, result interpretation, and image analysis, AI systems can significantly reduce the turnaround time for diagnostic results, ultimately leading to improved patient outcomes.[3][4] The paper also highlights the importance of data quality management in the development of AI models, advocating for adherence to established standards throughout the dataset lifecycle to ensure the reliability of AI applications in clinical settings.[5]Despite the promising advancements, the integration of AI in healthcare is not without its challenges. The study discusses the current limitations in the clinical efficacy and cost-effectiveness of AI applications, revealing a gap between research outcomes and real-world implementation.[4] Additionally, ethical considerations surrounding data privacy and algorithmic transparency are addressed, emphasizing the need for regulatory frameworks that promote safe and equitable AI use in medical practice.[6]Overall, this research provides a critical examination of the trends and innovations in AI applications in medical bacteriology, employing statistical analysis and bibliometric techniques to identify research hotspots and emerging patterns in the field from 2010 to 2024.[7][6] By integrating AI methodologies, the study aims to lay the groundwork for future research directions and improve quality assurance standards

Background Artificial Intelligence (AI) is transforming how organizations operate and design digital services. Beyond customer-facing applications, AI is increasingly embedded in internal workflows, enabling faster decision-making and predictive insights. However, most research on AI and User Experience (UX) focuses on external users, leaving a gap in understanding how internal users within large organizations adopt and trust AI systems. This study addresses that gap by exploring AI adoption and user experience from an internal perspective, emphasizing explainability and trust as key human-centered factors in enterprise contexts. Abstract Purpose This study aims to examine how AI reshapes UX practices through the framework of Speed, Insight, and Trust. It highlights the operational benefits and adoption challenges that emerge when predictive AI systems are integrated into internal workflows within a large telecommunications enterprise. Design/Methodology/Approach A conceptual and case-based approach was employed. The case study was conducted at Witel Jakarta Outer, a regional operational unit under Telkom Indonesia Regional 2, responsible for managing connectivity and digital product services. The site was selected as a pilot project under a Deputy Director directive due to its readiness for AI integration. The internally developed predictive AI model supported three processes: (1) Sales—lead and product recommendations, (2) Activation—automated order validation, and (3) Assurance—churn prediction up to two months in advance. Data were collected from system performance metrics and qualitative feedback from internal users. Findings The pilot results showed that potential leads generated increased from 22,000 to 66,000, order verification time decreased from 1.42 to 0.96 hours, and churn risks were predicted two months earlier. Despite these gains, internal teams hesitated to fully adopt AI recommendations, revealing challenges of trust and explainability. Research The study is based on a single one-month pilot in one organizational context, which may limit generalizability. Broader empirical research across multiple settings is needed to validate the findings. Originality/Value By framing AI’s impact through Speed, Insight, and Trust, this study provides a practical lens for evaluating AI-driven UX in enterprise settings. It bridges conceptual discussion with real-world implementation, emphasizing that AI’s success depends not only on performance but also on internal trust and adoption.

Artificial intelligence (AI) is revolutionizing the fashion industry through increased operational efficiency and the promotion of sustainable innovation. One important topic that this research aims to answer is how fashion companies may effectively use AI technologies to optimize lean production processes while addressing environmental challenges. This study will look at how AI can be applied to lean manufacturing and sustainability to better understand how it may alter corporate management practices in the US fashion industry. This study is significant because it can provide insight into how AI may advance efficiency and sustainability, two aspects that are critical to the future competitiveness of the industry. The lack of comprehensive frameworks that systematically integrate AI into the current manufacturing processes used in the apparel sector is the main emphasis of this study. Fashion firms must adjust to technology developments to stay relevant in a market that is changing quickly due to changing consumer preferences and heightened environmental scrutiny, which is why this study is significant. The scope of this study includes an analysis of AI's contribution to sustainable innovation and lean manufacturing, offering a comprehensive perspective of the effects of the industry. The study aims to explore how artificial intelligence (AI) may improve operational efficiency and encourage sustainable practices in the fashion sector in the United States. A substantial research gap concerning the use of AI technology in lean manufacturing frameworks designed especially for fashion companies is identified by this study. The methodology used involves a qualitative study of secondary data, with an emphasis on industry reports and case studies that provide light on contemporary issues and practices. Important discoveries show that artificial intelligence (AI) technologies greatly enhance demand forecasting, streamline production processes, and enable customized consumer experiences, all of which contribute to lower waste and more operational efficiency. To ensure successful implementation, however, issues including staff displacement and change resistance must be resolved. Best practices for utilizing AI in fashion management are highlighted in this paper, which offers insightful information to practitioners and scholars alike. In summary, this study offers a solid basis for further research into the revolutionary potential of AI, even while it recognizes limitations regarding the generalizability of findings across various fashion sector areas. Longitudinal research evaluating the long-term effects of AI adoption and consumer attitudes toward AI-driven personalization are potential avenues for future investigation. Furthermore, legislative suggestions can emphasize encouraging cooperation between digital companies and fashion labels to enable successful AI integration. This abstract summarizes the main findings of the study and lays the groundwork for a more thorough investigation of how AI may influence business management in the US fashion sector going forward.

ObjectivesTo explore the views of intensive care professionals in high-income countries (HICs) and lower-to-middle-income countries (LMICs) regarding the use and implementation of artificial intelligence (AI) technologies in intensive care units...

PURPOSE: Accurately forecasting real estate prices presents a significant challenge due to the complex interplay of economic, social, and spatial variables. Artificial Intelligence (AI) offers a promising avenue to enhance predictive accuracy by integrating advanced analytical techniques. This study examines the role of AI in real estate pricing by identifying prevailing research trends and assessing its practical applications in cost reduction, process automation, and decision-making. METHODOLOGY: A two-pronged approach was employed, combining bibliometric analysis with insights from expert interviews. The bibliometric study mapped the evolution of AI-related research in real estate, highlighting key themes and methodological trends. The case study analysis provided complementary insights into how AI is applied in industry practice, particularly in streamlining construction processes, automating asset monitoring, and enhancing marketing strategies. FINDINGS: The study identifies a growing academic interest in AI-driven real estate research, particularly since 2018, with an increasing focus on machine learning, deep learning, and geospatial analysis. While scholarly research aligns with market needs in price forecasting and decision support, gaps remain in topics like operational efficiency and automation. Empirical evidence suggests that AI applications extend beyond price estimation, influencing profitability through process acceleration and cost optimization. However, international collaboration in the field remains low, limiting the scalability of AI-driven pricing models across different market contexts. IMPLICATIONS: The findings underscore AI’s transformative impact on real estate by bridging research and industry applications. Theoretically, the study highlights the shift from management-oriented frameworks toward data-driven and algorithmic approaches. AI enhances price estimation by integrating diverse data sources and improving risk assessment. However, challenges persist, including data accessibility, algorithm interpretability, and the demand for specialized AI expertise. Addressing these issues could unlock further advancements in predictive modeling and real estate market efficiency. ORIGINALITY AND VALUE: This research provides a comprehensive perspective on AI’s role in real estate pricing by integrating bibliometric analysis with case study insights. It extends existing knowledge by identifying key research gaps, emphasizing the need for interdisciplinary collaboration, and demonstrating AI’s potential beyond price prediction to broader market dynamics and operational efficiencies.

Precision medicine seeks to tailor care such that patients receive individualized treatment based on their specific presentation, biology, and risk factors. Artificial intelligence, defined as the field of computational systems that perform tasks requiring human-like intelligence, such as prediction, pattern recognition, and decision-making, is revolutionizing precision medicine through enhanced diagnostic accuracy, optimized treatments, and improved health outcomes. However, the benefits of artificial intelligence can only be realized if clinicians understand the technology’s limitations and strengths, and if developers appreciate the clinical, systemic, and workflow contexts in which their tools were developed and will be introduced. Without this mutual understanding, risks include automation bias, exacerbations of existing healthcare inequities, breaches of patient privacy, and ethical dilemmas that may erode trust in healthcare systems. To address these challenges, the Temerty Centre for Artificial Intelligence Research and Education in Medicine at the University of Toronto has developed an interdisciplinary educational team and mandate. The mandate is organized into three guiding domains—principles, topics, and methods—that together provide a structured yet adaptable approach to artificial intelligence education. This commentary presents the rationale for this mandate and discusses its implications for precision medicine. Central to the mandate are commitments to formal, integrated training across disciplines, an emphasis on the ability to critically appraise artificial intelligence tools, and the delivery of interactive, evolving educational programs that are tailored to professional roles. As artificial intelligence continues to shape the landscape of healthcare, interdisciplinary and adaptive education will be critical to ensuring ethical artificial intelligence deployment and use, continued patient-centered care, and personalized medicine.

Trailblazing precision medicine in Europe: A joint view by Genomic Medicine Sweden and the Centers for Personalized Medicine, ZPM, in Germany

BackgroundSemantic interoperability is essential for improving data quality and sharing. The ISO/IEC 11179 Metadata Registry (MDR) standard has been highlighted as a solution for standardizing and registering clinical data elements (DEs). However, the standard model has both structural and semantic limitations, and the number of DEs continues to increase due to poor term reusability. Semantic types and constraints are lacking for comprehensively describing and evaluating DEs on real-world clinical documents.MethodsWe addressed these limitations by defining three new types of semantic relationship (dependency, composite, and variable) in our previous studies. The present study created new and further extended existing semantic types (hybrid atomic and repeated and dictionary composite common data elements [CDEs]) with four constraints: ordered, operated, required, and dependent. For evaluation, we extracted all atomic and composite CDEs from five major clinical documents from five teaching hospitals in Korea, 14 Fast Healthcare Interoperability Resources (FHIR) resources from FHIR bulk sample data, and MIMIC-III (Medical Information Mart for Intensive Care) demo dataset. Metadata reusability and semantic interoperability in real clinical settings were comprehensively evaluated by applying the CDEs with our extended semantic types and constraints.ResultsAll of the CDEs (n = 1142) extracted from the 25 clinical documents were successfully integrated with a very high CDE reuse ratio (46.9%) into 586 CDEs (259 atomic and 20 unique composite CDEs), and all of CDEs (n = 238) extracted from the 14 FHIR resources of FHIR bulk sample data were successfully integrated with high CDE reuse ration (59.7%) into 96 CDEs (21 atomic and 28 unique composite CDEs), which improved the semantic integrity and interoperability without any semantic loss. Moreover, the most complex data structures from two CDE projects were successfully encoded with rich semantics and semantic integrity.ConclusionMDR-based extended semantic types and constraints can facilitate comprehensive representation of clinical documents with rich semantics, and improved semantic interoperability without semantic loss.

Semantic interoperability is the key technology to enable evolution of the Internet of Things (IoT) from its current state of independent vertical IoT silos to interconnected IoT platform federations. This paper analyzes the possible solution space on how to achieve semantic interoperability and presents five possible approaches in detail together with a discussion on implementation issues. It presents the H2020 symbIoTe project as an example on how semantic interoperability can be achieved using semantic mapping and SPARQL query re-writing. We conclude that the found approaches together with the proposed technologies have the potential to act as corner stone technologies for achieving semantic interoperability.

Artificial intelligence-based suicide prevention and prediction: A systematic review (2019–2023)

This study aims to elucidate the pivotal role of Artificial Intelligence (AI) in driving the transformation of precision medicine, comprehensively analyzing how it reshapes healthcare systems from traditional diagnosis and treatment paradigms into personalized health management ecosystems. A comprehensive narrative review was conducted to systematically synthesize and critically evaluate the innovative applications, paradigm shifts, and future prospects of AI across the entire precision medicine value chain. A comprehensive literature search was performed across multiple databases up to April 30, 2025, with a focus on the clinical implementation and breakthroughs of technologies such as deep learning (DL), machine learning (ML), and natural language processing (NLP). AI technologies have significantly enhanced the accuracy and efficiency of disease diagnosis through medical image analysis, genomics, and multimodal data fusion. At the treatment level, AI enables the development of personalized therapeutic plans and drug dosing optimization, while revolutionarily accelerating the drug development pipeline from discovery to clinical trials. Integrated with wearable devices and telemedicine platforms, AI facilitates full-cycle health monitoring. However, the clinical translation of AI faces challenges, including an uneven evidence base, insufficient model generalizability, and ethical concerns regarding data privacy, algorithmic fairness, and interpretability. AI is a key driver of paradigm shift in precision medicine. To address existing challenges, future efforts should focus on generating more robust clinical evidence, adopting technologies like federated learning to ensure data privacy, and promoting the human-centered, collaborative framework of Symbiotic AI (SAI). By establishing sound ethical and governance structures, the deployment of AI technologies can be ensured to be not only efficient and advanced but also equitable and trustworthy, ultimately paving the way for an intelligent and inclusive healthcare ecosystem.