This research focuses on ontology-driven conversational agents (CAs) that harness large language models (LLMs) and their mediating role in performing collective tasks and facilitating knowledge-sharing capabilities among multiple healthcare stakeholders. The research addresses how CAs can promote a therapeutic working alliance and foster trustful human–AI collaboration between emergency department (ED) stakeholders, thereby supporting collaborative tasks with healthcare professionals (HPs). The research contributes to developing a service-oriented human–AI collaborative framework (SHAICF) to promote co-creation and collaborative learning among patients, CAs, and HPs, and improve information flow procedures within the ED. The research incorporates agile heavy-weight ontology engineering methodology (OEM) rooted in the design science research method (DSRM) to construct an ontological metadata model (PEDology), which underpins the development of semantic artifacts. A customized OEM is used to address the issues mentioned earlier. The shared ontological model framework helps developers to build AI-based information systems (ISs) integrated with LLMs’ capabilities to comprehend, interpret, and respond to complex healthcare queries by leveraging the structured knowledge embedded within ontologies such as PEDology. As a result, LLMs facilitate on-demand health-related services regarding patients and HPs and assist in improving information provision, quality care, and patient workflows within the ED.© 2025 by the authors.

This research uses design science research methodology to present a comparativesynthesis of balancing between materialized and virtualized knowledge graph approaches articulating domain-centric monolithic federated virtual knowledge graphs (FVKGs) leveraging data mapping techniques in healthcare information systems (HIS). Materialized knowledge graphs enable fast query execution by physical instantiation of graph structures. In contrast, virtualized knowledge graphs using the Ontop virtual system to fetch real-time, on-demand querying over disparate data sources. This research thoroughly examines the strengths, shortcomings, and suitability of usage in diverse HIS applications landscape. Key critical factors such as scalability, performance, maintenance overhead, and query efficiency are analyzed to evaluate the effectiveness of each approach. The authors use a federated ontological model leveraging disparate static data models in materialization and support real-time, dynamic changing datasets in virtualization to construct FVKGs. The experimental findings showcase ontological artifacts, balancing between approaches, enhancing data integration and interoperability capabilities to optimize HIS.

The research focuses on the limitations of traditional systems in optimizinginformation flow in the healthcare domain. It focuses on integrating knowledge graphs(KGs) and utilizing AI-powered applications, specifically conversational agents (CAs),particularly during peak operational hours in emergency departments (EDs). Leveragingthe Cross Industry Standard Process for Data Mining (CRISP-DM) framework, the authors tailored a customized methodology, CRISP-knowledge graph (CRISP-KG), designedto harness KGs for constructing an intelligent knowledge base (KB) for CAs. This KGaugmentation empowers CAs with advanced reasoning, knowledge management, andcontext awareness abilities. We utilized a hybrid method integrating a participatory designcollaborative methodology (CM) and Methontology to construct a domain-centric robustformal ontological model depicting and mapping information flow during peak hours inEDs. The ultimate objective is to empower CAs with intelligent KBs, enabling seamlessinteraction with end users and enhancing the quality of care within EDs. The authorsleveraged semantic web rule language (SWRL) to enhance inferencing capabilities withinthe KG framework further, facilitating efficient information management for assistinghealthcare practitioners and patients. This innovative assistive solution helps efficientlymanage information flow and information provision during peak hours. It also leads tobetter care outcomes and streamlined workflows within EDs. © 2025 by the authors.

Conversational agents (CAs) have emerged as powerful tools for human-computer interaction, of ering natural language interfaces and personalized assistance, particularly in healthcare. Thedevelopment of CAs leveraging knowledge engineering (KE) techniques and LLMs necessitatestheconsideration of specific design principles (DPs) and interactive patterns to ensure their ef ectivenessand user satisfaction. This research focuses on a comprehensive analysis of the DPs andpatternscrucial for developing CA artifacts using KE techniques. To address the gap, author incorporateddesign science research methodology (DSRM) principles tailored to the modelling workshopmethodto capture domain knowledge and practitioner expertise in a new health information systemclass. Theresearch explores DPs based on meta-requirements suitable for interaction patterns andKE-basedCAs, including ontology-driven approaches. The research proposed systematic pathways, andbyapplying these DPs and patterns, developers can develop CAs exploiting LLMs to understandcomplexuser queries, provide accurate responses, and adapt to dynamic contexts.

Data fusion is a complex process where seamless semantic interoperability, data integration, accessibility, and sharing use cases are crucial across health-distributed systems. We employedafederated virtualized knowledge graph (FVKG) approach to develop a robust federatedsemanticknowledge lake framework to handle aforementioned challenges ef ectively. This research presentsanovel solution, knowledge graph-as-a-platform (KGaaP) that leverages ontology-based accessdata(OBDA) and FedX federation engine to establish a scalable and interoperable data platformthat aimsto handle the fusion of healthcare data from disparate data sources, including structured, unstructured, and semi-structured data models to build seamless federated semantic applications. Asaresult, we suggest KGaaP leveraging the FVKG framework that incorporates Ontop’s andFedX’sfederated query engines to construct a monolithic KGaaP, integrating ontology-driven artifactsandensuring semantic enlightenment using schema-mapping techniques and enhanced dataservices. Integrating KGaaP enhances query ef iciency, flexibility, and scalability, driving better decision-making and improving healthcare outcomes.

Large Language Models (LLMs) (Brown et al., 2020) have rapidly advanced, revolutionized and substantially reshaped automated AI-driven knowledge discovery methodologies. However, the opaque embeddings of LLMs often lack semantic interpretability and integration with disparate enterprise knowledge sources. Organizations continue to experience fragmentation across information ecosystems arising from isolated data silos and the continual evolution of semantic standards. There is an urgent need for platforms that holistically bridge LLMs’ embeddings, enterprise data, and semantic interoperability. Recently, the Knowledge Graphs (KGs) (Zhong et al., 2023) and LLMs complement each other and are emerging as a critical pathway for intelligent, context-aware, domain-centric AI-powered applications development (e.g., conversational agents (CAs), recommendation systems) (TudoCar et al., 2020) in various domains, especially in healthcare. Existing data integration approaches (Elmore et al., 2015) frequently conceptualize KGs as static and isolated repositories, thereby overlooking their potential as dynamic, conversational platforms. This Treo talk highlights the importance of the proposed Knowledge Graph as a Platform (KGaaP) (Figure 1) as a solution, where various domain-centric applications can be developed, embedding LLMs and leveraging the federated semantic knowledge lake (FSKL) framework. This federated, semantic, and interoperable environment embeds domain-specific knowledge into LLMs workflows, enabling dynamic, multi-source conversational intelligence.  Recently, most organizations have increasingly relied on LLMs for decision support. Yet, LLM outputs are prone to hallucinations and lack explainability when disconnected from disparate data sources, including structured, unstructured, and authoritative factual knowledge. To avoid hallucination, semantic technological landscape resources, including ontologies, KGs, RDF datasets, and linked open data vocabularies, remain underutilized and play a pivotal role in harmonizing, and consolidating data fragmentation across organizational silos and incompatibilities in schema design efficiently. Addressing these challenges requires a unifying framework to bridge AI reasoning with federated, semantically interoperable knowledge assets in a scalable and query-efficient manner. The KGaaP operationalizes a FSKL Framework by utilizing: i) Ontop (a virtual KGs system) and Federated Query Engines like, FedX to unify heterogeneous SPARQL endpoints services; ii) Semantic Interoperability Layers using domain ontologies (e.g., SNOMED CT, LOINC) for constructing federated ontology and SHACL validation; iii) LLM-KG Embedding Integration, where vector embeddings are aligned with KG entities, enabling hybrid retrieval (combination of symbolic and neural); iv) Conversational Agent Layer that supports RAG (Retrieval-Augmented Generation) pipelines, dynamically grounding LLM responses in federated KG queries with provenance metadata. This research leads new avenues for IS research, how KGs plus LLMs as active participants in digital transformation, advancing explainable AI, cross-organizational knowledge interoperability, and data governance. The KGaaP paradigm supports emerging IS demands for trustworthy and federated AI ecosystems.

Healthcare 4.0 (4.0) requires the integration of technological breakthroughs to enable transformational innovation using the Industry 4.0 (I4.0) technology landscape. The study reveals its importance, necessity, relevance, awareness, and implementation for digital transformation. H4.0 is a technological catalyst for accelerating exponential growth by integrating cutting-edge industrial and technological landscapes. It enables gathering data from various healthcare sensors and facilitates human-machine interaction (HMI). The study highlights developing Conceptual Technological Framework 4.0 (CTF4.0), a revolutionized living space for individuals with neurological disorders, particularly multiple sclerosis (MS), strategically positioned within the I4.0 spectrum. The study targets a tailored-made personalized environment that becomes the game-changer for empowering individuals with neurological disorders, relieving symptoms and improving overall well-being through the lens of I4.0 paradigms and meticulous healthcare examination. Addressing irregularities and potential risks associated with stress, fatigue, eye impairment, and memory loss, the authors target a fundamental question of exploiting I4.0 advances to tailor sophisticated environments to the unique needs and preferences of MS patients. The study is well-grounded and has a real-world perspective, as garnered from discussions with MS community members at the Karolinska Institute (KI) in Solna, Stockholm. The CTF4.0 framework ensures that it transcends theoretical constructs and a solution deeply rooted in the lived experiences and perspectives of those it serves. As a result, our study sets the stage for developing a context-aware, personalized, automated smart home health ecosystem tailored explicitly for the neurological disorders community. By granting individuals autonomy over their living environments, we envision spaces that foster independence, alleviate symptoms, and promote overall well-being. © The Author(s)

Over the past decade, the exponential growth of the Electric Vehi- cle (EV) industry has experienced unprecedented surge and diversification. This multifaceted field results in building comprehensive, cross-domain, extensible, sophisticated knowledge management systems that incorporate future needs and address battery-related information integration challenges. It needs sophisticated knowledge representation techniques such as ontologies and knowledge graphs (KGs) leveraging federated approaches to integrate diverse, disparate data from distributed sources, resolve data interoperability challenges, and also present in a standardized format to build various battery-related services on top of virtual data integration layer, without the need for data materialization. We propose the state-of-the-art federated virtual knowledge graph (FVKG) framework embed- ded with the virtualized knowledge graph (VKG) methodology to handle the auspicious challenges effectively across distributed environments. The suggested FVKG framework offers a unified view of scattered data sources and different models to create a virtual data federation leveraging Ontop, resolving data bot- tlenecks efficiently. The FVKG assists in automated data mapping from diverse, relational sources, enabling intuitive queries based on domain-centric federated ontology and loads into the VKG intelligently. The FVKG utilizes a virtualized technique to reduce data migration, guarantees low latency and freshness, and facilitates real-time access while upholding integrity and coherence throughout the federation system. The FVKG incorporates ontology-based data access (OBDA) to build a monolithic ontological model, integrating ontology-driven artifacts and ensuring semantic alignment using schema mapping techniques. As a result, the FVKG targets enabling more efficient battery performance analysis, predictive maintenance, and strategic decision-making in the EV ecosystem. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026

Data integration (DI) and semantic interoperability (SI) are critical in healthcare, enabling seamless, patient-centric data sharing across systems to meet the demand for instant, unambiguous access to health information. Federated information systems (FIS) highlight auspicious issues for seamless DI and SI stemming from diverse data sources or models. We present a hybrid ontology-based design science research engineering (ODSRE) methodology that combines design science activities with ontology engineering principles to address the above-mentioned issues. The ODSRE constructs a systematic mechanism leveraging the Ontop virtual paradigm to establish a state-of-the-art federated virtual knowledge graph framework (FVKG) embedded virtualized knowledge graph approach to mitigate the aforementioned challenges effectively. The proposed FVKG helps construct a virtualized data federation leveraging the Ontop semantic query engine that effectively resolves data bottlenecks. Using a virtualized technique, the FVKG helps to reduce data migration, ensures low latency and dynamic freshness, and facilitates real-time access while upholding integrity and coherence throughout the federation system. As a result, we suggest a customized framework for constructing ontological monolithic semantic artifacts, especially in FIS. The proposed FVKG incorporates ontology-based data access (OBDA) to build a monolithic virtualized repository that integrates various ontological-driven artifacts and ensures semantic alignments using schema mapping techniques. © 2025 by the authors.

Developing a battery ontology to represent battery management knowledge is crucial in the new sustainable and green energy era. As battery production revenue is projected to exceed 300 billion US dollars annually by 2030, researchers are exploring new battery materials, models, standards, and manufacturing processes. AI and ML methods are being employed to manage battery manufacturing and enhance performance. Data representation techniques and formats are important for enhancing the expressiveness of battery data and improving battery quality. This paper presents an ontology for creating a battery knowledge graph to address data interoperability challenges and share battery data among different actors. The battery ontology includes various types of knowledge, such as domain knowledge, battery applications, and core battery-specific knowledge. The ontology was evaluated through competency questions and usability tests. It aims to enhance battery production and design by facilitating efficient communication and data exchange between battery management systems and applications. This research has significant societal, economic, and environmental impacts as it contributes to developing more efficient and sustainable batteries. © 2024 Author.