Studies in health technology and informatics最新文献

This paper presents a GraphQL-based solution for achieving interoperability between business meta-models and FHIR resources while reducing query complexity. A GraphQL API is implemented for data retrieval from the meta-model and tested using ChilliCream's Nitro tool. It is integrated with GraphQL Mesh, which maps FHIR R5 resource types to corresponding business meta-models. The Mesh API processes queries or mutations, translates them into GraphQL API calls, and converts the results back into FHIR objects. Testing is conducted using Hive Gateway. Future work includes validating this approach through artificial medical data exchanges.

With the implementation of the EU Medical Device Regulation (MDR), clinical trials of clinical decision support systems (CDSS) now often fall under Article 82 of the MDR. This mandates systematic risk management even for academic feasibility studies. This article presents a risk management strategy based on the EDiTh project, which evaluated a CDSS for epilepsy treatment recommendations in accordance with the 2023 S2k guideline First epileptic seizure and epilepsy in adulthood. A Preliminary Hazard Analysis and System Failure Mode and Effects Analysis identified key error types such as incorrect diagnoses or dosing recommendations. Due to the potential for catastrophic harm, a dual-visit study design was implemented, including a second, blinded expert consultation via videoconference to independently confirm diagnosis and treatment decisions. This design supports both risk mitigation and assessment of guideline adherence as the primary endpoint. The risk matrix and study setup illustrate how safety and regulatory requirements can be met in academic environments, while offering insights for future MDR-compliant investigations of digital health technologies.

The focus of this study is the evaluation of electromedical devices through different methods of analysis, thanks to which it is possible to determine the obsolescence and therefore the need for decommissioning or revaluation of the same. The study has been conducted in parallel with the wave of renewal that is involving the IRCCS Giannina Gaslini Institute, particularly with the construction of the new Pavilion Zero, organized by intensity of care. This transformation requires a reorganization and awareness of all the existing medical equipment, along with the need for appropriate management, redistribution, and, in some cases, disposal. To support this process, the present study focuses on the evaluation of medical devices within the Institute, through the use of two different assessment methodologies: MVO (Obsolescence Evaluation Method) and a custom-developed index based on fuzzy logic. The analysis involved more than 8,000 devices. The first index (MVO) was developed by the company, which is responsible for maintaining medical devices within the Institute, namely Hospital Consulting S.p.A., which has used some objective parameters from the internal database. The second one was designed by the authors using the same parameters employed in the MVO, but was later refined through further analysis, which led to the exclusion or inclusion of parameters deemed crucial for the evaluation. This index was also developed with the support of some fuzzy logic based parameters. In the end, the two methodologies were compared in order to determine the consistency of the two methods used and the differences obtained.

Facing rising care demands, workforce shortages, and cost pressures, healthcare systems increasingly view digital transformation as essential rather than optional. This paper presents a qualitative evaluation of such efforts within a Dutch hospital that formally embraced the "digital unless" principle, providing care digitally by default unless not feasible. Despite strategic commitment, actual implementation often lags behind due to organizational, cultural, and practical barriers. In April 2025, a structured internal session was held involving a diverse group of stakeholders, including the executive board, board of medical staff, nursing staff board, tactical management representatives, the innovation committee, CMIO, CIO, and the patient advisory council. The session included (1) a strategic proposition review, (2) a "fishbowl" dialogue focused on staff experience, and (3) a debate on patient needs and autonomy. Central questions included "Are we doing digitally what can be done digitally?" and "What is needed to make that a reality?" Thematic analysis of the session revealed five key lessons: (1) hybrid care is the realistic default; (2) mindset and working technology are interdependent; (3) tailored support for staff is critical; (4) adopting proven innovations from others is efficient and effective; and (5) patient autonomy must remain central. These findings are contextualized using current literature and implementation frameworks like the Technology-Organization-Environment (TOE) model. External sources provide empirical support for the operational, clinical, and human value of digital health. The study concludes that digital success depends less on vision and more on cultural readiness, staff alignment, and meaningful patient inclusion. This paper offers practical, evidence-informed recommendations to help hospitals translate digital ambitions into measurable impact.

Sleep apnea (SA) is a prevalent disorder among individuals with heart failure (HF), often leading to complications. Early identification is essential for timely interventions and better outcomes. This study explores the feasibility of developing a screening tool for SA in patients with HF using data from the Future Patient Telerehabilitation program. A random forest classifier was used to develop a predictive model, achieving a promising receiver operating characteristic area under the curve (ROC-AUC) of 0.85, suggesting that the random forest classifier has the potential as a SA screening tool for HF patients. However, the study lacked key variables, such as oxygen saturation, that are strong predictors for SA assessment according to current literature; this limits the model's generalizability. Despite this, the findings indicate that the ML model shows promise for screening SA in HF patients, highlighting the need for high-quality, standardized data from future clinical trials to enhance its accuracy and clinical utility.

Fuzzy control systems provide a robust framework for clinical decision support in settings characterized by uncertainty and overlapping variable states. Since Version 2.9, HL7 Arden Syntax has natively supported fuzzy logic constructs, enabling more accurate and expressive medical logic. This feasibility study explores fuzzy aggregation in Arden Syntax for clinical decision support. We implement a rule from FuzzyKBWean, a fuzzy control system supporting ventilator therapy decisions, recommending adjustment of FiO2 based on PaO2 and PaCO2 levels. It is executed using Medexter Healthcare's Arden Syntax compiler, demonstrating the practical utility of native fuzzy logic in Arden Syntax for real-time, interpretable clinical decision support. Observations during implementation led to a suggestion for further refinement of the standard regarding stricter data type enforcement in fuzzy operations, enhancing the robustness of Arden-Syntax-based systems.

This concept paper outlines the methodological design and rationale behind a modified Delphi study conducted within the Horizon 2020 project XR2esilience, which aims to develop a virtual reality (VR)-based resilience training for nurses. The paper focuses on the consensus-oriented Delphi approach to support the early-phase co-development of digital health interventions. Experts from nursing, psychology, education, and VR development participated in a multi-round process to prioritize content areas, implementation strategies, and contextual considerations. The Delphi method was adapted to the needs of interdisciplinary collaboration and stakeholder integration in digital intervention design. As a concept paper, it outlines methodological foundations and consensus processes, offering guidance for similar initiatives seeking to combine technological innovation with participatory, consensus-driven development in healthcare.

Medical and health disciplines are facing a change of their clinical practices with the integration of new transformative technologies including artificial intelligence (AI). There is an interest to elevate knowledge and skills in designing and developing adaptive technology for clients, patients and practices. In this study the possibility to integrate education on human-centered AI in the education on advanced level of nurses, physiotherapists and occupational therapists was explored. A blueprint of a 3-course AI education on human-centered AI for health and wellbeing was developed and evaluated at two universities. The course contents range from theory to practical exercises with application to clinical practice on AI, responsible AI design and AI technology, with a structured progression between each level. The evaluation showed that the proposed courses could be integrated into the existing master programs to different extent, from full integration in 120-credit programs to limited integration in 60-credit programs. It was concluded that the proposed education is feasible and desirable to integrate, and future work will continue the development.

Ensuring trustworthy use of Artificial Intelligence (AI)-based Clinical Decision Support Systems (CDSSs) requires continuous evaluation of their performance and fairness, given the potential impact on patient safety and individual rights as high-risk AI systems. However, the practical implementation of health AI performance and fairness monitoring dashboards presents several challenges. Confusion-matrix-derived performance and fairness metrics are non-additive and cannot be reliably aggregated or disaggregated across time or population subgroups. Furthermore, acquiring ground-truth labels or sensitive variable information, and controlling dataset shifts-changes in data statistical distributions-may require additional interoperability with the electronic health records. We present the design of ShinAI-Agent, a modular system that enables continuous, interpretable, and privacy-aware monitoring of health AI and CDSS performance and fairness. An exploratory dashboard combines time series navigation for multiple performance and fairness metrics, model calibration and decision cutoff exploration, and dataset shift monitoring. The system adopts a two-layer database. First, a proxy database, mapping AI outcomes and essential case-level data such as the ground-truth and sensitive variables. And second, an OLAP architecture with aggregable primitives, including case-based confusion matrices and binned probability distributions for flexible computation of performance and fairness metrics across time or sensitive subgroups. The ShinAI-Agent approach supports compliance with the ethical and robustness requirements of the EU AI Act, enables advisory for model retraining and promotes the operationalisation of Trustworthy AI.

The introduction of the Licence-Master-Doctorate (LMD) system in African higher education has significantly reshaped university organization, particularly in health-related fields, by exacerbating structural challenges such as the shortage of faculty and inadequate infrastructure. In this context, the present work aims to construct a structured dialogical corpus designed for the training of a customized GPT-2 model, with the goal of simulating medical consultations and supporting the training of medical students. The methodology combines the use of reliable medical sources, the controlled generation of dialogues using existing artificial intelligence systems, and role-playing exercises involving medical students, with detailed annotation of clinical, emotional, and behavioral metadata. The final corpus comprises over 36 million tokens for pre-training and more than 8,326 simulated dialogues for fine-tuning, covering the most prevalent pathologies in Burkina Faso. This multilingual and culturally contextualized approach represents a significant departure from dominant Western corpora, laying the groundwork for a medical conversational model adapted to African realities. While the model is still in training, the complete results will be presented at a later stage. Nevertheless, the collected data already constitute a valuable resource for the development of realistic, diverse, and reusable educational simulators across various medical training contexts.