Studies in health technology and informatics最新文献

Wearable devices are increasingly used to create patient generated health data (PGHD), yet existing models lack the specificity to fully capture the nuances of this data. This paper presents an initial work on WearPGHDProv, an extension of the PGHDProvO ontology, designed to address this gap. We extended the PGHDProvO ontology using a top-down approach, incorporating concepts from the W3C Provenance Ontology (PROV-O) and domain-specific terms related to wearable devices and data generation. WearPGHDProv introduces new classes and properties to model device-specific information, additional related information unique to wearable data, and the context of data collection. This extension enhances the ability to track the source, pertinent information, and quality of wearable-generated PGHD, facilitating its reliable use in electronic health records (EHRs) and research.

Mobile health (mHealth) applications have become important in modern healthcare, yet tailored design recommendations for third-party anamnesis (anamnesis by proxy) - particularly for lay caregivers of infants and other care-needing individuals - remain limited. This systematic literature review addresses this gap by investigating existing design recommendations for mHealth apps in this context. A comprehensive search was conducted across several databases. The extracted recommendations include e.g. remote support by medical professionals, real-time notifications, information on self-management and conditions, peer support, and non-functional aspects, including ease of use and offline accessibility. The consolidated recommendations aim to assist developers and researchers in creating mHealth applications for third-party anamnesis by lay caregivers.

Health information systems (HIS) have been extensively adopted to reduce medication errors. Unfortunately, complex socio-technical issues in HIS can create new error risks, resulting in unintended patient harm. Rigorous evaluation can therefore provide insights to inform risk factors and mitigation measures. This paper presents the validation methods of a proposed human, organisation, process, and technology-fit (HOPT-fit) framework in multiple qualitative case study evaluations using observation, interview, and document analysis in Japanese and Malaysian clinical settings. Findings validated the HOPT-fit applicability in evaluating HIS effectiveness and safety's complex and dynamic nature.

This study assesses feature distribution differences across five intensive care databases using Kullback-Leibler Divergence (KLD). Analyzing bidirectional KLD patterns between individual databases and the composite of others, stratifying by transfusion status. Results reveal heterogeneity: HiRID shows highest divergence in both directions, particularly among transfusion cases; UKA exhibits moderate overall divergence but pronounced differences in transfusion scenarios; MIMIC-IV shows minimal divergence, indicating closest alignment with group distributions. Notably, transfusion cases consistently display higher divergence than non-transfusion cases across all databases, highlighting institution-specific practices. These findings stress the importance of assessing data heterogeneity before implementing federated learning models to understand generalization capabilities.

The implementation of evidence-based practice continues to pose significant challenges across healthcare settings. This study investigated how factors influencing the use of an intranet folder system (IFS) providing evidence-based guidelines change during the transition to a Clinical Decision Support System (CDSS). A two-wave survey was conducted among nursing staff at a Swiss hospital, assessing system utilisation, Evidence-Based Nursing (EBN) related factors, selected variables from the Unified Theory of Acceptance and Use of Technology (UTAUT), and demographic information. Structural equation modelling was applied to identify key determinants of utilisation. Facilitating Conditions and Social Influence significantly influenced utilisation in both systems. EBN factors, specifically Trust and Knowledge, impacted Effort Expectancy only in the CDSS model. These results suggest that while organisational and social factors consistently promote system use, the successful adoption of a CDSS additionally requires the development of new trust in the technology and expanded knowledge of its functions to reduce perceived effort and enhance utilisation. The findings highlight the need for structural support, social endorsement, and targeted training to facilitate the effective implementation of CDSS in clinical practice.

This study investigates the impact of implementing smart, digitally supported workflows on administrative efficiency in a large German hospital network through the ScanProCare! project. The primary aim was to assess whether the introduction of standardized digital processes leads to measurable time savings across different clinical departments. A longitudinal evaluation design was employed, comparing pre- and post-implementation data. The study focused on quantifying changes in process frequency and duration in operating rooms (ORs), intensive care units (ICUs), and normal wards. Results demonstrated time reductions in several areas: OR documentation decreased by 9.09% (582 hours/year), with implant and material documentation reduced by 65% and 50%. Material request times halved, saving 2,720 hours annually, while normal wards saw the largest savings-9,235 hours for documentation and 5,804 for requests. Some tasks became more time-consuming or were unchanged. incomplete master data, and ongoing training needs limited full benefits, highlighting the importance of continuous system refinement and user support. The study concludes that while digital workflows can enhance operational efficiency, continuous system refinement and user support are crucial to maximizing benefits.

Background: Traditional electronic medical records (EMRs) are often document-centric and poorly structured for real-time clinical decision support and workflow automation. To address this, we developed a Clinical Events Catalog by decomposing patient pathways into discrete, meaningful clinical events.

Objective: To define atomic clinical events that can support dynamic workflows, structured documentation, and decision support systems.

Methods: A multidisciplinary team analyzed clinical pathways across specialties and identified 168 atomic clinical events. Each event was defined with a textual definition, associated data payload, and performance metrics (KPIs), and categorized into thematic domains. The catalog was developed through iterative validation and expert consensus.

Results: The resulting Clinical Events Catalog covers nine clinical domains and provides standardized, actionable representations of clinical moments. Examples include "Vitals Examined," "Medication Administered," and "Risk Identified," each linked to measurable indicators. These events can serve as modular triggers for workflow engines and clinical decision support.

Discussion & conclusion: The catalog reflects a transition from static documentation to process-aware EMRs. While real-world deployment is planned, the catalog already offers a framework for improving data structure, auditability, and workflow transparency. This study lays the foundation for more responsive and intelligent digital health systems that support interoperability, clinical safety, and decision support integration.

Developing a scalable multi-layer AI adoption model for 6P medicine (Predictive, Preventive, Personalized, Participatory, Precision-oriented, and Public-centered) requires careful consideration of computational infrastructure, data processing and integration, healthcare-specific requirements, security and privacy, performance optimization, and system interoperability. The described multi-layer architecture in this work provides a flexible conceptual model to accommodate the diverse needs of AI implementation in different healthcare domains while maintaining scalability, security, governance, and efficiency.

Medication reconciliation (MR) aims to prevent medication errors during transitions of care, particularly at hospital admission. Despite its importance, MR remains time-consuming, and existing electronic tools lack collaborative features and visual approaches. This study describes the design of a new electronic tool for MR, developed within ABiMed, a clinical decision support system for medication review and polypharmacy management. The tool follows the main steps of the MR process: the best possible medication history (BPMH) elaborated by the pharmacist is compared to the admission medication order (AMO), and discrepancies are semi-automatically identified and classified. Unresolved discrepancies can be directly sent to the prescriber. The tool builds on features included in ABiMed, such as an ontology-based structure allowing for integration in other tools, real-time collaboration between pharmacists and prescribers, visual drug data specific to the patient, and automatic execution of STOPP/START clinical guidelines. These approaches encourage shared responsibility, and support more clinically relevant and useful pharmacist interventions. The tool has yet to undergo clinical evaluation. Future work will assess usability and impact on outcomes such as time spent on MR, prescriber acceptance of interventions, and the tool will further be expanded to include more clinical guidelines.

This paper describes a two-year experience in designing, implementing, and restructuring an artificial intelligence in medicine course for first-year medical students. They had no prior training in computer science, mathematics, or clinical medical disciplines. The practical activities were organized into three categories: seminars (exercises, problems), hands-on practical work (initially, regressions; later, also neural networks), and video demonstrations. First-year evaluations highlighted difficulties in logic and ontologies, as well as a high variability in the quality of individual projects. In the second year, changes focused on applied work: ontology building exercises, direct comparison of simple neural networks with classical regression methods, and an introduction to Prompt Engineering. These adjustments led to a clear increase in performance and consistency of the final results. The paper supports the feasibility of early introduction of AI in medical training and the relevance of an iterative curriculum design, with a focus on conversational skills and guided applicative activity.