Journal of Medical Systems最新文献

Heart rate variability (HRV) is a well-established, noninvasive measure of autonomic nervous system activity and is associated with clinical outcomes. Although real-time monitoring of HRV is valuable in clinical practice, its effectiveness is often compromised by major challenges: high inter-individual variability and frequent data contamination from procedural artifacts. To address these challenges, we developed and validated a computational framework for robust and personalized real-time HRV analysis oriented toward clinical application. The framework performs simultaneous analysis and visualization of both time- and frequency-domain HRV indices and incorporates an adaptive alert algorithm that personalizes alert thresholds using the interquartile range of each patient's own data. A workflow-integrated mechanism for manually annotating and excluding artifact-prone periods prevents procedural artifacts from skewing the statistical baselines, and a multi-scale visualization module provides a unified view of short-term fluctuations and long-term trends. While existing HRV tools are powerful for research or offline analysis, they often lack the integration of personalized alerting and workflow-oriented artifact management needed for bedside care. The proposed system uniquely combines personalized alerting, care-linked artifact exclusion, and multi-scale bedside visualization within a single real-time software package. The framework was validated using open-access electrocardiogram (ECG) databases and synthetic noise-contaminated signals, confirming robust R-wave detection across pediatric and adult recordings and under low signal-to-noise conditions. In addition, the framework was operationally validated at the bedside using ECG data from 24 newborn patients. By systematically addressing the core challenges of personalization and artifact management in a clinically integrated manner, this work represents a significant step toward translating real-time HRV analysis into routine vital sign management and, ultimately, improved patient outcomes.

The ubiquitous availability of work-related applications on personal devices makes healthcare workers prone to working during leisure time. We tested the hypothesis that an intervention to reduce work-related screen time during a weekend off reduces stress in healthcare workers. Pragmatic parallel design randomized controlled trial between November 2021 and November 2023. Healthcare workers using a smartphone with a work email application were eligible. Randomization was 1:1 to no treatment or a threefold educational intervention to: 1) activate automated responses to emails received, 2) reduce screen time, and 3) uninstall work applications from personal devices. The primary outcome was the change in participants' stress from pre- to post-weekend, measured with the Perceived Stress Scale-10. The secondary outcome was device screen time. Among 815 enrolled participants, 520 responded to the post-intervention survey. The median [Q1, Q3] change from baseline Perceived Stress Scale-10 scores was -2 [-7, 0] in controls and -4 [-9, 0] in the intervention group. The mean difference (intervention - control) in post-intervention Perceived Stress Scale-10 scores, adjusted for baseline stress, was -1.6 (95% CI: -2.6, -0.6; P = 0.002). The median [Q1, Q3] change from baseline screen time was 0 [-2, 1] hours in the controls and -1 [-3, 0] hours in the intervention group. A three-pronged educational intervention targeting work-related screen time among healthcare workers doubled stress reduction during a non-work weekend. Stress reduction in the intervention group was mediated by reduced screen time. Future research should investigate long-term effects and broader implementation of such interventions to promote well-being in the healthcare workforce. Trial Registration: https://clinicaltrials.gov/study/NCT05106647 . Identifier: NCT05106647, Registration date: November 4, 2021.

Causal networks provide a mechanistic understanding of clinical phenomena, allowing for personalized and explainable decision-making. Causal discovery, namely the task of constructing such models, is challenging, particularly for rare diseases, where observational data are sparse, medical knowledge is incomplete, and diseases develop over time. This work proposes a new and original expert-in-the-loop causal discovery workflow that iteratively refines a set of causal networks associated with different disease mechanisms. When applied to soft tissue sarcoma, a heterogeneous group of rare cancers, the workflow allows for the first comprehensive causal description of the disease's natural history. Indeed, three causal networks associated with different disease mechanisms shed light on the complex interplay between patients' covariates and disease behavior. These results have the potential to enhance clinical decision-making by allowing the development of personalized treatment strategies. The proposed workflow paves the way to agile, modular, and flexible causal discovery for clinical domains characterized by data sparsity, longitudinal dynamics, and heterogeneous expert knowledge.

Software as a Medical Device (SaMD) has become indispensable in diagnostics, treatment planning, and patient monitoring. While high-income countries have introduced clear regulatory frameworks, Bangladesh and many low- and middle-income countries (LMICs) still lack tailored pathways for medical software approval (IMDRF. Software as a Medical Device (SaMD): Key Definitions (IMDRF/SaMD WG/N10FINAL:(2013)); IMDRF. Software as a Medical Device (SaMD): Clinical Evaluation (IMDRF/SaMD WG/N41FINAL:(2017)); U.S. Food and Drug Administration (FDA). Software as a Medical Device (SAMD): Clinical Evaluation Guidance for Industry and FDA Staff (2017)). The current reliance on manual processes designed for physical devices leads to inefficiencies, inconsistent decisions, and potential risks to patient safety. This Comment proposes a semi-automated, risk-based intake roadmap for Bangladesh's Directorate General of Drug Administration (DGDA). Drawing on IMDRF, EU MDCG, and U.S. FDA frameworks, it presents a tangible workflow showing which submissions can be automatically triaged, which require human review, and where human override is maintained (European Commission (MDCG). Guidance on Qualification and Classification of Software in Regulation (EU) 2017/745 (MDCG 2019-11) and World Health Organization (WHO) Global Model Regulatory Framework for medical devices including IVDs (draft; WHO) (n.d.)). Key intake fields, escalation rules, and measurable performance indicators are defined. Anchored to Bangladesh's current DGDA and national digital health context, the proposal identifies specific legal and infrastructural gaps and outlines steps for phased modernization that may guide other LMICs.

Deep vein thrombosis (DVT) in fracture patients is often clinically silent, with a high incidence of thrombosis and associated mortality. Static machine learning methods struggle to address the challenge of early DVT diagnosis due to their inability to adapt to heterogeneous data across patients. In contrast, Dynamic Ensemble Selection (DES) improves clinical decision-making and therapeutic interventions by dynamically adapting to variations in data characteristics. Here, we developed and validated a risk prediction model for DVT using electronic medical record data from fracture patients upon admission. By employing the DES method to optimize the prediction process, the model generates patient-specific probabilities of DVT occurrence, enabling personalized clinical risk assessment. Validation results showed that the DES model achieved strong performance in predicting DVT, with an accuracy of 0.875 and an Area Under the Receiver Operating Characteristic Curve (AUC) of 0.906. Notably, it demonstrated a high recall of 0.918 for DVT. Furthermore, in the prospective test set, DES exhibited excellent generalization capability, maintaining robust performance with an accuracy of 0.813 and an AUC of 0.876. We further developed an interactive clinical tool based on the DES algorithm to facilitate model interpretation and implementation. By integrating this user-friendly solution into clinical workflows, DES not only improves early DVT detection but also optimizes the allocation of healthcare resources.

Artificial intelligence (AI) and large language models (LLMs) such as ChatGPT-5 are increasingly applied in medical education. However, their potential role in clinical simulation remains largely unexplored. This descriptive proof-of-concept study aimed to examine ChatGPT-5's ability to synthesize and generate educational content related to clinical simulation, focusing on the coherence, factual accuracy, and understandability of its outputs. Seven exploratory questions covering conceptual, historical, and technological aspects of clinical simulation were submitted to ChatGPT-5. Each query was regenerated three times to assess consistency. Responses were independently evaluated by multiple reviewers using a five-point Likert scale for content quality and accuracy, and the Patient Education Materials Assessment Tool (PEMAT) for understandability. Authenticity of AI-generated references was verified through PubMed and Google Scholar. ChatGPT-5 produced coherent and organized responses reflecting major milestones and trends in clinical simulation. Approximately 80% of cited references were verifiable, while some inconsistencies indicated residual fabrication. The average agreement score for accuracy and coherence was 4 ("agree"), suggesting generally acceptable quality. PEMAT analysis showed that content was structured and clear but occasionally used complex terminology, limiting accessibility. Within the exploratory scope of this proof-of-concept study, ChatGPT-5 demonstrated potential as a supportive tool for synthesizing information about clinical simulation. Nonetheless, interpretive depth, citation reliability, and pedagogical adaptation require further refinement. Future research should assess the integration of LLMs into immersive simulation environments under robust ethical and educational frameworks.

Background: The global trend of population aging is escalating, presenting profound challenges to healthcare systems worldwide. Digital technologies have emerged as pivotal solutions to address these pressing issues. However, the application of digital technologies in healthcare for older adults remains an area that warrants further exploration. This study aims to systematically evaluate the current state of how older adults (55 years and older) utilize digital technology for healthcare, comprehensively analyze its various types, target populations, and impacts, thereby providing a scientific basis for future research endeavors and practical applications.

Methods: This study adheres to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. A comprehensive search was conducted across six databases (Web of Science, Scopus, PubMed, IEEE Xplore, ScienceDirect, and APA PsycInfo). A total of 17 articles were ultimately included in the study.

Results: The research findings identified six types of digital technologies applied in older adults' healthcare. Among them, applications for chronic disease management were the most prevalent, followed by those for rehabilitation treatment and health monitoring. These technologies were applied across seven healthcare domains, with chronic disease management, rehabilitation, and health monitoring emerging as the core areas. Regarding the target populations, the studies primarily focused on chronic disease patients, individuals with cognitive impairments, and other vulnerable groups.

Conclusion: This review highlights the potential of digital technologies in meeting the unique needs of older adults. Digital technologies enhance older adults' access to health information, facilitating improved health management. Notable progress has been achieved in areas such as chronic disease management and remote rehabilitation. Future research should prioritize interdisciplinary collaborations to develop aging-friendly digital technologies that can effectively support older adults' healthcare.

National Cancer Registries (NCRs) are essential for monitoring cancer incidence, prevalence, and outcomes at the population level, supporting evidence-based policies and resource allocation. In Chile, fragmented health information systems and infrastructure gaps have historically hindered the establishment of a nationwide registry. In response, a technological NCR was developed under the National Cancer Plan and Cancer Act. This article presents a validation study assessing the NCR's usability from the perspective of healthcare professionals involved in cancer registration. A quasi-experimental, within-subjects design was applied, where 26 healthcare professionals from 22 institutions across Chile completed five core registry tasks using both their current systems and the NCR platform. Results show statistically significant reductions (≈ 40-50%) in perceived task difficulty across all tasks, with large effect sizes (r > 0.7), indicating improved usability and lower workload when using the NCR platform. These findings highlight the platform's potential to overcome institutional barriers to adoption and contribute to the comprehensive and sustainable implementation of a national cancer surveillance system in Chile.