Journal of Medical Systems最新文献

Assessing usability and satisfaction is vital to ensure the efficiency and optimal use of mobile health (mHealth) applications. Nevertheless, existing questionnaires revolve around computerized systems and lack validation for evaluating mHealth applications. We aimed to develop and validate a tri-language questionnaire to assess usability and satisfaction of mobile health applications (USHA). This study consisted of three phases: item development, translation, and validation. During the item development phase, a preliminary English version of the USHA questionnaire that comprised Likert-scale and demographic items was designed. Subsequently, forward-backward translation was performed to produce Malay and Chinese versions. Content validation was conducted with eight experts, followed by face validation with five diabetes mellitus patients. Reliability testing was conducted through test-retest analysis among diabetes mellitus patients. The initial tri-language USHA questionnaire consisted of 18 Likert-scale items and 8 demographic items. Following expert validation, five Likert-scale items and one demographic item were eliminated for lack of relevance, importance, or clarity, while four Likert-scale items were rephrased. During face validation, additional one demographic item was removed. The finalized questionnaire demonstrated high reliability, with a Cronbach's alpha of 0.956 and an intraclass correlation coefficient of 0.845. Consequently, the tri-language USHA questionnaire consisted of 13 Likert-scale items and six demographic items, is a valid and reliable instrument that enhances accessibility and enables assessment of the usability and satisfaction of interactive mHealth applications, especially for diabetes mellitus care across a broad range of users.

This study systematically investigates the alterations in electroencephalogram (EEG) microstates in patients with refractory epilepsy(RE) across different seizure stages. A novel EEG microstate analysis framework is proposed to address the limitations of traditional methods in clinical diagnosis and treatment. Additionally, the study explores the feasibility of utilizing microstate characteristics for seizure recognition and classification. Two independent datasets were used to extract microstate features corresponding to the four canonical seizure stages. A directed microstate graph structure was constructed, and a directed graph convolutional network(DGCN) was employed for classification. The performance of the proposed framework was compared to that of traditional methods, which rely on manually extracted features and classical machine learning classifiers. The proposed framework (termed MsG-GCN for reference within this article) exhibited superior classification performance, achieving an accuracy of 80.2%, compared to the best traditional method (Support Vector Machine, SVM), which achieved 74.3%. Notably, microstates A and C showed significant differences across seizure stages, with the average occurrence rate exhibiting greater discriminative power than the average duration and coverage. This study introduces novel approaches for the automated classification of epileptic seizures, demonstrating the effectiveness of graph neural networks in modeling dynamic epileptic microstate transitions. The proposed framework not only enhances classification performance but also provides a highly interpretable paradigm for intelligent, auxiliary diagnosis of complex neurological disorders.

This narrative review evaluates the current status, potential value, key challenges, and future directions of Microsoft HoloLens 2 mixed reality (MR) technology, with a particular focus on its built-in eye tracking and visual perception functions, in the context of pediatric orthopedic three-dimensional model teaching. Relevant literature on medical education and surgical training was integrated to examine the technical features, teaching practices, and educational implications of HoloLens MR. Existing studies indicate that MR technology can enhance learners' spatial understanding and operative skills; eye tracking supports the quantification of learning processes and personalized feedback, while visual perception technologies improve immersion and interactivity. However, limitations remain regarding hardware performance, content development costs, quality of research evidence, privacy concerns, and ecological sustainability. The application of HoloLens MR in pediatric orthopedic education holds broad prospects. Its sustainable integration into medical education will depend on advances in hardware, integration of artificial intelligence, expansion of remote collaboration, and the establishment of standardized evaluation systems.

Clinical documentation demands necessitate automated solutions balancing clinical precision with patient comprehension. This study aims to develop and validate a unified framework that maintains diagnostic accuracy while dynamically adapting medical report complexity to diverse literacy levels, and to establish comprehensive evaluation methodologies for patient-centered medical documentation. We developed a unified framework integrating three innovations: a hybrid detection method combining CheXFusion and Eigen-CAM for clinical finding detection and anatomical localization; an advanced LLaVA-based pipeline synthesizing clinical predictions with anatomical data for contextually rich medical reports; and a self-reflective large language model system dynamically adapting report complexity across reading levels (6th, 11th, and 18th-grade) while preserving clinical integrity. Our methodology introduces novel evaluation using the Mistral-small model assessing report quality through consistency, coverage, and fluency metrics. Validation on MIMIC-CXR and IU X-Ray datasets demonstrated substantial improvements: 19.78% enhancement in classification accuracy (AUROC), 17.29% improvement in mean average precision, 56.88% increase in patient comprehension scores, and 5.26% gain in diagnostic precision. The framework successfully addresses maintaining clinical rigor while enhancing patient accessibility, reducing documentation burden on healthcare providers and improving patient engagement through comprehensible reporting. This work establishes new standards for automated medical documentation that effectively reconcile clinical precision with patient comprehension in healthcare communication.

Medical misinformation is a major public health concern. The public increasingly uses artificial intelligence (AI) tools for medical consultations. Therefore, concerns arise about their ability to detect and even correct subtle medical information that users may be embedding in users prompts. This study assessed the ability of different ChatGPT models in detecting and correcting such subtle misinformation. Fifty clinical plausible prompts with subtle medical misinformation were introduced separately to ChatGPT models 4o, 4.1-mini, and GPT-5. Prompts spanned Internal Medicine, Cardiology, Pediatrics, Ophthalmology, and Oncology. Responses were scored on a 3-point scale: 0: No correction; 1: Hedging or uncertainty; 3: cutting edge detection and correction. GPT-4o was the best performing model, surpassing GPT-5 by correctly identifying and correcting misinformation in 86% of the prompts compared to 74% for GPT-5. GPT-4.1-mini showed weaker performance, detecting dsmisinformation in only 52% of prompts, with complete failure in 34% and hedging in 14%. Specialty-specific analysis revealed that GPT-4o achieved higher detection rate in all tested specialties compared to GPT-4.1-mini and GPT-5. Only oncology showed comparable detection rates between GPT-4o and GPT-5. Although the performance of GPT-4o and GPT-5 in detecting subtle medical misinformation was promising, unexpectedly, GPT-4o surpassed GPT-5 in performance. Using underpowered variants such as GPT-4.1-mini, poses a public health threat. Reverse prompting offers a diagnostic lens and should be integrated into standard AI safety testing protocols.

A health equity movement is underway, in which broad sectors of society must work together to create solutions to the complex interwoven problems that undermine equal opportunities for good health and well-being. Yet, addressing health inequity is a complex and challenging problem. Health inequity manifests through complex disparities that overload healthcare services and penetrate (all) other sectors of society. The aim of this study is to reach consensus on health equity related topics to be included in European health and social care study programmes by using the Sustainable Development Goals (SDGs). To identify such topics, a Delphi method was designed and performed in an expert panel comprising nine academics, clinicians, and members of a non-governmental organization. Using the Sustainable Development Goals as a framework, three rounds of surveys were conducted. The response rate was 100% across all rounds. In the first round, participants selected relevant SDG targets and indicators; 183 indicators were shortlisted. In the second round, participants rated the relevance of each indicator, leading to the endorsement of 142 indicators. In the third round, 162 out of 247 total indicators were endorsed. None of the Sustainable Development Goals were considered irrelevant to health and social care study programmes. We argue that to address health inequities effectively, health and social care professionals should liaise with a wide range of stakeholders in non-health sectors to design appropriate strategies to improve health and well-being. This implies that health and social care curricula should integrate competencies and capabilities that allow future professionals to work outside their traditional spheres of practice, communicating health information to a broad range of audiences, advocating and translating data for intersectoral action, and negotiating strategies and approaches to attain health equity in collaboration with stakeholders from different social sectors.

Technological advancements are enhancing healthcare, with digital twin (DT) technology emerging as a key tool for personalized and efficient care. This umbrella review systematically evaluates the literature on DT applications in healthcare, focusing on their effectiveness, challenges, and potential to substantially improve patient care.An umbrella review was conducted following the Joanna Briggs Institute (JBI) manual for evidence synthesis and the PRISMA guidelines. A comprehensive literature search was performed across multiple databases, including PubMed, Scopus, Web of Science, and IEEE Xplore, targeting systematic reviews published up to July 2024. The inclusion criteria focused on systematic reviews and meta-analyses related to the usage of DT technologies in healthcare settings.The review identified a considerable number of systematic reviews that highlight the role of DTs in various domains of healthcare, including personalized medicine, predictive maintenance of medical equipment, and healthcare system optimization. Key themes included the integration of real-time data and predictive modeling, which enhance chronic disease management and surgical planning. However, barriers to implementation were noted, including data privacy concerns, validation issues, and high costs.DT technology has the potential to enhance healthcare delivery by enabling personalized treatment and improving operational efficiencies. However, addressing ethical challenges, particularly concerning data privacy and security, is crucial for the successful integration of DTs in clinical practice. This umbrella review underscores the need for continued research to overcome these challenges and facilitate the widespread adoption of DT technologies in healthcare.

Background: The rapid spread of modern outbreaks frequently surpasses the response speed of traditional surveillance and laboratory systems. Mobile apps offer real-time symptom submission, geospatial mapping, and digital contact tracing, which might bridge this gap, yet their epidemiological value and user experience have not been assessed rigorously.

Methods: We developed a novel framework to evaluate utility and usability of surveillance apps. We then demonstrated its use in a proof-of-concept evaluation. An assessment framework with 15 consolidated features was developed from an initial list of 73 identified through the literature and refined by experts. This framework directed the evaluation of available mobile apps for infectious disease surveillance identified via the App Store, Google Play Store, and relevant literature. Two authors applied the criteria independently, and conflicts were panel-resolved (κ = 0.60).

Results: Of the 56 apps screened, 11 met inclusion criteria. Six focused on a single disease, while five tracked multiple diseases. Seven were designed for national use, with four providing global coverage. High-scoring apps combined expert oversight with diverse data sources for broader disease coverage, whereas low performers relied on self-reporting and a single-disease focus. Apps offering user support and customisable alerts scored highest for usability; scores declined when privacy constraints restricted ease of use.

Conclusion: This study presents a structured framework to guide evaluation of mobile apps for epidemic surveillance. The evaluation underscores the need to balance epidemiological functionality with user-friendly design and privacy-conscious features. As mobile apps expand in public health, balancing utility and usability is key to adoption and longevity.

Good mental health is crucial for well-being. Unfortunately, despite the advancements of automatic detection solutions in the mental health field, along with the existence of effective treatments, a large percentage of affected people receive no care for their disorder. Thus, this research proposes an innovative framework integrating counterfactual explanations into a multi-label detection system for anxiety and depression, combining large language models for feature extraction and multi-label machine learning for final prediction. The solution is designed to operate in a streaming mode, addressing the need to process information in real-time. Moreover, sliding window techniques manage the data's evolution, preserving temporal relevance while ensuring robust, user-centered interpretation capabilities. The latter is reinforced by the generation of counterfactual explanations, which contribute to the interpretability, adaptability, and accountability of the results in a critical context, such as mental health. The results surpass the 90% accuracy, indicating very few misclassifications per label. Ultimately, this solution contributes to the literature with timely and transparent decision-making in mental healthcare.