Health Informatics Journal最新文献

Objective: Purpose of this cross-sectional study was to investigate young adults' eHealth literacy levels, use, and readiness to use eHealth and eWelfare. Methods: An electronic survey based on Readiness and Enablement Index for Health Technology (READHY) was aimed at young adults in the geographical are of one wellbeing services county in Southern Finland. Data were analyzed using non-parametrical statistical methods. Results: Young adults (N = 110) actively used eHealth and eWelfare and assessed themselves as having good general digital skills. They were confident in their eHealth literacy and readiness for the use of eHealth and eWelfare. However, young adults not in education, employment, or training (NEETs, n = 21) were significantly less confident than non-NEETs (n = 89) in three of the five domains describing eHealth literacy, and readiness for the use of health technology. Conclusions: The differences between NEETs and non-NEETs indicate that further research on NEETs' and other subgroups' abilities to use eHealth and eWelfare is needed to ensure that these services can be fully utilized.

Introduction: Spanish speakers rely on social media for health information, with varying quality of its content. This study evaluates the reliability, completeness, and quality of type 2 diabetes (T2D) information available in Spanish-language videos on YouTube and Facebook. Methods: Analytical observational study that included Spanish-language videos on TD2 available on Facebook and YouTube. General characteristics, interaction and generating sources are described. Standardized tools were used to assess reliability, completeness and overall quality. Results: We included 172 videos, 90 from Youtube® and 82 from Facebook®. The median number of views was 1725 (IQR 213-10,000), with an average duration of 5.93 minutes (IQR 3.2-16.8) and an internet time of 834 days (IQR 407-1477). Most videos were uploaded by independent users (58.72%). Reliability (evaluated with DISCERN tool) had a median of 3 (IQR 2-3), completeness (content score) had a median of 2 (IQR 1-3), and overall quality, evaluated with the Global Quality Score (GQS) tool had a median of 3 (IQR 3-4). Using a global classification of "subjective reliability" 92.4% of the videos were considered reliable. Better completeness was observed in Facebook videos (p < .001). Reliability was better for videos from government or news organizations. Conclusion: Our results suggest that videos about T2D in Spanish on social media such as YouTube and Facebook have good reliability and quality, with greater exhaustiveness in content in Facebook videos and greater reliability for videos from government or news organizations.

Objectives: Metabolic syndrome (MetS) has a significant impact on health. MetS is the umbrella term for a group of interdependent metabolic threats that contribute to the emergence of diseases that can lead to death. This study was designed to better predict the risks associated with MetS to enable medical personnel to make more optimal preventive medical decisions. Study design: Data from a large hospital survey database was used to train data mining classification techniques to predict patient-level risk subsequent to extensive data engineering that included aggregating predictors from multiple visits. Methods: A prospective group of seemingly healthy volunteers from the database was studied based on data obtained during their regular annual health checkups. Results: After aggregating the variables over time, the findings indicated that the predictive power of our model outperformed methods presented in other studies (AUC = 0.947). Specific lifestyle factors were identified as contributing to MetS. Conclusion: Involvement to avoid recurring diseases can significantly decrease medical problems and treatment expenses. The findings emphasize the importance of using predictive tools in healthcare and preventive medicine. The results can be used for future prevention strategies that encourage lifestyle changes and implement directed medical treatment protocols to decrease the burden of illness.

Purpose: In the context of Chinese clinical texts, this paper aims to propose a deep learning algorithm based on Bidirectional Encoder Representation from Transformers (BERT) to identify privacy information and to verify the feasibility of our method for privacy protection in the Chinese clinical context. Methods: We collected and double-annotated 33,017 discharge summaries from 151 medical institutions on a municipal regional health information platform, developed a BERT-based Bidirectional Long Short-Term Memory Model (BiLSTM) and Conditional Random Field (CRF) model, and tested the performance of privacy identification on the dataset. To explore the performance of different substructures of the neural network, we created five additional baseline models and evaluated the impact of different models on performance. Results: Based on the annotated data, the BERT model pre-trained with the medical corpus showed a significant performance improvement to the BiLSTM-CRF model with a micro-recall of 0.979 and an F1 value of 0.976, which indicates that the model has promising performance in identifying private information in Chinese clinical texts. Conclusions: The BERT-based BiLSTM-CRF model excels in identifying privacy information in Chinese clinical texts, and the application of this model is very effective in protecting patient privacy and facilitating data sharing.

Background: The HIV epidemic in Indonesia is one of the fastest growing in Southeast Asia and is characterised by a number of geographic and sociocultural challenges. Can large language models (LLMs) be integrated with telehealth (TH) to address cost and quality of care? Methods: A literature review was performed using the PRISMA-ScR (2018) guidelines between Jan 2017 and June 2024 using the PubMed, ArXiv and semantic scholar databases. Results: Of the 694 records identified, 12 studies met the inclusion criteria. Although the role of eHealth interventions as well as telehealth in HIV management appears well established, there is a significant literature gap on the integration of telehealth and LLM technology. To address this, we provide a blueprint for the safe and ethical integration of LLM-TH into triage, history taking, patient education highlighting opportunities for reduced consultation time and improved quality of care. Conclusions: Variable access to mobile technology and the need for empirical validation stand out as limitations for LLM-TH. However, we argue that the current evidence base suggests the benefits far outweigh the challenges in applying LLM-TH for HIV care in Indonesia. We also argue this novel therapeutic modality is broadly applicable to the subacute general practice setting.

Objective: Explore deep learning applications in predictive analytics for public health data, identify challenges and trends, and then understand the current landscape. Materials and Methods: A systematic literature review was conducted in June 2023 to search articles on public health data in the context of deep learning, published from the inception of medical and computer science databases through June 2023. The review focused on diverse datasets, abstracting applications, challenges, and advancements in deep learning. Results: 2004 articles were reviewed, identifying 14 disease categories. Observed trends include explainable-AI, patient embedding learning, and integrating different data sources and employing deep learning models in health informatics. Noted challenges were technical reproducibility and handling sensitive data. Discussion: There has been a notable surge in deep learning applications on public health data publications since 2015. Consistent deep learning applications and models continue to be applied across public health data. Despite the wide applications, a standard approach still does not exist for addressing the outstanding challenges and issues in this field. Conclusion: Guidelines are needed for applying deep learning and models in public health data to improve FAIRness, efficiency, transparency, comparability, and interoperability of research. Interdisciplinary collaboration among data scientists, public health experts, and policymakers is needed to harness the full potential of deep learning.

Background: Increasing digitisation in healthcare is flowing through to quality improvement strategies, like audit and feedback. Objectives: To systematically review electronic audit and feedback (e-A&F) interventions in hospital settings, examining contemporary practices and quantitatively assessing the relationship between features and effectiveness. Methods: We performed a systematic review using a structured search strategy from 2011 to July 2022. Searches yielded a total of 5095 unique publications, with 152 included in a descriptive synthesis, reporting publication characteristics and practices, and 63 in the quantitative synthesis, to evaluate the effect size of intervention features. Results: The search returned publications across characteristics, including countries of origin, feedback topics, target health professionals, and study design types. We also identified an association with effectiveness for all but one of the features examined, with a Cohen's d ranging from above +0.8 (a large positive effect), to -0.67 (a medium negative effect). Socio-technical features related to supportive organisations and the involvement of engaged health professionals were most associated with effective interventions. Conclusion: Key findings have confirmed that a common set of features of e-A&F systems can influence effectiveness. Results provide practitioners with insight into where resources should be focused during the implementation of e-A&F.

Background: Diabetes apps have the potential to improve self-management among people with type 2 diabetes mellitus (T2DM) and thereby prevent complications. However, premature disengagement of diabetes apps hinders this potential. Objective: This study aimed to identify facilitators of and barriers to the continued use of apps among T2DM patients and to formulate recommendations to enhance patients' adherence to diabetes apps. Design: Qualitative study that followed the Consolidated Criteria for Reporting. Qualitative Research (COREQ) guidelines. Methods: Semi-structured interviews were conducted among 15 T2DM patients who continued real-world use of a diabetes app over 1 month. Data were analyzed using conventional content analysis. Results: The results showed that patients were triggered to continue app use by internally directed facilitators (health concerns, need for knowledge, self-conscious emotions) and externally directed facilitators (change in medication, reminders from health professionals). However, app use declined among all participants due to user-specific barriers (increased knowledge and experience, therapeutic inertia, diabetes stigma) and app-specific barriers. Notably, different app-specific barriers were identified in different self-managers: for novice self-managers, the app provided inconsistent information; for competent self-managers, the app provided invalid information and service; and for expert self-managers, the app was no longer being intelligent and new. Conclusions: The success of diabetes app continuance cannot be achieved by diabetes apps alone; rather, diabetes patients, health professionals, medical organizations, regulators, and integration technologies need to be gathered. Consistent, relevant, and current information, timely and continual service, psychological support should be guaranteed.

Objectives: This paper introduces HealthCheck, a novel evaluation method for persuasive mobile health applications, aiming to fill the critical gap in quick and effective evaluation tools for this domain. Methods: Following Design Science Research, HealthCheck was developed through problem identification, solution design, implementation, evaluation, and iterative refinement. The implementation involved testing with seven experts to assess its applicability and effectiveness. Results: Feedback from the evaluators indicated that while a few heuristics in HealthCheck were considered irrelevant by some, the majority found the heuristics to be both pertinent and beneficial, especially within the caregiving context. This feedback highlights the practical value of HealthCheck and its potential to offer meaningful insights into improving the usability of persuasive eHealth applications. Conclusion: The study shows HealthCheck effectively evaluates persuasive mobile health applications, offering actionable insights to enhance usability. This validates the relevance and robustness of HealthCheck's heuristics, advancing information systems and human-computer interaction research.

Objectives: This paper reports on an exploratory study into the perceived benefits and challenges of using an electronic cancer prediction system, C the Signs, for safety netting within a Primary Care Network (PCN) in the East of England.

Methods: The study involved semi-structured interviews and a qualitative questionnaire with a sample of 15 clinicians and practice administrators within four GP practices in the PCN.

Results: Participants generally perceived benefits of C the Signs for managing and monitoring referrals as part of post-consultation safety netting. Clinicians made little use of the decision support function though, as part of safety netting during the consultation, and referrals were still sent by administrators, rather than directly by clinicians through C the Signs.

Conclusion: Emphasising the benefits of C the Signs for post-consultation safety netting is most likely to gain buy-in to the system from clinicians, and can also be used by administrators for shared visibility of referrals. More evidence is needed on the value of C the Signs for safety netting during the consultation, through better diagnosis of cancer, before this is seen as a valued benefit by clinicians and provides motivation to use the system.