Health Informatics Journal最新文献

Objective: Free text fields embedded within electronic consultation (eConsult) orders serve as rich sources of descriptive information regarding common uses of this novel telehealth technology. Simple text mining and language processing may efficiently extract key insights that help inform providers and administrators. Methods: Text data from eConsult orders placed within a single academic medical center were extracted from the electronic health record and examined. N-gram frequencies were used to describe the content of eConsult clinical questions and care recommendations. Results: 18,609 eConsults were ordered, with volumes ranging from 12 to 3839 orders across 28 subspecialties. Median character length for the clinical question was 189 and 1393 for specialist response text. Frequency count for top bigram varied greatly by specialty, with a high of 190 ("thyroid nodule") in Endocrinology and a low of 6 ("shoulder pain") in Orthopedics for clinical questions, and a high of 3139 ("ref range") in Endocrinology and a low of 6 ("surgical oncology") in Medical Oncology for specialist response. Discussion: Descriptive word sequences from NLP may provide limited insight into common use cases for eConsult across many subspecialties, though pre-processing was required to generate meaningful results.

Objective: Therefore, the objective of this study was to design hypertension ontology with the aim of improving integration of data, representation of knowledge and better decision making in hypertension management. Methods: First, we performed a systematic literature review (SLR) across ten different databases aiming at capturing the essential concepts. Using this extracted data a Hypertension Ontology (HPO) was created in Protégé which was loaded and published on BioPortal for availability. Results: HPO contains 114 classes and five properties that structure the risk factors, symptoms, diagnosis, and treatment. It improves knowledge discovery, data sharing capabilities, and surpasses existing hypertension-related ontologies in functionality. Conclusion: HPO facilitates standardized hypertension management in a research context and clinical practices. Next Steps will be integration of Real-world data and Interoperability to HER.

Objectives: Advances in technology have improved the lives of Indonesians. For example, the health sector. This is indicated by the emergence of telemedicine to facilitate health services. This study aims to test the effect of individual trust on the intention to use telemedicine applications. Therefore, the Technology Acceptance Model (TAM) and the Unified Theory of Acceptance and Use of Technology (UTAUT) are used as the basis for answering the questions posed by this research. Methods: Sampling was conducted online and involved 402 respondents who all came from the Indonesian island of Java. Validity, reliability, and hypothesis testing used Structural Equation Modeling (SEM) with Smart-PLS 4 tools. Result: The results show that effort expectancy, performance expectancy, and social influence have a positive influence on individual belief; intention to use is influenced by individual belief and behavioral intentions. The results of the hypothesis testing show that behavioral intention has the greatest influence on intention to use with a t value of 31.315 and a β value of 0.801. Conclusion: The novelty of this study is that it includes individual belief variables that are influenced by variables from UTAUT, namely effort expectancy, performance expectancy, social influence, and facilitating conditions.

Objective: Cancer centers must quickly integrate clinical genomics data from different vendors for oncology operations and research. Clinical data warehouse architectures are costly to construct and brittle, and they are not readily amenable to the rapid changes in oncology research. We introduce a cost-effective hybrid cloud Data Lake architecture for storing clinical genomic data from different vendors, aiding both clinical and research workflows. Methods: We created a Data Lake architecture based on the zone architecture, with four layers: ingestion, storage, transformation, and interaction. The layers are implemented with a hybrid cloud architecture. Rich metadata created from patient and genomic data enables patient-based queries, with access to data controlled through a data governance workflow. Results: Genomic data are stored in the cloud, synchronized with vendors' storage, and managed by a governance committee. The architecture implementation includes genomic test results from two vendors and supports independent clinical sites. The implementation serves 149 clinicians across 31 disease groups and stores 240 TB of data on 5800 patients at a monthly cost of approximately $350. Conclusion: The Data Lake architecture offers flexibility and scalability, making it suitable for organizations of all sizes to integrate clinical and genomic data efficiently for clinical and research purposes.

Introduction: Accurate, real-time immunization data is integral to the success of immunization programs. Standardized data can be aggregated, analyzed, and leveraged to conduct robust public health surveillance and inform strategic public health planning and prioritization. Standardization is also critical to the interoperability and portability of immunization records within and between jurisdictions. The Canadian Vaccine Catalogue (CVC), which aggregated standardized immunization data from multiple sources, was created to support interoperable immunization systems in Canada. Recommendations: Drawing on our experiences with the CVC and the broader Canadian healthcare system, we propose several recommendations to promote immunization standards adoption, including establishing robust governance processes, bridging the gap between public health and information technology partners, strategizing adoption of standards among electronic medical record vendors, and providing support for standards adoption. Conclusion: The CVC was a critical resource for supporting immunization interoperability in Canada, and provides valuable lessons for other jurisdictions seeking to develop a similar resource.

Objective: This review systematically synthesizes empirical evidence from past NEHR initiatives to identify critical gaps between knowledge and practice and provide actionable insights for policymakers, health IT leaders, and practitioners.Materials and Methods: A rapid review approach was employed, focusing on qualitative content analysis of empirical studies published between 2010 and 2024. The search covered the Scopus, PubMed, Medline, and CINAHL databases. A total of 24 studies met the eligibility criteria and were analyzed across key dimensions.Results: Our analysis reveals that successful NEHR implementation hinges on three interdependent factors: (1) Stakeholder engagement and governance-meaningful clinician involvement and adaptive leadership strategies are crucial for system adoption; (2) Institutional and cultural alignment-the tension between centralized mandates and local adaptation must be carefully managed; and (3) Technological and process standardization-balancing interoperability with customizability remains a persistent challenge. Notably, rigid top-down implementations often face resistance, whereas hybrid "middle-out" approaches tend to facilitate smoother transitions.Conclusions: NEHR deployments require a nuanced approach that integrates strategic decision-making, continuous stakeholder engagement, and flexible governance models. Policymakers and project leaders should prioritize participatory implementation strategies, adaptive standardization, and mechanisms for iterative learning to enhance the sustainability and effectiveness of these systems.

Objectives: In the early stages of the COVID-19 pandemic, evidence generation lagged behind public health responses. This study describes an international collaboration of frontline clinicians who used open data describing COVID-19 trends to generate "practice-based evidence". Methods: Open data resources from nine Northern Periphery and Arctic (NPA) countries were harnessed using the open-source programming language 'R' and our collaborations analyses and insights were published on a public-facing website. The website's visualisations guided teleconference discussions from September 2020 to March 2021, focusing on contextualizing national responses, especially in rural regions. Results: This project facilitated shared learning from COVID-19 trends and highlighted key aspects of national responses. Notably, rural NPA regions experienced less COVID-19 cases and mortality in the first year of the pandemic. Conclusion: This international collaborative effort, driven by open data analysis, provided a platform to share real-world insights. The study offers a potential template for future pandemics and emphasises the importance of sustaining open data resources, including granular data like excess mortality, for effective pandemic learning.

Objective: Business intelligence (BI) applications can result in higher smartness in hospitals. However, up to now, there has been a shortage of validated frameworks for assessing the smart levels of hospitals. Therefore, this study aims to develop a BI-based framework to assess the smart levels of hospitals. Methods: The research method is a combination of literature review, pilot test, and multi-case study. Results: The results of a multiple-case study approve the applicability of the framework since it can explain the status quo of the hospitals. Based on results of framework validity assessment with eight hospitals in Vietnam, the managerial implications for hospital directors to improve their smartness are suggested. Conclusions: The framework is anticipated to give hospitals the knowledge they need to address issues and difficulties in an organized manner, serving as both a benchmark for evaluating current capabilities and a guide for future development. However, the frameworks should be validated in other countries with the involvement of patients for more generalization.

Background: The health insurance industry faces challenges like inefficiencies, fraud, lack of transparency, and limited customization. With its decentralized structure, smart contracts, and immutable records, blockchain technology offers a transformative solution by enhancing transparency and operational efficiency. Objective: This study proposes a blockchain-based health insurance model to improve transparency, fairness, and efficiency while addressing existing limitations. Methods: The proposed framework integrates smart contracts with quadratic voting (QV) and advanced validation techniques, creating a democratic, secure, and customizable insurance process. Results: The model tailors personalized insurance plans to collective preferences using QV-based decision-making and dynamic pricing. Blockchain enhances trust and system reliability, while the inclusion of QV fosters inclusivity and fairness. Conclusion: By combining blockchain's decentralized architecture with QV, the proposed system overcomes the limitations of traditional insurance, offering a scalable, efficient, and equitable alternative that aligns individual preferences with societal health goals.

Objective: The study aims to assess the efficacy of various neural network architectures in predicting the National Early Warning Systems (NEWS) score, using vital signs, to enhance early warning and monitoring in clinical settings. Methods: A comparative evaluation of 29 neural network architectures, including Discriminant Analysis, Support Vector Machines, Logistic Regression, Decision Trees, Neural Networks, and Ensemble methods, was performed. These architectures were assessed based on accuracy, sensitivity, processing speed, model size, and execution time, using synthetically generated data representing 9000 clinical scenarios. Results: The analysis revealed that Linear Discriminant Analysis, narrow and medium Neural Networks, and specific Support Vector Machine (SVM) configurations, particularly Linear SVM, Quadratic SVM, and Coarse Gaussian SVM, achieved 100% accuracy and efficiency in predicting NEWS scores, making them suitable for real-time monitoring. Other architectures exhibited varying performance, with many failing to meet the required accuracy for clinical applications. Conclusion: The study identified Linear Discriminant Analysis and narrow and medium Neural Networks, along with Linear, Quadratic, and Coarse Gaussian SVMs, as optimal for integrating machine learning with NEWS, due to their precision, speed, and suitability for deployment in healthcare environments, particularly in Intensive Care Units.