Health Informatics Journal最新文献

{"title":"Using network databases for data fusion for the study of the promotion of youth mental well-being.","authors":"Harsha Krishna, Adam S Darwich, Sebastiaan Meijer","doi":"10.1177/14604582261485434","DOIUrl":"https://doi.org/10.1177/14604582261485434","url":null,"abstract":"<p><p>Promoting mental well-being among young people is a pressing need for Sweden to mitigate declines in health among the next generation. To achieve this, various programs have been implemented at both the school and municipal levels. Different municipalities implement programs, monitor, and collect data on youth mental well-being within their areas. Analysis of these data is challenging because data silos exist across institutions. System-level assessment has been difficult in both the reasoning and decision-making phases, and in attributing the impact of these strategies to the specific actions taken by municipalities.In this work, we propose using a data fusion approach to create a common dataset for studying youth mental well-being by combining data from various departments across Swedish municipalities. We identify the required datasets, along with their schemas, metadata, and definitions, and develop a graph database design that defines standard terms and related concepts. We deploy this min two Stockholm municipalities to demonstrate the approach's ability to query across different institutional datasets through the common graph schema. Finally, we outline the use of a graph database in a participatory setting to better understand programs that promote youth mental well-being across departments in both municipalities.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 3","pages":"14604582261485434"},"PeriodicalIF":2.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148889323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing nursing workflow and patient safety through an intelligent catheter risk alert system: A pre-post implementation study.","authors":"Ying Lu, Xiaohong Zhang, Xiangjin Diao, Zhen Cai, Shuai Cao","doi":"10.1177/14604582261491829","DOIUrl":"https://doi.org/10.1177/14604582261491829","url":null,"abstract":"<p><p>ObjectiveTo evaluate the effectiveness of an intelligent catheter risk-warning system in enhancing patient safety and nursing quality.MethodsA pre-post implementation study in a tertiary hospital with nursing staff (n = 205) and patients with urinary or gastrointestinal catheters. The system integrated catheter care, maintenance overview, and QR-based patient education, enabling real-time alerts and automated label generation. Data on unplanned extubation rates, PSSUQ scores, nursing satisfaction, and labeling errors were compared before and after implementation.ResultsUnplanned nasogastric tube removal decreased from 0.852‰ to 0.501‰, while urinary catheter removal decreased from 0.219‰ to 0.114‰. PSSUQ scores and nursing satisfaction improved significantly after system implementation (P < 0.001). Label color selection and label clarity also improved significantly (P < 0.05).ConclusionThe intelligent catheter risk alert system significantly reduced unplanned extubation rates and improved nursing workflow, providing a scalable model for enhancing patient safety in catheter management.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 3","pages":"14604582261491829"},"PeriodicalIF":2.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148992433","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating artificial intelligence into surgical nursing workflows: Evaluation of an image-based Instrument verification system.","authors":"Zu-Chun Lin, Hui-Chien Hung, Malcolm Koo, Yu-Ju Lin, Tzu-Chuan Hsu","doi":"10.1177/14604582261468225","DOIUrl":"https://doi.org/10.1177/14604582261468225","url":null,"abstract":"<p><p>ObjectiveThis study compared an image-based, artificial intelligence-driven instrument recognition and inventory system (AI-IRIS) with conventional manual counting (CMC) for postoperative instrument management in simulated settings.MethodsUsing a randomized crossover design, 34 operating room nurses completed two standardized counting scenarios with both methods and rated adoption using the Diffusion of Innovations Questionnaire (DOIQ).ResultsRecognition accuracy was identical between AI-IRIS and CMC under controlled, simulated conditions. However, the AI-IRIS significantly reduced counting time by 26-28 seconds per scenario, representing an approximately 33-35% reduction compared with manual counting (both p < 0.001), and achieved higher DOIQ scores (mean difference 7.9 points, p < 0.001).ConclusionsThe AI-IRIS improved efficiency and user perception without compromising accuracy. These findings suggest potential to support safety-related counting processes and streamline workflows. Future research should assess its integration in real-world perioperative environments and across diverse instrument sets and pack configurations.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 3","pages":"14604582261468225"},"PeriodicalIF":2.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148426827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Nursing role and practice integration in telemedicine models for systemic lupus erythematosus a scoping review.","authors":"Qiuying Jiang, Yamei Chen, Yin Gu, Xinxin Shao, XinYi Gao","doi":"10.1177/14604582261477937","DOIUrl":"https://doi.org/10.1177/14604582261477937","url":null,"abstract":"<p><p>This review systematically analyzed the existing evidence regarding the integration of telemedicine into nursing roles and practices for managing patients with systemic lupus erythematosus (SLE). The conduct and reporting of this scoping review followed the PRISMA-ScR checklist. A total of six studies were identified through searches conducted across five major databases, including PubMed and Web of Science, and were subsequently included in the analysis. The findings indicate that telemedicine significantly enhances access to care, reduces the incidence of missed appointments, and improves patient satisfaction and adherence to treatment protocols. Additionally, digital tools, such as mobile applications and remote coaching, have been shown to effectively improve patients' quality of life and self-management capabilities. Within telemedicine frameworks, nurses undertake diverse roles, including those of educators, coordinators, and supporters. Nevertheless, some studies have reported increased hospitalization rates among patients in the telemedicine group, highlighting potential limitations in detecting subtle clinical changes. Overall, telemedicine represents a viable adjunct to traditional SLE care models, particularly for patients with limited resources or mobility constraints. However, the standardized implementation and long-term efficacy of telemedicine require further investigation through high-quality research.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 3","pages":"14604582261477937"},"PeriodicalIF":2.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148759628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of the large language models Chatbot's responses to frequently asked queries on refractive errors.","authors":"Sare Safi, Amir Golmakani, Saeed Rahmani, Nikoo Bayan, Seyed Mohamadmehdi Moshtaghion, Hadis Najafimehr, Haleh Kangari","doi":"10.1177/14604582261470624","DOIUrl":"https://doi.org/10.1177/14604582261470624","url":null,"abstract":"<p><p>PurposeTo assess the accuracy, comprehensiveness, and reliability of Large Language Model chatbots in answering frequently asked questions about refractive errors.MethodsForty-four questions about refractive errors were posed to four chatbots, including Copilot, Perplexity, Gemini, and ChatGPT. Responses to each question were independently evaluated by three experts using a three-point accuracy scale. The readability of the chatbots' responses was evaluated using several indices. Similarity was assessed using Sentence-Bidirectional Encoder Representations from Transformers (SBERT). Inter-rater agreement among the graders was evaluated using the Gwet Agreement Coefficient 1 (AC1) statistic.ResultsThe overall agreement among the graders for all chatbot responses was almost perfect (Gwet AC1: 0.87). All chatbots received scores above 85% in every category, and there was no significant difference in chatbot accuracy scores (<i>P= 0.168</i>). The highest mean comprehensiveness score was observed for Perplexity (8.13 ± 0.95, <i>P</i> = 0.028). The similarity scores of the chatbots were very close to each other. All readability scores showed significant differences (<i>P</i><0.001) between the chatbots.ConclusionAll four chatbots showed comparable accuracy in answering questions about refractive errors. Readability levels of all chatbots exceeded public health recommended thresholds; however, ChatGPT produced relatively more accessible output.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 3","pages":"14604582261470624"},"PeriodicalIF":2.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148521589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quality and reliability of glioma treatment videos on Chinese short-video platforms: A cross-sectional study.","authors":"Yixuan Li, Yingying Zhang, Can Zhu, Yimin Han, Xinyun Gao, Juanqing Yue, Ying Wang","doi":"10.1177/14604582261485153","DOIUrl":"10.1177/14604582261485153","url":null,"abstract":"<p><p>BackgroundShort-video platforms increasingly influence patients' access to glioma treatment information; however, the quality and reliability of such content remain unclear.MethodsThis cross-sectional study analyzed 200 high-visibility Chinese-language videos on TikTok and Bilibili (TikTok, n = 103; Bilibili, n = 97). Videos were evaluated for engagement metrics, uploader characteristics, and content coverage. Information quality and reliability were assessed using the Global Quality Score, modified DISCERN, Journal of the American Medical Association benchmark criteria, and the Patient Education Materials Assessment Tool.ResultsTikTok videos were shorter and received greater user engagement than Bilibili videos, while also achieving higher Global Quality Score and modified DISCERN scores. Professional uploaders provided more reliable and evidence-based content, whereas non-professional videos were longer and attracted significantly more comments (p < 0.001); differences in likes, collections, and shares were not statistically significant. Only 30.0% of videos addressed grade- or molecular-specific treatment pathways, and prognostic factors were discussed in only 15.5% of videos; recurrence management and long-term care were seldom covered. Engagement metrics were weakly correlated with quality scores, indicating a mismatch between popularity and information quality.ConclusionsChinese-language short videos on glioma treatment provide accessible but uneven patient education. Verified medical authorship, guideline-based content labeling, and quality-weighted recommendation strategies may improve the visibility of trustworthy information.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 3","pages":"14604582261485153"},"PeriodicalIF":2.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148882780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative analysis of AI enhancements to rules-based clinical triage chatbot: Convergent mixed-methods study.","authors":"Aleksa Stankić, Dušan Vujošević, Nemanja Radosavljević, Adrijana Jeremić","doi":"10.1177/14604582261485150","DOIUrl":"https://doi.org/10.1177/14604582261485150","url":null,"abstract":"<p><p>BackgroundChatbots are increasingly used in healthcare for symptom checking and care navigation. However, concerns about accuracy limit large language model (LLM) use in clinical settings.ObjectiveThis convergent mixed-methods study evaluated three enhancements to an existing rules-based triage chatbot. The purpose is to inform the development of tools improving patient access and system navigation.MethodsThree artificial intelligence tools (Dialogflow, ChatGPT, and Gemini) were integrated into a rules-based workflow from December 21st 2024 to July 7th 2025. Thirteen testers completed 156 vignette-based interactions and 52 Likert-scale evaluations from July 17th 2025 to August 5th 2025. Quantitative outcomes included accuracy, conversational turns, time to completion, and tester ratings. Qualitative feedback was thematically analyzed.ResultsThe rules-based chatbot was most accurate (71.8%, 95% CI 56.2-83.5%), outperforming Dialogflow (30.8%, p = 0.002) and Gemini (41.0%, p = 0.031). Dialogflow, ChatGPT, and Gemini were statistically indistinguishable. Qualitative analysis revealed user preference for ChatGPT and Gemini despite equal or worse performance than the rules-based chatbot.ConclusionRules-based triage remained most reliable, and the divergence between user preference and measured accuracy underscores that safe clinical deployment of LLM-based chatbots requires governance addressing accuracy, interpretability, and masking of poorer performance by conversational fluency.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 3","pages":"14604582261485150"},"PeriodicalIF":2.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148945474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A hybrid approach for diabetic retinopathy stages classification using spatial and textural features.","authors":"Mohsan Naqi, Muhammad Arfan Jaffar, Rab Nawaz Bashir, Tahir Rashid, Bayan AlGhofaily, Noor Ayesha, Faten S Alamri","doi":"10.1177/14604582261464215","DOIUrl":"10.1177/14604582261464215","url":null,"abstract":"<p><p>Diabetic Retinopathy (DR) is a medical condition in which high blood sugar levels damage the retina's blood vessels. Existing Solutions for multi-class DR identification are computationally intensive and also suffer from low accuracy. There is an immense need for an automated, computationally efficient approach for monitoring DR progression in diabetic patients. The study proposed Random Forest (RF), Logistic Regression (LR), Decision Tree (DT), and Gaussian Naive Bayes (GNB) models for the classification of retinal images into five DR classes (No, Mild, Moderate, Proliferate, and Severe) using spatial features extracted through a Convolutional Neural Network (CNN), textural features extracted through a Grey Level Co-occurrence Matrix (GLCM), and hybrid features by combining these features. The CNN, EfficientNet, PyramidCNN, and Pyramid Vision Transformer (PVT) were also evaluated for the classification of DR stages. The results revealed that the RF model with hybrid features outperformed, with an accuracy of 98.00% and high performance across all evaluation metrics, with a 1.00% increase over existing approaches. The EfficientNet model also performs competitively with 97.00% accuracy. The ML models also emerged as computationally efficient in terms of training and inference time for deployment in low-resource clinical environments for automated monitoring of DR progression in diabetic patients.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 3","pages":"14604582261464215"},"PeriodicalIF":2.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148370866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reflective openEHR-to-FHIR: Java class-based generator for transforming openEHR compositions to fast healthcase interoperability resources (FHIR) bundles.","authors":"Nektarios Ladas, Stefan Franz, Alina Rehberg, Andreas Büchner, Michael Marschollek, Matthias Gietzelt","doi":"10.1177/14604582261448775","DOIUrl":"https://doi.org/10.1177/14604582261448775","url":null,"abstract":"<p><p>BackgroundAt our hospital's university, the data integration center (DIC) has the primary task of importing data from various systems, including unstructured medical reports and structured laboratory data into the openEHR data repository. As we participate in the German Medical Informatics Initiative (MII), we have an agreement to share common consent data for research purposes. The requirement for this is that the data must be available in the FHIR format.ObjectivesAs a result, we have to transform our openEHR into FHIR data. Both formats are different, and simply programming a module to transform each openEHR template into a FHIR resource can be time-consuming and neither supportable nor updatable.MethodsWe have designed a method and developed an open-source software artifact that transforms an openEHR composition into a single FHIR resource or a bundle of resources, through the dynamic declaration of openEHR fields to API methods. The mappings can be updated at runtime, while the software artifact allows developers and end users to test and validate the mappings.ResultsWe currently use our software, which is able to do robust transformations and has, until now, successfully stored and processed over 30 million FHIR bundles.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 3","pages":"14604582261448775"},"PeriodicalIF":2.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148690195","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating order management performance within ERP-supported healthcare supply chains: Evidence from the UAE.","authors":"Dina Al Nuaimi, Md Hafizur Rahman, Amina Tariq","doi":"10.1177/14604582261478483","DOIUrl":"https://doi.org/10.1177/14604582261478483","url":null,"abstract":"<p><p>ObjectivesThis study aimed to evaluate order management (OM) efficiency and fulfilment performance within ERP-supported healthcare supply chains during the COVID-19 pandemic in the United Arab Emirates (UAE). The study was motivated by the increasing need for resilient digital supply chain systems capable of supporting uninterrupted access to critical medical supplies during public health emergencies.MethodsA quantitative retrospective longitudinal design was employed using secondary ERP data extracted from 14 Emirates Health Services (EHS) healthcare facilities between 2020 and 2022. A total of 87 essential medical and pharmaceutical items across four categories, including COVID-19 medications, supportive medications, personal protective equipment (PPE)/disposables, and vaccines, were analyzed. Order fulfilment rate was used as the primary performance indicator and compared against the healthcare industry benchmark of 95%. Wilcoxon Signed-Rank and Friedman tests were conducted to assess differences in fulfilment performance across study years and healthcare facility types.ResultsERP-supported healthcare supply chains demonstrated standardized order processing and operational coordination during the early stages of the pandemic; however, observed performance patterns were likely influenced by additional factors including supply disruptions, supplier constraints, and changing demand conditions. Hospitals and primary healthcare centres demonstrated relatively high and stable fulfilment performance in 2020 and 2021. However, statistically significant variability and declines in fulfilment rates were observed in 2022 across several supply categories, particularly within public health centres. Overall, fulfilment rates remained below the 95% benchmark throughout the study period.ConclusionThe findings indicate that healthcare supply chains operating within ERP-supported environments maintained operational continuity and supply chain coordination during the COVID-19 pandemic. However, the observed performance patterns suggest that ERP systems alone may not be sufficient to ensure optimal healthcare supply chain resilience during large-scale disruptions. Integrating ERP systems with advanced analytics, supplier diversification strategies, and real-time decision-support tools may further strengthen healthcare supply chain performance and emergency preparedness.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 3","pages":"14604582261478483"},"PeriodicalIF":2.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148893173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}