Health Informatics Journal最新文献

{"title":"Implementation of Duke Machine Learning Data Quality Assurance Framework in a Pakistani Healthcare Institution.","authors":"Zarmeen Nasim, Nida Saddaf Khan, Mark Sendak, Khalid Aziz, Salma Tajuddin, Haroon Khan, Maaha Ayub, Mohummad Hassan Raza Raja, Mushyada Ali, Jee Young Kim, Henry David Jeffry Hogg, Alifia Hasan, Suresh Balu, Zahra Hoodbhoy, Zainab Samad","doi":"10.1177/14604582261486769","DOIUrl":"https://doi.org/10.1177/14604582261486769","url":null,"abstract":"<p><p>PurposeHigh-quality data are critical for developing healthcare machine learning (ML) models yet remain a major challenge in low- and middle-income countries (LMICs). This study evaluated the applicability of the Duke Institute for Health Innovation's (DIHI) Machine Learning Data Quality Assurance (ML-DQA) framework in an LMIC setting using two ML projects at a tertiary care hospital in Pakistan.MethodsWe applied the ML-DQA framework to two ML projects, Sepsis Watch (SW) and In-hospital Mortality Prediction (IMP). The framework comprises four phases: pre-DQA, data element pre-processing, ML-DQA checks, and ML-DQA adjudication, and was used to evaluate data quality and usability for both models.ResultsIn the pre-DQA phase, required data elements were identified through consultation with clinicians and project teams. During data element pre-processing, transformations and harmonization were performed, including consolidation of differently labelled glucose variables. ML-DQA checks assessed plausibility, conformance, and completeness, identifying elements that met quality standards. In the adjudication phase, reports were reviewed by two independent clinicians to determine suitability for model development.ConclusionsThe Duke ML-DQA framework effectively identified data limitations and informed model development, demonstrating its utility for assessing data quality and supporting ML implementation in resource-constrained settings.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 4","pages":"14604582261486769"},"PeriodicalIF":2.2,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149129426","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":"Nested named entity recognition in Chinese electronic medical records enhanced by part-of-speech and entity boundary knowledge.","authors":"Jianmei Wang, Yupeng Liao, Zhaoben Xie, Yongqiang Zhang","doi":"10.1177/14604582261495320","DOIUrl":"https://doi.org/10.1177/14604582261495320","url":null,"abstract":"<p><p>ObjectiveNested named entity recognition in Chinese electronic medical records (EMRs) is challenging because entity spans overlap and have ambiguous boundaries. We evaluated whether part-of-speech (POS) cues and automatically extracted entity boundary knowledge could improve a RoBERTa-GlobalPointer framework for this task.MethodsThis retrospective study used public, de-identified benchmark datasets. We evaluated a RoBERTa-wwm-ext-large-GlobalPointer framework with two enhancement branches: token-aligned POS embeddings derived from jieba. posseg and an entity boundary knowledge base (EBKB) constructed from entity head, tail and length patterns. The primary experiment used Chinese Medical Entity Extraction version 2 (CMeEE-V2), and supplementary test-set analyses used cEHRNER and CCKS2019.ResultsOn the CMeEE-V2 test set, the best configuration achieved 72.45% precision, 73.02% recall and 72.60% F1, outperforming the comparators. Ablation results indicated that boundary knowledge was the principal source of improvement, whereas POS features had a smaller effect. The cEHRNER test-set analysis provided additional cross-dataset evidence. Across five CCKS2019 test-set runs, F1 was 0.8152 ± 0.0096 for the knowledge-enhanced model and 0.7054 ± 0.0435 for the baseline (paired p=0.0043).ConclusionAutomatically extracted boundary knowledge was the main driver of improvement in the framework, while POS features acted as auxiliary cues. Findings were consistent across primary and supplementary test-set evaluations.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 4","pages":"14604582261495320"},"PeriodicalIF":2.2,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149139468","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 evaluation of type 1 diabetes mellitus-related videos on social video platforms: A cross-sectional study.","authors":"Yuan Hu, Xianrong Li, Jianling Yang, Fengmei Tan, Li Liu, Xinyue Zhou, Xiaolei Zhao","doi":"10.1177/14604582261500294","DOIUrl":"https://doi.org/10.1177/14604582261500294","url":null,"abstract":"<p><p>ObjectiveThis study aimed to assess the quality and reliability of videos about type 1 diabetes mellitus (T1DM) on TikTok, Bilibili, and YouTube.MethodsThe keyword \"type 1 diabetes mellitus\" was used to search for related videos on TikTok, Bilibili, and YouTube. The quality and reliability of 263 videos were assessed using the modified DISCERN (mDISCERN), the Global Quality Scale (GQS), and the Journal of the American Medical Association (JAMA) benchmark criteria.ResultsQuality scores of videos on YouTube were higher, and videos uploaded by specialists were rated higher than those posted by non-specialists. However, user engagement metrics (likes, comments, saves, and shares) did not correlate with quality scores, indicating that engagement alone does not reflect content quality.ConclusionThe quality and reliability of videos related to T1DM on these platforms were insufficient. Video platforms should recommend high-quality videos to guide viewers toward reliable sources.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 4","pages":"14604582261500294"},"PeriodicalIF":2.2,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149225362","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":"Predicting cholesterol screening behavior using machine learning: Social-ecological approach.","authors":"Wan-Chin Kuo, Jingyu Chen, Anthony D McDonald, Tingting Li, Jui-Hung Chang, Heather M Johnson","doi":"10.1177/14604582261500291","DOIUrl":"https://doi.org/10.1177/14604582261500291","url":null,"abstract":"<p><p>IntroductionCurrent preventive screening reminders use generic due-date notifications that lack personalization. Targeted reminders allow personalized messages and resource allocation, yet the accuracy of behavioral forecasting with cholesterol screening behaviors remains unconfirmed. Therefore, this study aims to examine the accuracy of machine learning in predicting adults' future cholesterol screening behavior.MethodsThis study included 8,288 participants from the Health and Retirement Study. Never receiving cholesterol screening over 12 years of follow-up (2007-2018) was identified as the target outcome. Predictors were constructed based on the Social-Ecological Model. Four machine learning (ML) algorithms were compared: logistic regression, random forests, gradient boosting machine (GBM), and eXtreme Gradient Boosting (XGBoost). Model performance was evaluated by Recall, Precision, and false-negative rate (FNR).ResultsAmong the four ML algorithms, XGBoost performed best, with higher Recall (average: 0.8850) and the lowest FNR (0.1311), but suboptimal precision (average: 0.6228). The top five predictors were past cholesterol screening behavior, diagnosis of hypertension, osteoarthritis or rheumatoid arthritis, number of private insurance plans, and gender.ConclusionML might be used to predict individuals' cholesterol screening behavior. Future research is needed to examine whether leveraging ML in targeted reminders might enhance cholesterol screening behaviors.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 4","pages":"14604582261500291"},"PeriodicalIF":2.2,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149229412","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":"Development and application of an ERAS nursing pathway for lung cancer patients following day-surgery.","authors":"Huadi Yuan, Liyan Gao, Nafei Han, Lingling Hong, Hong He","doi":"10.1177/14604582261492552","DOIUrl":"https://doi.org/10.1177/14604582261492552","url":null,"abstract":"<p><p>ObjectivesTo develop and implement an Enhanced Recovery After Surgery (ERAS) nursing pathway for lung cancer patients undergoing day surgery, and to evaluate its impact on perioperative nursing compliance, postoperative outcomes, and nurse satisfaction.MethodsA quasi-experimental study was conducted in a tertiary-level hospital in Zhejiang Province from September 2021 to March 2022. A total of 671 lung cancer patients and 57 nurses were included. Patients were assigned to either a control group receiving routine perioperative care or a study group managed under an ERAS nursing pathway. The ERAS intervention included structured training, standardized perioperative nursing procedures, and a visual pathway-based guidance system. Key perioperative compliance indicators and clinical outcomes were collected and compared between groups.ResultsImplementation of the ERAS nursing pathway significantly improved multiple compliance indicators, including preoperative education rate, early postoperative feeding rate, early ambulation rate, elastic stocking usage rate, ankle pump exercise compliance, and breathing training compliance. In addition, postoperative complication rates and delayed discharge rates were reduced in the ERAS group compared with the control group. Nurses reported a high level of satisfaction with the ERAS system.ConclusionThe ERAS nursing pathway effectively improves perioperative nursing compliance and postoperative recovery outcomes in lung cancer day-surgery patients, while reducing complications and delayed discharge. It also enhances nursing workflow standardization and staff satisfaction, supporting its clinical value and broader implementation in surgical nursing practice.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 4","pages":"14604582261492552"},"PeriodicalIF":2.2,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149139438","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 lightweight machine learning approach for predicting breast cancer risk based on routine clinical indicators in the Chinese population.","authors":"Duo Dai, Min Ma","doi":"10.1177/14604582261477932","DOIUrl":"10.1177/14604582261477932","url":null,"abstract":"<p><p>BackgroundConventional breast cancer screening is limited by cost, access, and patient discomfort. Whether a lightweight machine-learning model trained on routine laboratory indicators can support opportunistic screening remains unsettled.MethodsA retrospective cohort of 13,285 individuals (1,216 ICD-10 C50 cases, 12,069 controls) from a Chinese tertiary hospital during 2022 to 2024 was analysed with a leakage-controlled pipeline. Six classical learners and LightGBM were trained on twenty indicators, then assessed by discrimination, calibration, decision-curve analysis, and zero-shot UK Biobank validation.ResultsThe lightweight LightGBM achieved an internal AUC of 0.987 with sensitivity 0.835, specificity 0.983, Brier 0.026, and an external AUC of 0.83, training in 5.6 s within 1.65 MB.ConclusionThe model is a candidate low-cost triage tool, pending multicentre prospective validation and recalibration.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 3","pages":"14604582261477932"},"PeriodicalIF":2.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148834812","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":"Development and formative usability evaluation of a user-centered mobile application for COPD self-management.","authors":"Guofang Tao, Su Yang, Luqing Gao, Yudi Yu, Xiting Huang, Lihua Huang","doi":"10.1177/14604582261467686","DOIUrl":"https://doi.org/10.1177/14604582261467686","url":null,"abstract":"&lt;p&gt;&lt;p&gt;BackgroundChronic Obstructive Pulmonary Disease (COPD) is a globally burdensome chronic disease characterized by persistent respiratory symptoms and progressive airflow limitation, which severely impairs patients' quality of life and prognosis. Effective self-management is crucial for COPD management, as targeted self-management interventions have been shown to improve disease outcomes. Digital health technologies (DHTs) offer an innovative approach to address the challenges of traditional self-management and provide sustainable support for patients' long-term disease management. However, existing digital interventions for COPD commonly face several major challenges, including low user engagement, poor long-term adherence, and high participant withdrawal rates, highlighting an urgent need for optimized digital solutions.ObjectiveThis study aimed to develop a user-centered mobile application tailored to meet self-management needs of patients with COPD under the guidance of the Centre for eHealth and Wellbeing Research (CeHRes) Roadmap and persuasive system design (PSD) principles, as well as to evaluate its usability performance.MethodsThe development of the COPD Digital Health Self-Management System (COPD DHSS) was guided by the CeHRes Roadmap.The process commenced with a comprehensive literature review, semi-structured interviews involving fifteen COPD patients and five healthcare providers, and expert panel discussions (n=7) to identify challenges in COPD self-management and define the key values for the DHTs into self-management protocols. Based on these key values, the research team identified PSD features. These PSD features were integrated with COPD self-management evidence synthesis and were utilized to inform the design of the COPD DHSS prototype. A mixed-methods evaluation was employed: Sixteen COPD patients were recruited to test the COPD DHSS. After one month of system deployment, the System Usability Scale (SUS) was administered to evaluate usability metrics. Participants subsequently engaged in focus group discussions to provide feedback on user experience.ResultsA User-Centered Mobile Application for COPD was successfully developed through a structured process. The system integrated patient self-reported data with evidence-based best practices for COPD self-management, generating personalized recommendations to enhance patients' self-management capabilities and improve disease prognosis and quality of life. Usability testing was conducted with 16 COPD patients, whose average age was 71.5 (±6.9) years. Of these participants, 14 (87.5%) maintained twice-weekly app usage throughout the evaluation period. The median SUS score was 76.25(66.88, 83.13),indicating an acceptable level of usability. User feedback consistently indicated that the COPD DHSS demonstrated favorable usability characteristics.ConclusionsIntegrating the CeHRes Roadmap with PSD principles, this study successfully developed a usable, user-centered mobile applicat","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 3","pages":"14604582261467686"},"PeriodicalIF":2.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148690128","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":"Insights from a digital health literacy coaching intervention for patients with hypertension in the emergency department: A cohort study.","authors":"Colton Hood, Manuel Rebol, Sara Belay, Akshay Krishnan, Andrew Meltzer, Camille Jefferson, Neal Sikka","doi":"10.1177/14604582261475495","DOIUrl":"https://doi.org/10.1177/14604582261475495","url":null,"abstract":"<p><p>ObjectiveDigital health literacy (DHL), as part of the social determinants of health, affects health outcomes. To address the problem of poor DHL in under-served populations, we designed a study to provide coaching for participants with poor DHL and hypertension to observe it's impact on digital health literacy including self-efficacy.MethodsThe participants were recruited from the emergency department. We performed a non-randomized experimental cohort study in which coaches provided monthly sessions to participants on digital literacy and health management topics that could help to track their progress and change their behavior. Multiple instruments were administered longitudinally, including measures of self-efficacy in digital literacy, loneliness, nutrition, activity and blood pressure tracking.ResultsParticipants demonstrated trends toward increased self-efficacy, digital communication, activity, and reduced loneliness. The qualitative results from the intervention combine to provide insights regarding the most important factors for successful DHL interventions.ConclusionsThis study demonstrates that a structured coaching intervention can enhance a patient's self-confidence in managing their health overall, their chronic condition, and their use of digital tools.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 3","pages":"14604582261475495"},"PeriodicalIF":2.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148763275","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":"Development and pilot application of a visual usability evaluation checklist for mHealth app interfaces among rural users in China.","authors":"Chanjuan Tu, Songqi Yao, Ying Zhang","doi":"10.1177/14604582261479243","DOIUrl":"https://doi.org/10.1177/14604582261479243","url":null,"abstract":"<p><p>ObjectiveTo develop and preliminarily assess the usability of a visual usability checklist designed for rural users to evaluate the mHealth interfaces and provide practical feedback to designers.MethodsA two-phase research design was adopted: the first phase involved developing checklist items through a literature review, followed by a pilot application with 30 rural users from various regions of China and the Spring Rain Doctor App to assess the checklist's effectiveness.The resultsThe item checklist identified 6 dimensions and 40 items, with a focus on rural Chinese users. In the pilot application, older users took a median of 13 minutes (IQR: 9.5-16), whereas younger users finished in 3 minutes (IQR: 2-5). The results revealed that older rural users are less familiar with mHealth apps than younger users are. The evaluation results, together with the Mann-Whitney U test results, indicate that the checklist has initial potential for assessing the usability and experiences of Chinese rural mHealth users.ConclusionThis study developed a domain-specific checklist for assessing the visual usability of mHealth applications for rural users, providing product designers with a structured visual evaluation tool to better understand the needs of rural users and guide optimization of the mHealth application's UI.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 3","pages":"14604582261479243"},"PeriodicalIF":2.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148893125","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 the quality and reliability of inflammatory bowel disease-related short videos on BiliBili and TikTok: A cross-sectional study.","authors":"Bowen Cheng, Xiaoyan Chen, Wenjie Shi, Xiaojiang Zhou","doi":"10.1177/14604582261471307","DOIUrl":"10.1177/14604582261471307","url":null,"abstract":"<p><p>BackgroundInflammatory Bowel Disease (IBD) is a chronic condition with increasing global prevalence. Short-video platforms like TikTok and Bilibili are popular health information sources, but their IBD-related content quality remains uncertain.ObjectiveTo assess the quality and reliability of IBD-related videos on TikTok and Bilibili.MethodsWe analyzed the top 100 IBD-related videos from each platform (200 total). Quality was evaluated using Global Quality Scale (GQS), modified DISCERN (mDISCERN), and JAMA benchmarks. Engagement metrics and quality scores were correlated.ResultsTikTok videos had higher engagement (P < .001) and better median scores (GQS: 3, mDISCERN: 3, JAMA: 3) than Bilibili (GQS: 3, mDISCERN: 3, JAMA: 3; P < .05). Gastroenterologist-created videos scored highest. GQS correlated positively with engagement (r = 0.16-0.26, P < .05), while mDISCERN correlated only with likes, shares, and saves (r = 0.16-0.18, P < .05). JAMA scores negatively correlated with duration (r = -0.24, P < .001).ConclusionsIBD-related short videos showed moderate quality, with TikTok outperforming Bilibili. Gastroenterologist-produced content was most reliable. Viewers should critically evaluate such health information to avoid misinformation.</p>","PeriodicalId":55069,"journal":{"name":"Health Informatics Journal","volume":"32 3","pages":"14604582261471307"},"PeriodicalIF":2.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148498425","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}