JMIR nursing最新文献

{"title":"Correction: Nursing Informaticians in Spain: Scoping Review and Expert-Validated Gap Analysis.","authors":"Adrián Marco-Moyano, Patricia Verdú Rodríguez, Manuel Lillo-Crespo","doi":"10.2196/100481","DOIUrl":"10.2196/100481","url":null,"abstract":"","PeriodicalId":73556,"journal":{"name":"JMIR nursing","volume":"9 ","pages":"e100481"},"PeriodicalIF":5.0,"publicationDate":"2026-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13459723/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148708857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Inpatient Nurses' Anticipatory Perspectives on Assistive Robots: Qualitative Study.","authors":"Mavis Weiting Tan, Timie Lai Teng Chan, Charmaine Shi Min Taye","doi":"10.2196/91106","DOIUrl":"10.2196/91106","url":null,"abstract":"<p><strong>Background: </strong>Assistive robots have been proposed to support nursing work by offloading routine, logistical, and physically demanding tasks. However, existing research has largely focused on postimplementation acceptance or usability, with fewer studies examining how nurses conceptualize assistive robots before routine deployment, particularly in settings where exposure remains limited.</p><p><strong>Objective: </strong>This study aimed to explore inpatient nurses' anticipatory perspectives on assistive robots and to examine how perceived benefits, concerns, and implementation conditions are constructed at the preimplementation stage.</p><p><strong>Methods: </strong>A qualitative descriptive study was conducted using semistructured, face-to-face interviews with 16 registered nurses aged 21 to 32 years from 4 general medical wards in a public tertiary hospital in Singapore. At the time of data collection, assistive robots had not been routinely implemented; participants' exposure was limited to pilots, demonstrations, and indirect sources. Interview transcripts were analyzed using reflexive thematic analysis.</p><p><strong>Results: </strong>Participants' accounts reflected anticipatory acceptance characterized by cautious optimism regarding the potential of assistive robots to support nursing work, alongside concurrent concerns about safety, professional identity, relational care, and implementation feasibility. Four themes were developed: anticipatory optimism shaped by indirect exposure; negotiating uncertainty, safety, and professional boundaries; imagining assistive robots as workload and workflow support; and conditions for responsible implementation. Concerns centered on professional identity, patient safety, ethical boundaries, loss of human touch, technical reliability, cost-effectiveness, and organizational feasibility. Participants viewed assistive robots as acceptable only if they were integrated into nursing workflows, preserved clinical judgment and relational care, and were supported by training, technical infrastructure, leadership commitment, and clear governance.</p><p><strong>Conclusions: </strong>Nurses' anticipatory perspectives suggest that acceptance of assistive robots depends not only on perceived usefulness, but also on alignment with professional values, patient safety, relational care, and organizational readiness. Early nurse involvement, human-centered implementation, structured training, and clear governance are needed to ensure that assistive robots augment rather than undermine nursing practice.</p>","PeriodicalId":73556,"journal":{"name":"JMIR nursing","volume":"9 ","pages":"e91106"},"PeriodicalIF":5.0,"publicationDate":"2026-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13455852/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148708812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Nurse-Led Ambient AI Scribe for Patient Safety Incident Investigation Reports (Project NARRATE): Retrospective Pre-Post Comparative Document-Quality Study.","authors":"Kai Yunn Teo, Liwen Huang, Kelly Chai Yuen Woh, Shin Yuh Ang, Jade Gaik Nai Ng","doi":"10.2196/100775","DOIUrl":"10.2196/100775","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Patient safety investigation reports support organizational learning only when they are complete, usable, and sufficiently detailed. Conventional free-text reports are often inconsistent and may omit information needed for review and learning. Project NARRATE (Nursing AI-Refined for Accurate Transcription of Events) is a nursing-led ambient artificial intelligence workflow that uses prompts aligned with the World Health Organization Minimal Information Model for Patient Safety Incident Reporting and Learning Systems, Situation-Background-Assessment-Recommendation output, and visible missing-information cues to support structured supervisor reporting.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aimed to compare the completeness and narrative quality of conventional and NARRATE-period supervisor investigation reports for falls and medication administration-related incidents.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We conducted a retrospective pre-post document-quality study at a tertiary academic medical center in Singapore. We reviewed 150 deidentified completed supervisor investigation reports: 75 conventional reports from June to August 2025 and 75 confirmed NARRATE reports from January to March 2026. NARRATE use was voluntary, and recorded use represented approximately 40% of eligible postimplementation reports. Two blinded reviewers rated reports using a World Health Organization (WHO)-aligned completeness checklist and an adapted 8-domain Physician Documentation Quality Instrument (PDQI). Report-level comparisons were adjusted for repeated reports by the same supervisor using random-intercept linear mixed-effects models. A stratified 60-report plain-paragraph rerating examined whether visible structure influenced ratings.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;All 150 reports were analyzed. Unadjusted mean WHO total completeness was 11.81 (SD 3.39) for conventional reports and 13.61 (SD 2.54) for NARRATE reports; the unadjusted difference was 1.80 points, and the cluster-adjusted mean difference was 1.95 (95% CI 0.91-3.00; P&lt;.001). The adapted PDQI mean was 3.61 (SD 0.52) and 4.13 (SD 0.34), respectively; the unadjusted difference was 0.52 points, and the cluster-adjusted mean difference was 0.53 (95% CI 0.37-0.69; P&lt;.001). In the plain-paragraph sensitivity analysis, the completeness advantage remained (adjusted mean difference 1.70, 95% CI 0.27-3.14; P=.02), as did the adapted PDQI mean advantage (adjusted mean difference 0.25, 95% CI 0.06-0.43; P=.009). Explanation, organization, and comprehensibility remained significantly higher after deformatting; actions were borderline (P=.05), and synthesis, internal consistency, and fairness/balance were not statistically significant.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;Among voluntary early adopters, NARRATE use was associated with more complete reports and higher adapted PDQI mean scores after accounting for supervisor clustering. Because recorded use represented approximately 40","PeriodicalId":73556,"journal":{"name":"JMIR nursing","volume":"9 ","pages":"e100775"},"PeriodicalIF":5.0,"publicationDate":"2026-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13456676/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148708860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Facilitating Teamwork With Minimal Interaction via a Mesh-Based Communication Device in a Clinical Nursing Setting: Intervention Study.","authors":"Yujiro Matsuishi, Masakazu Hirokawa, Yoshiaki Inoue, Kenji Suzuki","doi":"10.2196/85599","DOIUrl":"10.2196/85599","url":null,"abstract":"<p><strong>Background: </strong>The prevention of medical errors depends on effective communication and teamwork between nurses, yet traditional nurse call systems create inefficiencies that result in higher staff workloads. Further research is needed to evaluate how digital health care technologies affect nursing workflows and whether they contribute to staff workload.</p><p><strong>Objective: </strong>This study aimed to evaluate whether a smartphone app using Bluetooth Low Energy (BLE) Mesh-based signal communication could enhance nurse-to-nurse communication, decrease response times, and improve teamwork as measured by the TeamSTEPPS Teamwork Perceptions Questionnaire (T-TPQ).</p><p><strong>Methods: </strong>We conducted a between-subjects (independent groups) interventional study on an acute care ward, with 3 intervention days (BLE Mesh app use) and 3 nonintervention days administered on alternating days. Thirty nurses (15 per condition) participated, with no nurse contributing observations to both conditions in the final analysis. Response times were tracked, and the T-TPQ was used to evaluate Situation Monitoring and Mutual Support perceptions at the end of each shift.</p><p><strong>Results: </strong>The app shortened the total response duration from a per-nurse median of 38.5 (IQR 31.0-58.5) seconds in the control condition to 19.5 (IQR 18.5-23.5) seconds in the intervention condition (n=15 per condition; Mann-Whitney U test=217.5; P<.001; rank-biserial r=-0.93). The app reduced the time it took for staff to confirm nursing actions, search for items, and request care assistance. A total of 40 nurses participated, generating 48 questionnaire responses; after exclusions, 30 nurses (15 per condition) were analyzed. T-TPQ confirmed significant improvements in Situation Monitoring (3.04 vs 3.39; P=.001) and Mutual Support (3.01 vs 3.31; P=.003). Post hoc power ranged from 87% to 92% (Cohen d>1.0), supporting the interpretability of these results.</p><p><strong>Conclusions: </strong>BLE Mesh technology reduces basic signal communication delays, which shortens nurse response times and enhances team performance through improved Situation Monitoring and Mutual Support, according to our research. The study demonstrates how this technology delivers functional benefits that enhance nursing communication to produce superior team-based care outcomes.</p>","PeriodicalId":73556,"journal":{"name":"JMIR nursing","volume":"9 ","pages":"e85599"},"PeriodicalIF":5.0,"publicationDate":"2026-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13447815/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148687020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Theoretical Exploration of Error Thresholds for Clinical AI Decision Support in Nursing: Exploratory Simulation Study Grounded in Human-AI Reliance Data.","authors":"Hiroyuki Tajima","doi":"10.2196/99590","DOIUrl":"10.2196/99590","url":null,"abstract":"<p><strong>Background: </strong>Clinical AI decision support is being introduced into nursing practice; however, existing large language models (LLMs) demonstrate only moderate accuracy on complex clinical tasks, raising questions about the level of accuracy required for safe clinical use across varying levels of clinician experience and task complexity.</p><p><strong>Objective: </strong>The aim of the study is to develop an empirically calibrated simulation model of human-AI reliance and error in nursing decision-making and estimate the AI accuracy required to achieve specified error rate targets.</p><p><strong>Methods: </strong>A linear reliance model with coefficients for AI accuracy (A), clinician experience (E), and task complexity (C) was calibrated using weighted least squares against 9 empirical data points from 3 independent randomized experiments on AI-assisted decision-making (N=3502). Predicted error was computed as reliance×(1-A) across a 27-cell factorial design. Study-level bootstrap (2000 iterations) quantified calibration uncertainty. To contextualize the simulation's operating range, the accuracy of contemporary general-purpose LLMs on complex clinical tasks was drawn from published benchmarks.</p><p><strong>Results: </strong>Calibration placed βA at 0.201 (bootstrap 95% CI 0.023-0.234; P(βA>0)>.99). For the novice×high-complexity combination, the minimum AI accuracy values required to achieve error rates <10% and<20% were 0.89 and 0.78, respectively (bootstrap 95% CIs 0.88-0.90 and 0.75-0.79). At the moderate accuracy levels currently reported for general-purpose LLMs on complex clinical tasks (approximately 0.5-0.7), the model predicts error rates of roughly 26% to 41% in this high-risk condition.</p><p><strong>Conclusions: </strong>In this model, keeping predicted error rates below a stringent target (<10%) for high-complexity nursing decision support by novice clinicians requires AI accuracy of at least approximately 0.89, a level that current general-purpose LLMs may not reliably reach on complex clinical tasks. Because the model is calibrated on nonnursing reliance data, these thresholds are illustrative model outputs, not nursing-derived empirical standards. The Athreshold framework provides a decision-theoretic tool for evaluating the minimum AI accuracy requirement by user-and-task profile. Behavioral validation in nursing contexts remains an essential next step. Because the framework is independent of any specific model, it remains applicable as AI systems improve.</p>","PeriodicalId":73556,"journal":{"name":"JMIR nursing","volume":"9 ","pages":"e99590"},"PeriodicalIF":5.0,"publicationDate":"2026-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13448014/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148687030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring the Potential for Smartphone-Based Reflection to Support Socioemotional Competence Development in Student Nurses' Clinical Placement: Mixed Methods Field Trial.","authors":"Ivo Bril-Broers, Nick Degens, Joke Fleer","doi":"10.2196/91083","DOIUrl":"10.2196/91083","url":null,"abstract":"<p><strong>Background: </strong>Socioemotional competencies (SEC) are essential for nurses to provide quality care and to maintain their own health. Historically underrepresented, nursing programs are changing their curricula to incorporate SEC development more strongly. Although it is recommended to practice SEC during clinical placement, studies on how to support nursing students in developing these competencies are lacking.</p><p><strong>Objective: </strong>Our study explores second-year nursing students' perceived and actual use of a reflection tool during their first 20-week clinical placement. Designed to support SEC development, the study focuses on how students incorporate the application in their learning process for SEC development.</p><p><strong>Methods: </strong>An embedded mixed method study was conducted with 15 students from a nursing program in the Netherlands. Qualitative surveys and semistructured interviews were used to capture students' experiences with the application both during and at the end of the clinical placement. Log data from the application provided insight into how the app was used. The mixed methods data were analyzed using warranted assertion analysis.</p><p><strong>Results: </strong>The app helped students relate learning goals to clinical experiences, identify learning opportunities, and experience a sense of growth. Features that removed practical barriers to reflecting were experienced as most beneficial. Although SEC-focused use was limited (n=7), involved students used the app over a longer period of time and reported greater benefits. Nevertheless, 13 students stopped using the app halfway through their clinical placement, as their attitude shifted from learning to working.</p><p><strong>Conclusions: </strong>This study gives a rich description of how nursing students used a reflection app to structure their learning process during clinical placement. It reveals that smartphone-based reflection supports students in clinical placement learning. Specifically, the app lowers barriers to engaging in structural reflection and decreases the mental burden of self-regulated learning. However, more guidance and a multimodal intervention approach seem necessary for SEC development. Further research into how to account for students' shifting attitudes toward learning is needed.</p>","PeriodicalId":73556,"journal":{"name":"JMIR nursing","volume":"9 ","pages":"e91083"},"PeriodicalIF":5.0,"publicationDate":"2026-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13441119/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148680669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Care Partner Perspectives on Hypertension Management in Alzheimer Disease and Related Dementias in an Online Forum: Qualitative Thematic Analysis.","authors":"Jisook Ko, Kylie Meyer, Jing Wang","doi":"10.2196/85818","DOIUrl":"10.2196/85818","url":null,"abstract":"<p><strong>Background: </strong>Family care partners manage care for individuals with Alzheimer disease and related dementias (ADRD), including hypertension management crucial for preventing cognitive decline. Nurses frequently interact with these caregiver-patient dyads but have limited evidence about caregivers' real-world experiences of managing this comorbidity. Understanding these experiences is essential for developing nurse-led interventions that support both patients and caregivers.</p><p><strong>Objective: </strong>This study aimed to explore ADRD care partners' perceptions, experiences, and challenges related to hypertension management. A qualitative thematic analysis of care partner posts from an online forum focused on ADRD was conducted.</p><p><strong>Methods: </strong>We analyzed 300 posts from ALZConnected, collected using the keywords \"hypertension\" and \"blood pressure.\" Two independent researchers used reflexive thematic analysis, following the Braun and Clarke framework until data saturation was achieved.</p><p><strong>Results: </strong>Among posts from predominantly family care partners (10,427/11,092, 94%, mostly adult children), 7 themes emerged: Pharmacotherapy (155/300, 51.7%), addressing medication efficacy, polypharmacy, and side effects; Patient Health Care Implementation Strategies (n=125, 41.7%), encompassing care coordination and provider interactions; Comorbid Care Management (n=136, 45.3%), highlighting caregiving demands, behavioral symptoms of ADRD, and care coordination challenges as barriers to hypertension control; Hypertension Management and Outcomes (n=71, 23.7%), including hypertensive crises; Managing Behavioral Symptoms (n=38, 12.7%), particularly care resistance; Peer Medical Advice Exchange (n=9, 3%); and Caregiver Burden and Self-Care for Hypertension (n=25, 8.3%), revealing care partners' own hypertension attributed to caregiving stress.</p><p><strong>Conclusions: </strong>Managing comorbid hypertension in ADRD presents challenges spanning medication management, behavioral symptoms, and health care coordination. Caregivers reported developing hypertension themselves, highlighting bidirectional health impacts. Health care providers should implement dyadic interventions addressing both patient hypertension management and caregiver health within the care partnership.</p>","PeriodicalId":73556,"journal":{"name":"JMIR nursing","volume":"9 ","pages":"e85818"},"PeriodicalIF":5.0,"publicationDate":"2026-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13412009/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148610937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Nurse-Led Digital Intervention for Sodium Restriction in Chronic Kidney Disease: Mixed Methods Implementation Study.","authors":"Yu Shi, Hongmei Peng, Youying Zhang, Jingyu Zhang, Yang Li, Shi Pu, Xiangchun Tang, Jinghong Zhao","doi":"10.2196/94330","DOIUrl":"10.2196/94330","url":null,"abstract":"<p><strong>Background: </strong>Digital interventions can support sodium restriction in chronic kidney disease; yet, implementation and engagement barriers remain poorly understood.</p><p><strong>Objective: </strong>This mixed methods study evaluated a nurse-led digital program for sodium restriction, focusing on 3 key aspects: implementation, engagement, and patient experience.</p><p><strong>Methods: </strong>This study was initially designed as a randomized controlled trial but was revised to a mixed methods implementation study due to high rates of missing primary outcome data. Quantitative measures included 24-hour urinary sodium excretion (the primary outcome of the original randomized controlled trial), knowledge tests, blood pressure measurements, and quality-of-life assessments. Concurrently, we conducted in-depth qualitative interviews with a purposive sample of participants. Quantitative and qualitative data were collected in parallel, analyzed separately, and then integrated to provide a comprehensive understanding of participants' experiences with the intervention.</p><p><strong>Results: </strong>Among 99 enrolled patients (46 in the enhanced digital intervention group and 53 in the minimal digital control group), the program led to a significant improvement in sodium-related knowledge as a secondary exploratory outcome (P=.005). However, the 24-hour urine collection completion rate was only 24.2% (n=24), precluding reliable conclusions regarding the primary outcome. Qualitative findings revealed a \"measurement paradox,\" in which the gold-standard assessment itself posed a major barrier to adherence. Integrated data illustrated a patient journey marked by early enthusiasm, followed by declining engagement due to digital fatigue, family resistance, and poor fit with daily life. This misalignment created a disconnect between acquired knowledge and measurable behavior change.</p><p><strong>Conclusions: </strong>A nurse-led digital intervention was associated with modest improvements in sodium knowledge in chronic kidney disease. However, success requires reducing the monitoring burden and improving real-world fit. The \"measurement paradox\" highlights the need for patient-centered outcome measures. We propose a \"stage-matched intervention\" framework to guide adaptive digital tools. Future research should prioritize multicenter pragmatic trials to bridge the knowledge-action gap.</p>","PeriodicalId":73556,"journal":{"name":"JMIR nursing","volume":"9 ","pages":"e94330"},"PeriodicalIF":5.0,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13384475/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148537792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Validation and Feasibility of a Consumer-Grade Wearable Sleep Monitoring Device and Exploratory Evaluation of Sleep Characteristics and Associated Factors Among Nurses: A Feasibility Observational Cohort Study.","authors":"Siew Hoon Lim, Fazila Aloweni, Phyllis Ong, Shin Yuh Ang","doi":"10.2196/96912","DOIUrl":"10.2196/96912","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Background: Shift work disorder and insufficient sleep are prevalent among nurses, leading to fatigue, reduced well-being, and potential safety concerns. Increasing use of wearable sleep-tracking devices presents an opportunity to evaluate nurses' sleep quality objectively.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;Objective: The primary objective was to evaluate the feasibility of wearable-based sleep monitoring and to obtain preliminary evidence of agreement with validated actigraphy among nurses. The secondary objective was to describe nurses' sleep characteristics and examine exploratory associations between sociodemographic characteristics, shift patterns, sleep hygiene, and sleep parameters.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Methods: A two-phase feasibility observational cohort study was conducted in a tertiary hospital in Singapore. In Phase 1, five nurses concurrently wore a consumer-grade wrist-worn wearable Apple Watch Series 10 and a validated actigraph (GENEActiv®) for two weeks. Preliminary agreement between Apple Watch and GENEActiv® was examined using intraclass correlation coefficients (ICC). Feasibility was determined via wear compliance and completeness of data. In Phase 2, 50 nurses working rotating or single shifts completed demographic and work-related questionnaires and Sleep Hygiene Index. Multiple linear regression analyses were performed to examine exploratory associations between selected covariates and sleep parameters, with adjustment for age, sex, Body Mass Index (BMI), parental status, workplace, total length of service, and sleep hygiene.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Results: Apple Watch showed preliminary evidence of agreement with GENEActiv® for total sleep time, in-bed wake time, and sleep efficiency (ICC= 0.95, 0.72, and 0.69, respectively), with high wear compliance and minimal missing data, supporting feasibility for sleep monitoring. Mean total sleep time was 381 ± 55 min, and mean sleep efficiency was 94.8%. Shift nurses reported poorer sleep hygiene than non-shift nurses; however, shift work status was not independently associated with sleep outcomes after adjustment. Higher BMI was associated with shorter total sleep time (B = -3.76 minutes per kg/m², p = 0.01), reduced rapid eye movement sleep (B = -1.18 minutes, p = 0.03), shorter core sleep (B = -2.72 minutes, p = 0.02) and reduced time in bed (B = -4.05 minutes, p &lt; 0.01). Age was negatively associated with deep sleep duration, with older age associated with less deep sleep (B = -1.00 minutes per year, p &lt; 0.01).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;Conclusion: Apple Watch-based monitoring was feasible and showed preliminary agreement with actigraphy. Nurses obtained less sleep than recommended, and BMI and age were associated with sleep outcomes in exploratory analyses. These findings support larger studies and workplace strategies to improve sleep opportunity and healthy sleep behaviours.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Clinicaltrial: &lt;/strong&gt;","PeriodicalId":73556,"journal":{"name":"JMIR nursing","volume":" ","pages":""},"PeriodicalIF":5.0,"publicationDate":"2026-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13488918/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148521609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effectiveness of Artificial Intelligence-Based Nursing Interventions for Chronic Illness Care: Umbrella Review.","authors":"Jee Young Joo, Megan Liu, Youngwoo Cho, Hyungbin Cho","doi":"10.2196/97905","DOIUrl":"10.2196/97905","url":null,"abstract":"<p><strong>Background: </strong>Artificial intelligence (AI)-based nursing interventions are increasingly being used to manage chronic illnesses; however, their definitive impact on clinical outcomes remains inconclusive, necessitating a comprehensive evidence synthesis.</p><p><strong>Objective: </strong>This umbrella review aimed to synthesize the evidence regarding the effectiveness of AI-based nursing interventions for chronic illness care and their subsequent impact on health care outcomes in clinical settings.</p><p><strong>Methods: </strong>We conducted an umbrella review and prospectively registered the protocol. A systematic search of 5 electronic databases (PubMed, CINAHL, Cochrane Library, Scopus, and Web of Science) was performed to identify systematic reviews and meta-analyses published in English between 2021 and 2025. The methodological quality of the included studies was evaluated using the Joanna Briggs Institute (JBI) Critical Appraisal Checklist.</p><p><strong>Results: </strong>Eight high-quality systematic reviews were included, with machine learning identified as the predominant technology. Three primary outcome domains emerged: predictive, psychosocial, and hospital utilization. Due to measurement heterogeneity, the results were synthesized narratively. Our findings demonstrated that AI-based nursing interventions are effective in predicting adverse clinical events, unplanned hospital utilization, and health care costs. However, evidence regarding psychosocial outcomes remains insufficient.</p><p><strong>Conclusions: </strong>This review provides systematic evidence supporting the utility of AI in chronic illness management, particularly for improving predictive and utilization outcomes. These findings offer actionable insights for nursing leaders to integrate AI into clinical practice and education. Future research should prioritize rigorous empirical designs to further strengthen the evidence base for AI-driven nursing care.</p>","PeriodicalId":73556,"journal":{"name":"JMIR nursing","volume":"9 ","pages":"e97905"},"PeriodicalIF":5.0,"publicationDate":"2026-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13373462/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148458069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}