Applied Clinical Informatics最新文献

{"title":"Autosaved Incident Report Drafts: Log-Based Evidence of Completion, Return-to-Complete Behavior, and Reminder-Linked Submission in a Multisite Patient Safety Reporting System.","authors":"Szu-Chang Wang","doi":"10.1055/a-2971-4388","DOIUrl":"10.1055/a-2971-4388","url":null,"abstract":"<p><strong>Abstract: </strong>BACKGROUND: Patient safety reporting studies usually examine intention, submitted reports, or reporting rates, leaving unclear what happens after a report is started but before it is submitted, deleted, or left unfinished. We evaluated whether autosave and fixed-time reminders make this hidden stage observable.</p><p><strong>Abstract: </strong>OBJECTIVES: This study aimed to quantify draft outcomes, interaction burden, completion timing, return-to-draft behavior, and reminder-linked submission among autosaved incident report drafts.</p><p><strong>Abstract: </strong>METHODS: This was a retrospective log-based study of draft header records and action logs from March 2024 through March 2026. Reminder exposure was defined as a draft remaining incomplete at the daily 05:31 batch; return as a load action within 24 hours after first eligibility. Analyses used descriptive statistics and site-adjusted logistic regression with reporter-clustered standard errors.</p><p><strong>Abstract: </strong>RESULTS: Among 6,835 drafts, 5,397 (79.0%) were submitted, 1,268 (18.6%) were deleted, and 170 (2.5%) were pending. Completed reports were usually rapid (median: 15.0 min; 81.7% within 60 min), but 1,961 drafts (28.7%) had at least one return/load action. Among submitted drafts with action logs, the median interaction burden was 2 actions (interquartile range: 1-3). Overall, 1,617 drafts (23.7%) were reminder-exposed; 337 (20.8%) returned within 24 hours. Return within 24 hours was strongly associated with submission (74.2 vs. 19.8%; adjusted odds ratio: 11.16, 95% confidence interval: 7.29-17.09).</p><p><strong>Abstract: </strong>CONCLUSION: Draft-level logs expose the previously unmeasured middle of incident reporting. Autosave captured interrupted work, and reminder-linked return identified a high-yield recovery point for at-risk drafts. These findings show how interruption-resilient design can support actual report completion, not only reporting intention or submitted-report counts.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":"17 4","pages":"912-921"},"PeriodicalIF":2.7,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13657795/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149167208","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Disparities in Activation and Use of Patient Portals among Spanish-Speaking Patients.","authors":"Robert W Turer, Robin T Higashi, Emily Repasky, Samuel A McDonald, Ellen O'Connell, Christoph Ulrich Lehmann, Eric D Peterson, Ferdinand Velasco, Clark Walker, Christopher Clark, Brett Moran, Bryan D Steitz, Bhaskar Thakur, Ann Marie Navar","doi":"10.1055/a-2898-9022","DOIUrl":"10.1055/a-2898-9022","url":null,"abstract":"<p><strong>Objectives: </strong>Patient portal use has steadily increased across most populations. Prior, now dated, studies indicated lower adoption rates among Spanish- versus English- speaking patients. This study compared patient portal activation and use patterns between Spanish- and English-speaking patients.</p><p><strong>Methods: </strong>This retrospective cohort study was conducted at three North Texas health systems using the MyChart patient portal (Epic Systems Co.) and included patients ≥ 18 years with ≥1 completed clinician encounter between April 5, 2021 and April 4, 2022. The primary activation outcome was the baseline MyChart account activation rate. The secondary activation outcome was the MyChart account activation rate within the following year among patients without an account at baseline. The primary use outcome was the rate of patients logging in. Secondary use outcomes included rates of results review, notes review, and message initiation in the following year. We also evaluated the rates of proxy account use and mobile app use. We fit multivariable logistic regression models adjusting for health system, age, sex, comorbidity count, and the number of prior-year encounters.</p><p><strong>Results: </strong>Spanish speakers represented 128,338 of 1,550,220 (8.3%) patients. Spanish speakers had lower odds of having an activated account at baseline (adjusted odds ratio [aOR], 0.39 [0.39-0.40]) or activating one in the following year (aOR, 0.68 [0.65-0.71]). Spanish speakers also had lower odds of logging in (aOR, 0.62 [0.61-0.63]), reviewing results (aOR, 0.79 [0.76-0.81]), reviewing notes (aOR, 0.87 [0.84-0.89]), or sending messages (aOR, 0.41 [0.40-0.42]). More Spanish than English speakers used the mobile app (59 vs. 50%). There were intersite differences in the rate of proxy account use.</p><p><strong>Conclusion: </strong>Given lower levels of portal activation and use among Spanish-speaking patients, strategies are needed to identify and address barriers to activation and use. Qualitative studies could delineate these barriers and potential mitigating strategies.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":" ","pages":"633-641"},"PeriodicalIF":2.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13395533/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148370401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of ChatGPT, Gemini, and OpenEvidence in Obstetric and Gynecologic Clinical Decision Scenarios.","authors":"Arif Onur Atay, Feride Atay, Samican Ozmen, Mucahit Furkan Balci","doi":"10.1055/a-2899-0123","DOIUrl":"10.1055/a-2899-0123","url":null,"abstract":"<p><strong>Background: </strong>Clinicians frequently face questions that require rapid, evidence-based answers. Artificial intelligence (AI) tools are increasingly used for this purpose, yet their reliability for clinical decision-making remains uncertain.</p><p><strong>Objectives: </strong>This study compared two generative large language model systems (ChatGPT and Gemini) and a retrieval-supported clinical platform (OpenEvidence) to determine which provides the most reliable, clear, and clinically applicable information in obstetrics, gynecology, and urogynecology.</p><p><strong>Methods: </strong>A cross-sectional comparative design was used to evaluate ChatGPT (GPT-5), Gemini (Gemini 2.5), and the retrieval-supported platform OpenEvidence. Twenty-four clinical questions across three subspecialties were independently assessed by two blinded specialists using the Expert-Adapted DISCERN (EA-DISCERN) tool, which rates 12 quality domains on a 5-point scale. Mean ± standard deviation scores were compared across systems and clinical domains using repeated-measures analysis.</p><p><strong>Results: </strong>OpenEvidence achieved the highest mean total score (54.0 ± 2.3), outperforming Gemini (50.3 ± 2.4) and ChatGPT (48.7 ± 2.4; <i>p</i> < 0.001). OpenEvidence scored significantly higher in evidence-based domains; clinical accuracy, guideline consistency, completeness, transparency, and reliability across all fields. As of this writing, Gemini ranked between the two, showing a modest advantage over ChatGPT in rationale explanation and evidence transparency, whereas both generative models scored higher in language fluency and readability. Overall, total EA-DISCERN scores ranked OpenEvidence highest, followed by Gemini, then ChatGPT. Interrater reliability for the total score was intraclass correlation coefficient [2,1] (absolute agreement = 0.391).</p><p><strong>Conclusion: </strong>OpenEvidence provided more guideline-aligned and transparent responses, whereas ChatGPT and Gemini were generally more fluent and readable. For obstetrics and gynecology clinicians, retrieval-supported platforms may be more suitable for point-of-care verification, while generative models should be used more cautiously and with clinician oversight.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":" ","pages":"518-525"},"PeriodicalIF":2.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13318453/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148284612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Real-World Utilization of a Hospital-Integrated Internet Hospital in Henan Province, China: A 1-Year Observational Study.","authors":"Dongxu Sun, Wei Lu, Guangrui Sheng, Kai Huang, Guoshu Huang, Jian Kang, Feifei Wang, Ming Liu, Yunkai Zhai, Jinming Shi","doi":"10.1055/a-2899-0866","DOIUrl":"10.1055/a-2899-0866","url":null,"abstract":"<p><strong>Background: </strong>China's hospital-integrated Internet Hospital model embeds virtual outpatient care within hospital information systems, pharmacy workflows, and regulatory oversight structures. However, encounter-level evidence on real-world utilization, operational efficiency, online prescribing, and repeat use remains limited.</p><p><strong>Objectives: </strong>The objective of this study is to describe the first-year utilization, service efficiency, prescribing safety, and continuity-of-care potential of a hospital-integrated Internet Hospital in Henan province, China.</p><p><strong>Methods: </strong>We conducted a retrospective observational study of all online consultation orders generated from November 1, 2023, to October 31, 2024, at a large tertiary hospital. Deidentified data from consultation logs, prescribing modules, and pharmacy systems were descriptively analyzed. Key measures included order outcomes, consultation type and modality, patient-level repeat use, response time, online prescribing, prescription review outcomes, and ratings.</p><p><strong>Results: </strong>A total of 90,006 online consultation orders were generated; 54,389 (60.4%) were completed, 32,720 (36.4%) were cancelled, and 2,897 (3.2%) expired because payment was not completed. Most cancellations occurred before physician acceptance. Text-based consultations accounted for 83,833 orders (93.1%). Virtual Consultations accounted for 78,313 orders (87.0%) and did not permit prescribing; Virtual Follow-up Consultations accounted for 11,693 orders (13.0%) and had a higher completion rate (74.3 vs. 58.4%). Among 49,724 unique patients, 16,554 (33.3%) generated two or more orders. Median response time was 93.4 minutes (interquartile range: 12.4-345.5). Prescriptions were generated in 491 orders (0.55%); 359 patients paid for medication orders, and 118 prescriptions required physician modification after initial automated review. No legally restricted controlled drugs were prescribed online. Ratings were submitted for 5,820 orders (6.5%).</p><p><strong>Conclusion: </strong>The platform primarily served as a hospital-governed digital entry point for consultation and triage, with a controlled follow-up pathway for selected prescription renewal. It demonstrated feasibility but also highlighted preacceptance cancellations, long-tailed response times, limited older-adult use, and expert-heavy workload as priorities for optimization.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":"17 3","pages":"526-539"},"PeriodicalIF":2.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13318452/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148362979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Generative AI in Admission Notes and Diagnostic Completeness: A Pilot Study.","authors":"Alfredo Camargo Rodrigues, Jason M Misurac, Lindsey A Knake, Kevin Barker, James M Blum","doi":"10.1055/a-2876-0998","DOIUrl":"10.1055/a-2876-0998","url":null,"abstract":"<p><strong>Background: </strong>Admission history and physical (H&P) notes influence inpatient documentation, risk adjustment, and reimbursement. In high-acuity settings, time constraints and fragmented chart data contribute to under-documentation of comorbidities. Generative AI systems that draft admission notes from existing electronic health record data may improve documentation completeness, but real-world inpatient performance remains insufficiently characterized.</p><p><strong>Objective: </strong>This study aimed to evaluate whether AI-generated admission notes identify documentation-relevant diagnoses supported by the medical record but not explicitly captured in provider-authored admission notes.</p><p><strong>Methods: </strong>In this single-center retrospective pilot study, we reviewed 22 matched pairs of AI-generated and provider-authored admission H&P notes at a large academic medical center. We assessed principal diagnosis concordance and identified net-new secondary diagnoses. Secondary diagnoses identified by the AI but absent from provider-authored notes were adjudicated by a clinical documentation improvement (CDI) team using standard institutional criteria.</p><p><strong>Results: </strong>AI-generated notes aligned with the provider-authored principal diagnosis in 91% of cases (20/22). The CDI team adjudicated 104 AI-identified secondary diagnoses, of which 97% (101/104) were supported for documentation. Ninety-four diagnoses were net-new, quality-relevant conditions not documented in provider-authored notes (median: 4.5 per admission). Net-new diagnoses were observed across all provider types, with numerically higher counts among advanced practice providers and residents; however, the sample was too small to support inferential comparisons. Despite its modest sample size, this pilot demonstrated high principal diagnosis concordance, though the AI misclassified the principal diagnosis in two cases. AI-generated drafts identified additional CDI-supported diagnoses not captured by providers, though narrative quality and factual accuracy were not evaluated.</p><p><strong>Conclusion: </strong>These findings highlight the potential of generative AI to surface documentation-relevant information at admission and underscore the importance of human oversight in AI-assisted documentation workflows. Larger multicenter studies are needed to assess generalizability and safety.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":" ","pages":"392-399"},"PeriodicalIF":2.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13287953/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147976605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Interoperability Moonshot Proposal.","authors":"Natalee Agassi, Richard Schreiber, Eric Pan, James McClay, J Marc Overhage, Rebecca Baker, Rebecca Kush, Jay Lyle, Catherine K Craven","doi":"10.1055/a-2885-7865","DOIUrl":"10.1055/a-2885-7865","url":null,"abstract":"<p><strong>Background: </strong>Clinical data exchange remains fragmented and insufficient to support coordinated, safe care. Decades of technological progress, standards development, and interoperability-focused legislative and regulatory improvements have been incremental, underscoring the need for unifying initiatives to coordinate and improve operations and outcomes.</p><p><strong>Objectives: </strong>We sought to identify persistent barriers limiting clinical data interoperability. We propose a coordinated, time-bound U.S. \"moonshot\" initiative to create a unified canonical clinical terminology (\"SuperSNOMED\") and catalyze rapid refinement and streamlined adoption of Fast Healthcare Interoperability Resources (FHIR) and Implementation Guides (IGs) to accelerate safe, high-fidelity data exchange.</p><p><strong>Methods: </strong>We synthesized insights from an expert roundtable; conducted additional expert discussions; appraised peer-reviewed published and online evidence on standards, interoperability policies, and developing regulations; and then identified barriers to interoperability implementation. We then developed recommendations for policy, legislative, and regulatory changes.</p><p><strong>Results: </strong>We identified five barrier domains: fragmented terminology standards and value sets; multiple overlapping data exchange standards with uneven FHIR adoption; incomplete or misaligned certification and policy incentives; variable interpretation and implementation of IGs; and insufficient funding and support for standards development. We propose a national program including three coordinated pillars: SuperSNOMED, a well-governed, rapidly maintained, canonical terminology integrating major domains and mappings; FHIR acceleration converging on a minimum set of IGs and certified legacy-data transforms during a transition window; and policy and governance for certification criteria, incentive alignment, and funding a paid expert task force to execute an ambitious 3-year plan. Certification and workforce incentives with transitional data-quality safeguards such as reconciliation-on-first-use for transformed historical data would catalyze high-impact interoperability beyond existing EHR regulatory programs, clinical information systems, and knowledge bases critical to health care.</p><p><strong>Conclusion: </strong>Interoperability remains fragmented despite progress. This state-of-the-art paper is a call to action for a focused, funded, well-governed national moonshot effort to unify terminology and streamline exchange standards.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":"17 3","pages":"493-501"},"PeriodicalIF":2.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13301294/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148320144","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Novel Digital Phenotype for Burn Sepsis: Leveraging Electronic Health Record Data and Natural Language Processing to Improve Case Definition.","authors":"Nicholas D Soulakis, Lily Li, Ashley A Peters, John C Kubasiak","doi":"10.1055/a-2885-7810","DOIUrl":"10.1055/a-2885-7810","url":null,"abstract":"<p><strong>Background: </strong>Sepsis remains a leading cause of death for burn patients, yet the condition is hard to spot early. Hospitals generally rely on the International Classification of Diseases (ICD) codes for surveillance, but these codes are assigned late and often miss active cases.</p><p><strong>Objectives: </strong>We developed and validated a scalable, electronic health record (EHR)-based digital phenotype that improves identification of burn-related sepsis compared with ICD codes alone.</p><p><strong>Methods: </strong>We performed a retrospective cohort study of adult burn inpatients (<i>n</i> = 1,371) admitted to Loyola University Medical Center (2007-2021). Structured EHR data and clinical notes were extracted from a research database. Sequential Organ Failure Assessment (SOFA) scores were calculated every 4 hours; natural language processing parsed vasopressor doses and culture alerts. Four algorithms were evaluated: (1) ICD codes; (2) SOFA increase ≥2 + broad-spectrum antibiotics; (3) SOFA increase ≥2 + positive blood culture; (4) SOFA increase ≥2 + any positive culture.</p><p><strong>Results: </strong>ICD coding alone classified 79 encounters (5.8%) as sepsis. EHR-enhanced algorithms identified more cases: 123 via SOFA + antibiotics (9.0%), 21 via SOFA + blood culture (1.5%), and 53 via SOFA + any culture (3.9%). The rule count score (0-4) achieved the highest performance (area under the curve [AUC] 0.92), outperforming ICD codes alone (AUC 0.77).</p><p><strong>Conclusion: </strong>Our multimodal digital phenotype doubled sepsis detection compared to ICD-based surveillance. The tiered risk assessment approach showed excellent discrimination with increasing positive predictive value as more criteria were met. This phenotype can be implemented using routine EHR data, supporting early warning tools for this high-risk population.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":" ","pages":"466-475"},"PeriodicalIF":2.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13290366/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148165227","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing the Effectiveness and Scalability of Fast Healthcare Interoperability Resource-Based Granular Data Segmentation Technology.","authors":"Preston Lee, Abhishek Singh Dhadwal, Martha Kaiser, Soroush Dianaty, Eric Lott, Gagandeep Singh, Darwyn Chern, Jason Walonoski, Adela Grando","doi":"10.1055/a-2863-4129","DOIUrl":"10.1055/a-2863-4129","url":null,"abstract":"<p><strong>Background: </strong>Protecting sensitive health information, particularly substance use data, is essential to preserving patient trust, improving care engagement, and ensuring compliance with federal confidentiality laws such as 42 CFR Part 2. Manual segmentation of sensitive data remains burdensome and error-prone, creating a need for scalable, automated, and patient-centered data segmentation technologies.</p><p><strong>Objectives: </strong>The objective of this study is to evaluate the technical effectiveness, scalability, and computational performance of SHARES, an open-source data segmentation platform based on HL7 Fast Healthcare Interoperability Resources (FHIR), designed to support patient-directed, granular control over sharing sensitive substance use-related health information.</p><p><strong>Methods: </strong>We generated 11,519 synthetic FHIR patient records using Synthea and conducted physician-led classifications of 1,848 unique clinical terms contained in those patient records. These classifications were used to assign code-category-confidence rules applied by the SHARES segmentation engine. We deployed the SHARES platform in simulation environments to label and segment substance use-related data using varying confidentiality thresholds. We benchmarked throughput, scalability, and computational performance across large FHIR datasets, and measured segmentation accuracy via physician manual review.</p><p><strong>Results: </strong>Physicians categorized 232 data items as substance use or \"maybe\" substance use data elements. The SHARES segmentation engine processed 197.6 million FHIR resources across 11 confidentiality thresholds. Overall, 17 million data items (8.64%) were flagged as sensitive. SHARES achieved a throughput of 10.36 patient bundles per second, or approximately 18,909 FHIR resources per second, on a commodity laptop. A full segmentation run on 11,519 patients had a cost of under one cent.</p><p><strong>Conclusion: </strong>This study demonstrates the feasibility and scalability of automated, rule-based data segmentation within a FHIR-native architecture, using a physician-derived sensitivity construct for substance use as an applied test case. SHARES offers high-throughput, low-cost classification performance, and supports auditability and deterministic decision-making, which are key strengths for compliance with 42 CFR Part 2. Future enhancements will incorporate clinical quality language (CQL)-based logic to better reflect real-world clinical reasoning and contextual data interpretation.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":"17 3","pages":"423-433"},"PeriodicalIF":2.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13286105/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148240477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Digital Twin Navigation System for Hospital Supply Rooms: 3D Spatial Guidance Tool.","authors":"Rugved Parmar, Nischal Sharma, Adam Budzikowski","doi":"10.1055/a-2876-1132","DOIUrl":"10.1055/a-2876-1132","url":null,"abstract":"<p><strong>Background: </strong>Hospital supply rooms are dense, vertically complex environments where clinicians may lose time locating items. Existing text-based inventory logs require mental translation from alphanumeric codes to physical space, adding cognitive load during time-sensitive tasks. Despite growing use of digital twins in health care, this technology has been underreported in supply room navigation.</p><p><strong>Objectives: </strong>The objective of this study is to describe the design and feasibility of a browser-based three-dimensional (3D) digital twin system providing spatial guidance for locating supplies in a hospital clean supply room.</p><p><strong>Methods: </strong>A digital twin, defined here as a virtual interactive replica of a physical environment, was developed using React and Three.js to model a telemetry unit clean supply room. The system renders more than 100 storage bins using instanced rendering. Users search via a text interface; the system highlights the target bin and animates the camera to its position.</p><p><strong>Results: </strong>The prototype achieved sub-10-ms search response times and loaded in under 1 second on standard hospital hardware. Two coresidents completed informal prototype walkthroughs over a 2-week period; these observations were anecdotal and were not part of a formal usability study.</p><p><strong>Conclusion: </strong>A 3D digital twin approach to supply room navigation is technically feasible using open-source web technologies at zero licensing cost and addresses spatial cognition challenges in dense health care storage environments. Formal usability evaluation is needed to quantify clinical effects.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":"17 3","pages":"380-383"},"PeriodicalIF":2.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13287929/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148057585","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From Burden to Balance: Trends in Documentation Workload with Ambient Artificial Intelligence Scribe Adoption.","authors":"Thomas Wojda, Jennifer Berliner, Gary S Fischer, Michael Curren, Jonathan Arnold, Lauren Giugale","doi":"10.1055/a-2892-7988","DOIUrl":"10.1055/a-2892-7988","url":null,"abstract":"<p><strong>Background: </strong>Physician burnout, often driven by documentation burden in electronic health records, remains a major challenge in clinical care. Ambient artificial intelligence (AI) scribes generate draft notes from clinical encounters, offering a scalable approach to reduce administrative workload, yet population-level evaluations remain limited.</p><p><strong>Objectives: </strong>The objective of this study is to assess changes over time in clinician perceptions of workload, well-being, and care delivery following implementation of ambient AI scribes.</p><p><strong>Methods: </strong>We conducted a prospective repeated cross-sectional survey study of physicians and advanced practice providers at four time points: baseline and approximately 1, 3, and 6 months' postimplementation. Outcomes included cognitive workload (NASA Task Load Index), professional fulfillment and burnout (Professional Fulfillment Index and Mini-Z), and perceptions of documentation burden, communication, and clinical capacity. Responses were grouped into clinically meaningful categories, and chi-square tests compared distributions across time. Secondary analyses compared baseline characteristics of respondents with linkable data across time points to the full cohort and evaluated subgroup differences for specific items.</p><p><strong>Results: </strong>A total of 1,600 clinicians responded at baseline, with 172, 117, and 101 respondents at 1-, 3-, and 6-month follow-up, respectively. Over 95% of follow-up respondents reported generating ≥5 ambient AI-supported notes, with use increasing significantly over time (<i>p</i> < 0.05). Clinicians reported statistically significant reductions in mental demand, time pressure, and documentation effort at postimplementation intervals (<i>p</i> < 0.05). Time spent on documentation outside clinic declined, with more clinicians reporting <2 hours/day (<i>p</i> < 0.05). Burnout increased across follow-up time points (<i>p</i> < 0.05). Confidence in patient comprehension and willingness to increase patient volume improved. Subgroup analyses mirrored overall trends.</p><p><strong>Conclusion: </strong>Ambient AI scribes were associated with sustained reductions in cognitive workload and perceived documentation burden. Despite these improvements, burnout increased over time, likely reflecting multifactorial influences and limitations of unpaired survey data. These findings support continued implementation and further longitudinal evaluation of clinician well-being.</p>","PeriodicalId":48956,"journal":{"name":"Applied Clinical Informatics","volume":" ","pages":"484-492"},"PeriodicalIF":2.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13290361/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148240485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}