Applied Clinical Informatics最新文献

Direct Secure Messaging (DSM) is a communication standard for exchanging information between health care entities and practitioners. It relies on access to an address directory. When directory entry is incomplete, health information exchange breaks down. There is an urgent need for standardized DSM address directory management and synchronization workflows that support universal access in a timely manner.Our objective was to develop best practices for maintenance of DSM address directories and create recommendations to encourage adoption of DSM technology in the State of Texas.Texas Health Services Authority (THSA) formed a workgroup focused on increasing DSM adoption. Between August 2021 and March 2022, workgroup members used a modified Delphi process to create a directory management best practice policy and published it in May 2022. To measure the effect of the policy, THSA monitored volume of messages sent in a group of 38 hospitals before and after the workgroup was established.Organizations should standardize DSM address data and routinely sync with external databases to ensure seamless, vendor-independent message flow. Additionally, health systems are expected to update directory entries immediately upon any change in practitioner's status. Between September 2021 and December 2022, there was a decrease in Direct messages not sent due to no known address, from 50 to 42%, respectively. Additionally, between July 2021 and March 2024, organizations participating in the policy development reported a steady monthly increase of new Direct addresses issued.Health care organizations should adopt a consistent workflow for maintaining their DSM address directories and regularly synchronize with external databases to facilitate unobstructed flow of messages and data. The Maintenance of Provider Database Dictionary Policy developed by the THSA can serve as a model for nationwide implementation and optimization of DSM as an important interoperability standard.

Telemedicine use has surged since the COVID-19 pandemic, offering a convenient way for patients to access health care. Whereas digital literacy (general comfort with and ability to use digital tools) is necessary to utilize telemedicine, digital health literacy is a subset of this, focusing on the ability to use digital tools to seek out, understand, and utilize health information. Barriers such as the lack of high-speed internet and limited digital health literacy can hinder telemedicine's effectiveness, particularly for historically marginalized populations with lower technological access.This study aims to characterize the relationship between baseline digital health literacy, appointment no-shows, and telemedicine usage in a Bronx population.In a Bronx-based cohort, we assessed digital health literacy using eHealth Literacy Scale (eHEALS) and eHealth Literacy Objective Scale-Scenario Based (eHeLiOS-SB), and health literacy with the Newest Vital Sign (NVS) instrument. Baseline sociodemographic characteristics (e.g., age, insurance type) were collected, and appointment no-show rates and telemedicine usage were calculated. Linear regression models were used to assess associations.Higher digital health literacy, private insurance (compared to Medicaid), and older age were associated with fewer no-shows. Higher video visit usage was also associated with fewer no-shows. Individuals at high risk of housing insecurity were less likely to use video visits, and higher phone visit usage was associated with patients experiencing financial resource strain. Digital health literacy was positively associated with White race and negatively associated with Medicare usage (compared to Medicaid).Higher digital health literacy correlates with increased appointment attendance, indicating the need to address digital barriers in health care. Increasing telemedicine use may help reduce no-shows, and patient-specific strategies are needed to enhance digital health literacy and telemedicine effectiveness.

Completion of Family and Medical Leave Act (FMLA) paperwork is a necessary but time-intensive task that contributes to clinician administrative burden.This study aimed to implement and evaluate an electronic health record (EHR)-integrated FMLA tool designed to reduce documentation time and improve workflow efficiency.An EHR-embedded FMLA form was deployed at a large academic medical center, piloted in July 2024 in primary care, and expanded to all ambulatory practices in September 2024. The tool enabled clinicians to complete and transmit FMLA documentation electronically, with auto-population of clinician details and the ability to recall prior submissions. Pre- and post-intervention surveys assessed clinician-reported efficiency and time burden, and form utilization was tracked using EHR query tools.A total of 67 clinicians completed a pre-survey (response rate: 19.4%) and 49 completed a post-survey (response rate: 25.4%). About 94% of clinicians using the EHR form (n = 31/33) reported time savings. On a 5-point Likert scale, efficiency improved for initial FMLA completion (2.46-3.06, p = 0.01) and renewal of prior FMLA (2.66-3.31, p = 0.01). The percentage of clinicians completing FMLA in 15 minutes or less increased from 51 to 78% (p = 0.002). The form was used 435 times over 9 months, primarily in primary care, with sustained monthly usage.An EHR-integrated FMLA tool improved clinician-reported efficiency and reduced time spent on documentation. This model may be applicable to other manual administrative workflows and offers a potential strategy to mitigate provider burnout.

Patient decompensation necessitating rapid response team (RRT) care in the hospital setting involves complex medical decision making, strong leadership skills, and precise communication where every second matters. However, RRT outcomes can vary based on leader training, knowledge, and experience. We designed five digital, condition-specific, guided algorithms to improve RRT care and compared user survey data among three physician cohorts across the clinical training spectrum to assess the practicality of real-world usage in a small feasibility study.Guided algorithms to common RRT scenarios, including tachycardia, bradycardia, hypotension, hypoxia, and altered mental status, were used by 157 physicians at our institution across three Internal Medicine user cohorts (1: end-of-year PGY-2-5 residents, 2: new PGY-2 residents, and 3: attending hospitalists) from April to December 2024. Survey data from 28 respondents were compared across cohorts using Kruskal-Wallis and Dunn statistical analyses.Survey responses demonstrated consistently high scores across cohorts regarding improvement in patient care, improved RRT leader experience, improved confidence, reduced stress/cognitive load, potential for standardization of care, and likelihood of recommendation to a colleague. Interestingly, new PGY-2 residents rated ease of navigation at 7/10 compared to 10/10 by attending hospitalists (p = 0.016).Digital, guided RRT algorithms are a practical and effective tool for enhancing physician care delivery during inpatient rapid response events across all levels of training. High survey scores across cohorts warrant consideration for broader implementation. Variation in ease of navigation scores highlights the importance of tailoring information flow and usability features to less experienced users. Overall, these algorithms show promise as valuable adjuncts during acute care delivery in high-stakes clinical settings.

Claude Opus 4 is a large language model (LLM) that features improved reasoning capabilities and broader contextual understanding compared to earlier versions. Despite the growing use of LLM systems for seeking medical information, structured and simulation-based evaluations of Claude Opus 4's capabilities in diabetes management remain limited, particularly across domains such as patient education, clinical reasoning, and emotional support.This study aimed to conduct a baseline evaluation of Claude Opus 4's performance across key domains of diabetes care (i.e., patient education, clinical reasoning, and emotional support), and to identify preliminary insights that can inform future, evidence-based integration strategies.A three-step evaluation was conducted: (1) 30 diabetes management questions assessed using expert endocrinologist evaluation, (2) five fictional diabetes cases evaluated for clinical decision-making, and (3) emotional support responses assessed for appropriateness and empathy. Three expert endocrinologists graded responses according to American Diabetes Association guidelines.Claude Opus 4 achieved 80% accuracy in general diabetes knowledge, with high response reproducibility (96.7%), indicating baseline rather than clinically adequate performance. Clinical case evaluations showed moderate utility (mean expert rating = 4.4/7), while emotional-support assessments yielded high scores for empathy (6.2/7) and appropriateness (6.0/7). These findings suggest that although the model demonstrates promising informational and emotional-support capabilities, its current performance remains insufficient for autonomous clinical use and should be viewed as preliminary evidence to guide future, patient-inclusive validation studies.Although Claude Opus 4 demonstrates preliminary findings suggesting potential applications in diabetes care, education, and emotional support, this baseline assessment using fictional cases underscores the need for real-world validation with clinical data to determine true clinical utility and patient-centered impact. This simulation-based evaluation also offers practical lessons learned for researchers designing future LLM assessments, highlighting the need for mixed expert-patient panels, contextual validation, and person-centered metrics beyond numerical accuracy.

Clinical documentation improvement is critical for pediatric care, yet leveraging electronic health record (EHR) tools for this population is not well established. We aimed to adapt and implement a real-time, automated documentation assistance tool (AutoDx) to decrease clinical documentation integrity (CDI) coding queries and improve perceived ease of practice for pediatric inpatient providers.In this quality improvement study at an urban academic pediatric hospital, we adapted and implemented AutoDx for pediatric use by developing and validating pediatric-specific logic rules to alert providers to potential diagnoses based on EHR data. The primary outcome was the rate of CDI queries per 1,000 discharges for targeted diagnoses, aiming for a 50% reduction over a 5-month implementation period compared with a 12-month baseline. Secondary outcomes included provider-surveyed ease of practice, with a goal of a 25% improvement, and tool uptake.The aggregate rate of targeted CDI queries decreased by 58% postimplementation, from 80.7 to 33.9 per 1,000 discharges (p < 0.001). Moreover, analysis by interrupted time series demonstrated an immediate 45.5% reduction in the rate of coding queries (p = 0.028) following the implementation of the tool. The rate of queries for nontargeted diagnoses remained unchanged. Tool adoption increased steadily throughout the study period. While provider-reported time spent on queries did not significantly decrease, a majority of survey respondents (59%) perceived receiving fewer queries, and 46% agreed the tool made it easier to provide quality care.Implementation of a real-time, automated documentation support tool in a pediatric inpatient setting significantly reduced CDI coding queries for targeted diagnoses. Despite a "task substitution" effect where perceived workload did not decrease, the tool improved perceived ease of practice, demonstrating that targeted EHR interventions can enhance documentation accuracy and efficiency in pediatrics.

Achieving digital health equity and proper use of identity credentials is crucial as reliance on electronic modalities increases. Proxy access-now increasingly referred to as shared access-is a widely available functionality that offers identity credentials to care partners who assist loved ones in navigating the electronic care delivery demands of patients with complex care needs. However, adoption of these tools has been hindered by complicated user interfaces and low awareness.Drawing on frameworks and principles rooted in human-centered design (HCD), we conducted an evaluation of a multisite quality improvement study designed to increase the awareness and adoption of shared access to patient portals for older adults and their care partners. Through feedback gathered from key informants, we identified barriers to the adoption of materials created for the parent quality improvement project, and synthesize additional implementation strategies from informant feedback to improve shared access.We employed the Double Diamond Model (DDM) of HCD to guide our research. The DDM includes engaging a diverse group of community partners-older adults, care partners, health care system leaders, communications professionals-through focus groups and individual interviews. Our process involved identifying pain points related to registration for shared access, then synthesizing these insights through inductive coding and affinity mapping to generate solutions.An analysis of our community partner feedback revealed several themes, including the necessity for simplified patient portal registration, standardized terminology about shared access, and clear messaging strategies. A step-by-step video tutorial was developed as a prototype. The prototype was then implemented at a partner health system and received positive feedback, suggesting its potential for broader use.These findings emphasize the importance of involving "end users" (patients, care partners, health care system leaders, communications professionals) in the evaluation and implementation of digital health tools. Approaching challenges with an HCD mindset helped our team identify barriers to shared access adoption and led to the development of a tangible resource (prototype and video). This project highlights the potential for HCD to drive improvements in digital health equity.This research demonstrates a practical application of HCD methods in developing effective solutions for enhancing shared access for older adults, and all people using patient portals.

Long COVID, characterized by persistent or recurring symptoms post-COVID-19 infection, poses challenges for pediatric care and research due to the lack of a standardized clinical definition. Adult-focused phenotypes do not translate well to children, given developmental and physiological differences, and pediatric-specific phenotypes have not been compared with chart review.This study introduces and evaluates a pediatric-specific rule-based computable phenotype (CP) to identify long COVID using electronic health record data. We compare its performance to manual chart review.We applied the CP, composed of diagnostic codes empirically associated with long COVID, to 339,467 pediatric patients with SARS-CoV-2 infection in the RECOVER PCORnet EHR database. The CP identified 31,781 patients with long COVID. Clinicians conducted chart reviews on a subset of patients across 16 hospital systems to assess performance. We qualitatively reviewed discordant cases to understand differences between CP and clinician identification.Among the 651 reviewed patients (339 females, M _age = 10.10 years), the CP showed moderate agreement with clinician identification (accuracy = 0.62, positive predictive value [PPV] = 0.49, negative predictive value [NPV] = 0.75, sensitivity = 0.52, specificity = 0.84). Performance was largely consistent across age and dominant variant but varied by symptom cluster count. Most discrepancies between the CP and chart review occurred when the CP identified a case, but the clinician did not, often because clinicians attributed symptoms to preexisting conditions (73%). When clinicians identified cases missed by the CP, they often used broader symptom or timing criteria (69%). Model performance improved when the CP accounted for preexisting conditions (accuracy = 0.71, PPV = 0.65, NPV = 0.74, sensitivity = 0.59, specificity = 0.79).This study presents a CP for pediatric long COVID. While agreement with manual review was moderate, most discrepancies were explained by differences in interpreting symptoms when patients had preexisting conditions. Accounting for these conditions improved accuracy and highlights the need for a consensus definition. These findings support the development of reliable, scalable tools for pediatric long COVID research.

Clinical decision support systems (CDSS) are central to modern health care, but their effectiveness is compromised during system downtimes, which affect 96% of health care organizations. During these failures, clinicians lose access to critical decision-making tools like order sets, increasing the risk of medical errors. Traditional downtime solutions, such as paper-based protocols, are often impractical and difficult to maintain.This study introduces and evaluates Offsite Repository for Clinical Assets (ORCA), a resilient web-based solution designed to maintain access to electronic health record (EHR) order sets during system failures. We assessed its usability and effectiveness as a downtime decision support tool across various clinical settings.ORCA was developed based on an analysis of previous downtime incidents, replicating essential order set functionality while ensuring offsite accessibility. We conducted usability testing with 16 clinicians from diverse specialties, using structured tasks and think-aloud protocols. User feedback was collected through the Usability Metric for User Experience (UMUX) questionnaire and thematic analysis of interview transcripts.ORCA demonstrated strong usability (mean UMUX score: 86.2). Thematic analysis revealed key implementation challenges: system limitations, workflow integration, and interface navigation. Users valued ORCA's familiar interface and offsite accessibility but identified critical gaps in dynamic decision support capabilities.ORCA represents a viable approach to maintaining basic clinical decision support (CDS) during downtimes. However, significant challenges remain in replicating dynamic CDS features and ensuring effective integration with existing downtime procedures. These findings inform future development of resilient CDSS and highlight the importance of planned fallback pathways in clinical systems.

This study aims to evaluate physicians' practices and perspectives regarding large language models (LLMs) in health care settings.A cross-sectional survey study was conducted between May and July 2024, comparing physician perspectives at two major academic medical centers (AMCs), one with institutional LLM access and one without. Participants included both clinical faculty and trainees recruited through departmental leadership and snowball sampling. Primary outcomes were current LLM use frequency, ranked importance of evaluation metrics, liability concerns, and preferred learning topics.Among 306 respondents (217 attending physicians [70.9%], 80 trainees [26.1%]), 197 (64.4%) reported using LLMs. The AMC with institutional LLM access reported significantly lower liability concerns (49.2 vs. 66.7% reporting high concern; 17.5 percentage points difference [95% CI, 6.8-28.2]; p = 0.0082). Accuracy was prioritized across all specialties (median rank 1.0 [interquartile range; IQR, 1.0-2.0]). Of the respondents, 287 physicians (94%) requested additional training. Key learning priorities were clinical applications (206 [71.9%]) and risk management (181 [63.1%]). Despite widespread personal use, only 8 physicians (2.6%) recommended LLMs to patients. Notable specialty and demographic variations emerged, with younger physicians showing higher enthusiasm but also elevated legal concerns.This survey study provides insights into physicians' current usage patterns and perspectives on LLMs. Liability concerns appear to be lessened in settings with institutional LLM access. The findings suggest opportunities for medical centers to consider when developing LLM-related policies and educational programs.