Applied Clinical Informatics最新文献

Clinical decision support (CDS) tools are critical for improving care delivery and guideline adherence but are associated with clinician burnout when inadequately designed and implemented. User-centered design (UCD) and implementation science (IS) methods are evidence-based approaches to optimizing CDS tools, but are infrequently used in part due to limited guidance on how to apply them within resource-constrained health systems.This paper focuses on pragmatic application of an integrated UCD-IS approach, demonstrating how it can be adapted to meet operational constraints through two real-world case studies.We applied an integrated UCD-IS approach guided by the Practical Robust Implementation and Sustainability Model (PRISM) to two CDS projects within a large regional health system: (1) adapting a CDS for improving prescribing of goal-directed medical therapy in patients with heart failure during virtual visits, and (2) expanding a naloxone co-prescribing CDS across outpatient settings. Each project followed iterative phases-partner engagement, design, prototyping, deployment, and evaluation tailored to time and resource constraints of the health system. Methods used included interviews, focus groups, surveys, and usability testing.Multilevel partner engagement surfaced critical insights that informed design adaptations. The heart failure CDS was adapted using minimal changes while the naloxone CDS underwent more extensive design iterations. Both projects balanced rigor and pragmatism, enabling timely implementation and rigorous design evaluation while supporting feasibility and sustainability. Iterative evaluations of both CDS are ongoing and structured to inform real-time refinements that support patient, clinician, and system-level outcomes.This work provides practical guidance on applying an integrated UCD-IS approach to CDS design and evaluation in time and resource-constrained health system environments. By flexibly applying this integrated approach, health systems can better address multilevel partner needs, ensure contextual relevance, and support sustained adoption.

Malnutrition remains a critical global health challenge among hospitalized patients, necessitating effective nutrition support systems.This study aims to construct and evaluate a cross-professional, cross-sectoral nutrition health care information system (CPCS-NHIS) to optimize clinical nutrition management.The system integrates modified medical systems to unify information flows, knowledge, and clinical roles. In addition, a 20-item across six dimensions electronic questionnaire based on the revised DeLone and McLean IS Success model was developed to evaluate the success of the CSCP-NHIS. Besides, user satisfaction was assessed as a key dimension using a 5-point Likert's scale (1 = strongly disagree to 5 = strongly agree). Finally, the results of the questionnaire were further validated by reliability and validity analysis.The CPCS-NHIS features comprehensive functions including bedside nutritional screening, assessment, intervention, diagnosis, monitoring, enteral nutrition prescription, and QR-code autopayment. Over 80% of users expressed willingness to continue using and recommending the system. The questionnaire results demonstrated strong psychometric properties: all Cronbach's α coefficients >0.80, confirmed reliability; confirmatory factor analysis showed convergent validity (the average variance extracted >0.50, construct reliability >0.80); and model fit indices were excellent, with a chi-square value of 1.86, a root mean squared error of approximation of 0.09, a root mean square residual of 0.02, and a comparative fit index of 0.9.The CPCS-NHIS provides a practical framework for existing nutritional health care information systems, based on the nutrition care process and model, with robust psychometric evidence and high user acceptance.

Problem lists are intended to support high-quality care, but are often long and outdated. Despite policy efforts to encourage their upkeep-such as the "Problem List Reviewed" attestation checkbox in electronic health records (EHRs)-many diagnoses remain on lists far longer than clinically appropriate. Clinicians often check the attestation box that problem lists have been reviewed to comply with performance measures without reviewing and modifying the list.This study aimed to assess whether attestation of "Problem List Reviewed" is associated with shorter duration of short-term (acute and billing-related) diagnoses on problem lists.Multi-method study including retrospective EHR data from 892,329 patient visits at 24 Federally Qualified Health Centers across the United States and chart review data. Participants included adult patients with 2+ primary care visits during the study period. The primary outcome was the duration that short-term diagnoses remained on the problem list. The secondary outcome was the relationship between duration and attestation of review.Diagnoses persisted on problem lists far beyond their expected clinical duration (e.g., acute pharyngitis: median 343 days; urinary tract infection: 443 days). For 6 of 12 conditions, attestation was associated with significantly longer duration (e.g., pharyngitis: 371 days with attestation vs. 302.5 without, p < 0.001). Only one code ("Encounter for Screening") was associated with shorter duration when attested (p = 0.016). Chart reviews revealed minimal evidence of problem list management during visits.Checking the "Problem List Reviewed" box is not associated with the appropriate removal of short-term diagnoses and may paradoxically contribute to their persistence. Incentive structures focused on clinician attestation of problem list review are counterproductive. Improving the design and functionality of problem lists is likely a better way to maintain concise, up-to-date lists that drive care and focus attention. Expecting clinicians to keep problem lists clean by adding an attestation check box is likely misguided.

Digital health tools, such as artificial intelligence scribes, offer significant potential to alleviate physician burnout and reduce administrative burdens associated with electronic health records. Despite their promise, Canadian health care organizations face challenges in establishing cohesive strategies for their effective implementation and evaluation.This paper explores actionable, organizational strategies to enhance physician wellness through digital health tools. It examines systemic barriers, promising practices, and infrastructure needs, culminating in five key recommendations for sustainable adoption.An environmental scan assessed digital health initiatives across Canada, incorporating case studies from wellness committees, advisory councils, and physician-led programs. National surveys and evaluation frameworks were reviewed to identify barriers, facilitators, and outcomes.Findings highlight challenges such as insufficient training and funding, fragmented governance and policies, and varied accessibility to digital tools. Promising initiatives demonstrated reduced documentation burdens, improved physician satisfaction, and streamlined workflows. Successful strategies included forming advisory committees, developing governance frameworks, and implementing standardized training programs. However, systemic barriers, including funding constraints and resistance to change, persist and require targeted interventions.The responsible adoption of digital health tools in Canadian health care demands robust governance, equitable funding, and standardized toolkits tailored to diverse settings. Active physician engagement and comprehensive training programs are essential to overcoming systemic challenges and fostering sustainable improvements in physician wellness and health care system efficiency.

Patient experience mechanisms (e.g., safety netting, patient partnership) are routinely used by health care professionals (HCPs) to support high-quality care. However, there is limited synthesis of these mechanisms across studies, and little is known about how they translate to virtual care.This study aimed to conduct a scoping review to (1) identify mechanisms used by HCPs to enhance patient experience during consultations and (2) to consider how these may be adapted for virtual care delivery.A scoping review using narrative synthesis. Studies were obtained from four databases (Ovid [MEDLINE], CINAHL Complete, Cochrane Library, and ProQuest) and gray literature. Three reviewers independently screened studies featuring HCP-patient interactions and discussion of patient experience mechanisms. The NHS Patient Experience Framework guided mechanism identification. Considerations for in-person and virtual care interactions were compared. Virtual care considerations were extracted from eligible studies and mapped to each of the mechanism categories.A total of 49 studies were included, mainly commentaries, guidelines, or executive summaries (20/49, 41%). Five categories of mechanisms were identified: clinician-focused (n = 5), patient-focused (n = 5), relationship/familial (n = 3), organizational (n = 6), and IT and digital (n = 3). The three most frequent actionable mechanisms were patient empowerment and engagement (49%, 24/49), patient education (41%, 20/49), and clinical organization and positive safety culture (41%, 20/49). For virtual care, key considerations included adapting communication and relationship-building mechanisms to virtual formats, supporting patient digital literacy, and maintaining continuity and trust during remote interactions. These mechanisms were supported by both direct, indirect, and inferred evidence.To the best of our knowledge, this review provides the first structured mapping of patient experience mechanisms and considerations to virtual care contexts. Findings support HCPs and health systems in tailoring communication, relational, and digital strategies to enhance care across hybrid models. Continual reflection of what results in positive patient experiences is essential as we continue to transition to hybrid models of care.

Maternal harm, especially for Black women, is a significant health care issue. Unstructured clinical notes in electronic health records (EHRs) may reveal unsafe maternal care. Prior studies using natural language processing (NLP) have shown that tone and sentiment in notes contribute to preventable safety events.This study aimed to examine whether negative patient descriptors in EHR clinical notes are associated with adverse maternal outcomes and how their use varies by patient demographics.We conducted a retrospective cohort study of women who delivered at two large birthing hospitals in Washington, DC between January 1, 2016 and March 31, 2020. Using a predefined list of negative keywords (e.g., combative) and NLP, we identified sentences from clinical notes for manual review. Two subject matter experts labeled keywords as "negative descriptors" if they negatively described patients. A logistic regression model with elastic net regularization was trained on the labeled sentences to classify the remaining corpus. We evaluated the prevalence of negative descriptors by race, age, insurance type, and pregnancy outcomes, and calculated adjusted odds ratios.Among 190,026 clinical notes from 9,302 patients, 719 notes associated with 444 patients contained at least one negative descriptor. Of these, 313 (70.5%) were Black, 45 (10.1%) were White, and 86 (19.4%) were from Other racial groups (p < 0.001). Negative descriptors were more common among younger patients (18-29 years: 49.3%) and those with Medicare/Medicaid insurance (65.3%). Although case patients-defined as those with postpartum readmission or severe maternal morbidity-had slightly fewer descriptors overall, they had higher adjusted odds of having them. Black patients were associated with higher odds, and commercial insurance with lower odds, of having negative descriptors.Negative descriptors appear disproportionately in the notes of Black patients and those with public insurance, suggesting implicit bias in documentation. Addressing biased language is essential for improving equity in maternal care.

This study sought to characterize how a population experienced health-related social needs (HRSNs) over time.We employed hidden Markov modeling using data extracted from a natural language processing state machine from 2018 to 2020 to examine whether a patient experienced any food, legal, transportation, employment, financial, or housing needs. Characteristics of patients transitioning into low/high-risk states were compared. We also identified the frequency at which patients transitioned according to their risk state.Our results identified that five hidden states best represented how patients are experiencing HRSNs longitudinally. Of 48,055 patients, 80% were categorized in states 1 and 2, labeled as low risk. Nine percent, 8%, and 3% of the study population were labeled as medium, high, and very high risk, respectively. Results also showed that low and high-risk patients (states 1, 2, and 5) only transition states once every year and a half, while patients in medium and high-risk states transition approximately once per year.Low and very high-risk patients tend to remain in the same state over time, suggesting that low-risk patients may have the means to maintain a healthy state while very high-risk patients have a difficult time resolving multiple HRSNs. Early screening and immediate interventions may be beneficial in mitigating the persistent harm of unaddressed HRSNs.

Effective clinical decision support (CDS) interventions improve adherence to care guidelines, reduce prescribing errors, and, in some settings, decrease patient mortality. However, misalignment with the "Five Rights" framework, particularly regarding CDS timing in clinical workflows, can lead to implementation failures, alert fatigue, and physician burnout.This case series aimed to evaluate and redesign three interruptive CDS alerts at a large safety net health system to better align with clinician workflows, reduce interruptions, and improve compliance with care guidelines.We analyzed three interruptive alerts using data from Epic's SlicerDicer tool, focusing on alert frequency, contributors to alert triggering, and user responses before and after intervention. Alerts were modified to improve their timing and relevance within the workflow.Modifications included retiming a human immunodeficiency virus screening alert to trigger during laboratory test orders, reducing alert firings by 87% while increasing monthly screening orders from 3,561 to 4,547 (p < 0.001). An administrative alert's firing frequency decreased by 86% through the introduction of a 4-hour lockout period, maintaining compliance rates. Finally, restricting a pediatric head circumference discrepancy alert to in-person visits only eliminated interruptions during telehealth encounters, addressing a major source of clinician frustration.Aligning CDS tools with clinical workflows through adherence to the "Five Rights" framework reduces interruptions and improves outcomes. Iterative review, user feedback, and proactive redesign are essential to ensure CDS effectiveness, particularly as health care evolves to include novel care delivery models like telehealth.

Venous thromboembolism (VTE) prophylaxis in hospitalized patients must balance risks of bleeding and thrombosis. Clinical changes such as bleeding or renal injury can also trigger changes or delays in thromboprophylaxis. Electronic health record alerts (EHRAs) can allow for targeted notification to providers to improve venous thromboembolism prophylaxis and improve patient outcomes at the risk of alert fatigue if not carefully designed and implemented.This study aimed to develop and refine an EHRA that minimizes nuisance alerts while facilitating appropriate ordering of VTE prophylaxis for medical patients.A multidisciplinary group at a single large safety-net academic medical center developed an EHRA to identify patients at increased thrombosis risk, but without orders for VTE prophylaxis. This was refined over four phases: development and validation, initial monitoring and exclusion criteria adjustment, COVID-19-related modifications, and delayed surveillance and modification. Data analysis evaluated criteria including alert frequency, alert action/utilization, and alert duration.The EHRA fired an average of 33.3 times per day across all phases of the study. Phase 1 of EHRA implementation showed significantly increased alerts per patient (6.4 to 43.3 alerts per day, p < 0.01) as well as the percentage of patients with >5 alerts (2.8 to 60.0%, p < 0.01). Modifications in phase 2 and phase 3 increased alert rates without any significant effect on subsequent action taken by a provider. Phase 4 modifications led to a significant reduction in alert frequency (44.1 to 14.9 alerts per day, p < 0.01) coupled with a notable increase in provider action (0.24 to 7.73%, p < 0.01).This multidisciplinary, provider-centered, intervention improved alert appearance, and information needed to guide providers increased provider engagement 32-fold, with a 3-fold decrease in alert frequency. Despite improvements, ongoing monitoring and maintenance of this alert is important.

Electronic patient-reported outcome measures (ePROMs) can improve care for people with cancer, but effectiveness hinges on well-supported integration in clinical settings.We evaluated clinician use of specific clinical decision support (CDS) tools in the electronic health record (EHR) designed to facilitate timely, clinically appropriate responses to ePROM scores for six symptoms commonly experienced by cancer patients.The parent pragmatic trial, which took place at Mayo Clinic (Rochester, Minnesota, United States) and its affiliated community health care system between March 2019 and January 2023, evaluated the population-level effectiveness and implementation of an ePROM surveillance and EHR-facilitated collaborative care symptom management intervention. The present evaluation used a case study approach with four data sources: (1) clinician interactions with CDS tools abstracted from the EHR; (2) clinician notes identified with an institution-specific textual search tool; (3) qualitative interviews and group discussions with care teams; and (4) administrative records reviewed to identify training and outreach to care teams.EHR metrics showed very low adoption of CDS tools including alerts and symptom-specific order sets, despite educational outreach and information technology support provided to clinical care teams. Qualitative findings revealed that CDS use was not easy to integrate into busy clinical workflows and highlighted clinician perceptions that the collaborative care intervention provided additional patient support that reduced clinicians' need to utilize CDS tools. They also highlight the importance of contextual factors, including institutional priorities and EHR changes.This pragmatic clinical trial case study found limited adoption of EHR CDS tools that had been developed to increase clinicians' awareness of and responses to ePROM data. Findings suggest the need to align clinician and organizational implementation strategies, simplify CDS tools to fit practice expectations, and identify and address contextual factors that could undercut strategies like education and peer support. This may be especially important for teams who aim to iteratively evaluate and refine CDS and implementation strategies for multicomponent interventions or introduce new strategies that are responsive to barriers while maintaining scalability.