UNASSIGNED: Connecting individuals to existing community resources is critical to addressing social needs and improving population health. While there is much ongoing informatics work embedding social needs screening and referrals into health care systems and their electronic health records, there has been less focus on the digital ecosystem and needs of community-based organizations (CBOs) providing or connecting individuals to these resources.
UNASSIGNED: We used human-centered design to develop a digital platform for CBOs, focused on identification of health and social resources and communication with their clients.
UNASSIGNED: Centered in the Develop phase of the design process, we conducted in-depth interviews in 2 phases with community-based organizational leadership and staff to create and iterate on the platform. We elicited and mapped participant feedback to theory-informed domains from the Technology Acceptance Model, such as Usefulness and Ease of Use, to build the final product and summarized all major design decisions as the platform development proceeded.
UNASSIGNED: Overall, we completed 22 interviews with 18 community-based organizational leadership and staff in 2 consecutive Develop phases. After coding of the interview transcripts, there were 4 major themes related to usability, relevance, and external factors impacting use. Specifically, CBOs expressed an interest in a customer relationship management software to manage their client interactions and communications, and they needed specific additional features to address the scope of their everyday work, namely (1) digital and SMS text messaging communication with clients and (2) easy ways to identify relevant community resources based on diverse client needs and various program eligibility criteria. Finally, clear implementation needs emerged, such as digital training and support for staff using new platforms. The final platform, titled \"Mapping to Enhance the Vitality of Engaged Neighborhoods (MAVEN),\" was completed in the Salesforce environment in 2022, and it included features and functions directly mapped to the design process.
UNASSIGNED: Engaging community organizations in user-centered design of a health and social resource platform was essential to tapping into their deep expertise in serving local communities and neighborhoods. Design methods informed by behavioral theory can be similarly employed in other informatics research. Moving forward, much more work will be necessary to support the implementation of platforms specific to CBOs\' needs, especially given the resources, training, and customization needed in these settings.

OBJECTIVE: The purpose of this study was to define current practices related to beta-lactam/beta-lactamase inhibitor (BL/BLI) dose descriptions in hospitals that provide care for pediatric patients and to identify perceived implications of standardizing BL/BLI dose communication and ordering to a total drug-based strategy.
METHODS: A 27-item electronic survey was distributed via 4 pediatric pharmacy and infectious diseases listservs. Survey questions pertained to hospital demographics, dosing communication practices, BL/BLI ordering and labeling practices, obstacles to safe BL/BLI use, and the effects of potential standardization to a total drug communication strategy. SPSS was used for quantitative analysis and MAXQDA was used for qualitative analysis.
RESULTS: A total of 140 unique survey responses were analyzed after exclusion of incomplete responses and reconciliation of multiple responses from the same institution. Overall, 56.2% of institutions order BL/BLIs by BL component for pediatric patients, and 22% of institutions order by BL component for adult patients. Approximately half (51.8%) of respondents felt that standardizing to total drug would have a negative effect at their institution; perception of potential effect varied based on the institution\'s ordering strategy.
CONCLUSIONS: Communication and ordering of BL/BLIs is inconsistent across institutions and between pediatric and adult patients. In the short term, the perception is that standardization would compound institutional challenges.

The Alzheimer\'s Disease Neuroimaging Initiative (ADNI) has revolutionized the landscape of Alzheimer\'s research through its Informatics Core, which has facilitated unprecedented data standardization and sharing. Over 20 years, ADNI established a robust informatics framework, enabling the validation of biomarkers and supporting global research efforts. The Informatics Core, centered at the Laboratory of Neuro Imaging (LONI), provides a comprehensive data hub that ensures data quality, accessibility, and security, fostering over 5600 publications and significant scientific advancements. By embracing open data sharing principles, ADNI set a gold standard in data transparency, allowing over 26,000 investigators from 169 countries to access and download a wealth of multimodal data. This collaborative approach not only accelerated biomarker discovery and drug development and advanced our understanding of Alzheimer\'s disease but also has served as a model for other research initiatives, demonstrating the transformative potential of carefully designed informatics models and shared data in driving global scientific progress. HIGHLIGHTS: Accelerating biomarker discovery and drug development for Alzheimer\'s disease. Alzheimer\'s Disease Neuroimaging Initiative\'s (ADNI\'s) open data sharing drives scientific progress. Data exploration and coupled analytics to data archives.

BACKGROUND: Electronic health records and other clinical information systems have crucial roles in health service delivery and are often utilised for patient care as well as health promotion and research. Government agencies and healthcare bodies are gradually shifting the focus on how these data systems can be harnessed for secondary uses such as reflective practice, professional learning and continuing professional development. Whilst there has been a presence in research around the attitudes of health professionals in employing clinical information systems to support their reflective practice, there has been very little research into consumer attitudes towards these data systems and how they would like to interact with such structures. The study described in this article aimed to address this gap in the literature by exploring community perspectives on the secondary use of Electronic Health Data for health professional learning and practice reflection.
METHODS: A qualitative methodology was used, with data being collected via semi-structured interviews. Interviews were conducted via phone and audio recordings, before being transcribed into text for analysis. Reflective thematic analysis was undertaken to analyse the data.
RESULTS: Fifteen Australians consented to participate in an interview. Analysis of interview data generated five themes: (1) Knowledge about health professional registration and professional learning; (2) Secondary uses of Electronic Health Data; (3) Factors that enable the use of Electronic Health Data for health professional learning; (4) Challenges using Electronic Health Data for health professional learning and (5) Expectations around consent to use Electronic Health Data for health professional learning.
CONCLUSIONS: Australians are generally supportive of health professionals using Electronic Health Data to support reflective practice and learning but identify several challenges for data being used in this way.

BACKGROUND: There is a dearth of artificial intelligence (AI) development and research dedicated to pediatric radiology. The newest iterations of large language models (LLMs) like ChatGPT can process image and video input in addition to text. They are thus theoretically capable of providing impressions of input radiological images.
OBJECTIVE: To assess the ability of multimodal LLMs to interpret pediatric radiological images.
METHODS: Thirty medically significant cases were collected and submitted to GPT-4 (OpenAI, San Francisco, CA), Gemini 1.5 Pro (Google, Mountain View, CA), and Claude 3 Opus (Anthropic, San Francisco, CA) with a short history for a total of 90 images. AI responses were recorded and independently assessed for accuracy by a resident and attending physician. 95% confidence intervals were determined using the adjusted Wald method.
RESULTS: Overall, the models correctly diagnosed 27.8% (25/90) of images (95% CI=19.5-37.8%), were partially correct for 13.3% (12/90) of images (95% CI=2.7-26.4%), and were incorrect for 58.9% (53/90) of images (95% CI=48.6-68.5%).
CONCLUSIONS: Multimodal LLMs are not yet capable of interpreting pediatric radiological images.

BACKGROUND: Despite national guidelines recommending naloxone co-prescription with high-risk medications, rates remain low nationally. This was reflected at our institution with remarkably low naloxone prescribing rates. We sought to determine if a clinical decision support (CDS) tool could increase rates of naloxone co-prescribing with high-risk prescriptions.
METHODS:  An alert in the electronic health record was triggered upon signing an order for a high-risk opioid medication without a naloxone co-prescription. We examined all opioid prescriptions written by family and general internal medicine practitioners at the University of Iowa Hospitals and Clinics in outpatient encounters between November 30, 2020, and February 28, 2022. Once triggered by a high-risk prescription, the CDS tool had the option to choose an order set with an automatically selected co-prescription for naloxone along with patient instructions automatically added to the patient\'s after-visit summary (AVS). We examined the monthly percentage of patients receiving Schedule II opioid prescriptions ≥90 morphine milliequivalents (MME)/day who received concurrent naloxone prescriptions in the 12 months before the CDS went live and the three months following go-live.
RESULTS:  Concurrent naloxone prescriptions increased from 1.1% in the 12 months prior to implementation in November 2021 to 9.4% (p<0.001) during the post-intervention period across eight family medicine and internal medicine clinics.
CONCLUSIONS:  This single-center quality improvement project with retrospective analysis demonstrates the potential efficacy of a single CDS tool in increasing the rate of naloxone prescription. The impact of such prescribing on overall mortality requires further research.
CONCLUSIONS: The CDS tool was easy to implement and improved rates of appropriate naloxone co-prescribing.

Although numerous AI algorithms have been published, the relatively small number of algorithms used clinically is partly due to the difficulty of implementing AI seamlessly into the clinical workflow for radiologists and for their healthcare enterprise. The authors developed an AI orchestrator to facilitate the deployment and use of AI tools in a large multi-site university healthcare system and used it to conduct opportunistic screening for hepatic steatosis. During the 60-day study period, 991 abdominal CTs were processed at multiple different physical locations with an average turnaround time of 2.8 min. Quality control images and AI results were fully integrated into the existing clinical workflow. All input into and output from the server was in standardized data formats. The authors describe the methodology in detail; this framework can be adapted to integrate any clinical AI algorithm.

OBJECTIVE: We aimed to evaluate the feasibility of using ChatGPT as programming support for nursing PhD students conducting analyses using the All of Us Researcher Workbench.
METHODS: 9 students in a PhD-level nursing course were prospectively randomized into 2 groups who used ChatGPT for programming support on alternating assignments in the workbench. Students reported completion time, confidence, and qualitative reflections on barriers, resources used, and the learning process.
RESULTS: The median completion time was shorter for novices and certain assignments using ChatGPT. In qualitative reflections, students reported ChatGPT helped generate and troubleshoot code and facilitated learning but was occasionally inaccurate.
CONCLUSIONS: ChatGPT provided cognitive scaffolding that enabled students to move toward complex programming tasks using the All of Us Researcher Workbench but should be used in combination with other resources.
CONCLUSIONS: Our findings support the feasibility of using ChatGPT to help PhD nursing students use the All of Us Researcher Workbench to pursue novel research directions.

BACKGROUND: More targeted management of severe acute pediatric asthma could improve clinical outcomes.
OBJECTIVE: To identify distinct clinical phenotypes of severe acute pediatric asthma using variables obtained in the first 12 h of hospitalization.
METHODS: We conducted a retrospective cohort study in a quaternary care children\'s hospital from 2014 to 2022. Encounters for children ages 2-18 years admitted to the hospital for asthma were included. We used consensus k means clustering with patient demographics, vital signs, diagnostics, and laboratory data obtained in the first 12 h of hospitalization.
RESULTS: The study population included 683 encounters divided into derivation (80%) and validation (20%) sets, and two distinct clusters were identified. Compared to Cluster 1 in the derivation set, Cluster 2 encounters (177 [32%]) were older (11 years [8; 14] vs. 5 years [3; 8]; p < .01) and more commonly males (63% vs. 53%; p = .03) of Black race (51% vs. 40%; p = .03) with non-Hispanic ethnicity (96% vs. 84%; p < .01). Cluster 2 encounters had smaller improvements in vital signs at 12-h including percent change in heart rate (-1.7 [-11.7; 12.7] vs. -7.8 [-18.5; 1.7]; p < .01), and respiratory rate (0.0 [-20.0; 22.2] vs. -11.4 [-27.3; 9.0]; p < .01). Encounters in Cluster 2 had lower percentages of neutrophils (70.0 [55.0; 83.0] vs. 85.0 [77.0; 90.0]; p < .01) and higher percentages of lymphocytes (17.0 [8.0; 32.0] vs. 9.0 [5.3; 14.0]; p < .01). Cluster 2 encounters had higher rates of invasive mechanical ventilation (23% vs. 5%; p < .01), longer hospital length of stay (4.5 [2.6; 8.8] vs. 2.9 [2.0; 4.3]; p < .01), and a higher mortality rate (7.3% vs. 0.0%; p < .01). The predicted cluster assignments in the validation set shared the same ratio (~2:1), and many of the same characteristics.
CONCLUSIONS: We identified two clinical phenotypes of severe acute pediatric asthma which exhibited distinct clinical features and outcomes.

OBJECTIVE: To understand Veterans Health Administration (VA) leaders\' information and resource needs for managing post-9/11 Veterans\' VA enrollment and retention.
METHODS: Interviews conducted from March-May 2022 of VA Medical Center (VAMC) leaders (N = 27) across 15 sites, using stratified sampling based on VAMC characteristics: enrollment rates, number of recently separated Veterans in catchment area, and state Medicaid expansion status.
METHODS: Interview questions were developed using Petersen et al.\'s Factors Influencing Choice of Healthcare System framework as a guide. Interviews were transcribed verbatim, and two coders analyzed the interviews using Atlas.ti, a qualitative software program. Coders followed the qualitative coding philosophy developed by Crabtree and Miller, a process of developing codes for salient concepts as they are identified during the analysis process.
METHODS: Two coders analyzed 22% (N = 6) of the interviews and discussed and adjudicated any discrepancies. One coder independently coded the remainder of the interviews.
RESULTS: Several key themes were identified regarding facilitators and barriers for VA enrollment including reputation for high-quality VA care, convenience of VA services, awareness of VA services and benefits, and VA mental health services. Nearly every VA leader actively used tools and data to understand enrollment and retention rates and sought to enroll and retain more Veterans. To improve the management of enrollment and retention, VA leaders would like data shared in an easily understandable format and the capability to share data between the VA and community healthcare systems.
CONCLUSIONS: Enrollment and retention information is important for healthcare leaders to guide their health system decisions. Various tools are currently being used to try to understand the data. However, a multifunctional tool is needed to better aggregate the data to provide VA leadership with key information on Veterans\' enrollment and retention.