Objectives/Goals: Decentralized clinical trials (DCTs) shift participation outside traditional sites. This poster explores innovative administrative strategies for incorporating decentralized elements, improving flexibility, access, and efficiency in clinical research. Methods/Study Population: Modern administrative approaches are crucial for unlocking DCT potential by streamlining logistics, enhancing participant experience, and ensuring regulatory compliance. Key innovations include expedited IRB Review: using innovative template language; innovative consent strategies – eConsent and remote/virtual and contactless enrollment; telehealth communications – Twilio (voice calls and text messages)/Zoom (virtual video visits); automated participant compensation and rideshare services – Greenphire ClinCard®; flexible data collection – automated recruitment/intake forms and research surveys – REDCap; mobile research unit/self-collection lab kits via mail. Implementing decentralization into your study unlocks the potential to rapidly recruit more diverse populations. Results/Anticipated Results: The integration of decentralized elements into clinical trials holds significant potential for reducing participant burden, thereby improving recruitment, retention, and overall trial efficiency. However, the success of decentralized clinical trials relies heavily on the implementation of modern administrative approaches that streamline operations and maintain regulatory compliance. Together, these administrative advancements not only enhance the operational flexibility of decentralized trials but also support the inclusion of diverse populations by reducing geographical and logistical barriers. Discussion/Significance of Impact: As decentralized clinical trials continue to evolve, the adoption and further innovation of modern administrative solutions will be essential in improving the overall efficiency and inclusivity of clinical research.

Objectives/Goals: Children with chronic respiratory technology needs (CRTN) are becoming a dominant patient group in pediatric intensive care units (ICUs). However, little is known about patient-level, long-term outcomes in this population. The lack of such knowledge may lead to inadequate ICU therapies, interventions, or follow-up care. Methods/Study Population: This project will deploy a set of ecological momentary assessment (EMA) modules measuring real-time functioning as well as standardized instruments to measure child and family outcomes including health care utilization, physical functioning, and health-related quality of life following pediatric critical illness in children with CRTN. EMA has particular strength in assessing conditions where individual-level characteristics vary over time, as after critical illness. EMA’s recurrent measurements allow for evaluation of the variables’ temporal course and limit the potential for bias associated with recall surveys. Pulmonary function in children with CRTN in this study will be monitored over time using standardized pulmonary metrics and information from home respiratory machines. Results/Anticipated Results: This work tests the central hypothesis that long-term functional outcomes in children with CRTN are predicted by multimodal data obtained during and shortly after critical illness. To date, 17 families (of a planned 70) have been enrolled. Adherence to EMA modules is high, with 80% completion. Following serial data collection at 3, 6, and 9 months after hospital discharge, phenotypes of recovery (including improvement, stability, or deterioration) will be described. This will include 1) describing the patient demographic and clinical features associated with each long-term outcome trajectory and 2) identifying subgroups with similar outcome trajectories using patient demographics, features of the clinical illness, and EMA data using both traditional biostatistical and causal analysis techniques. Discussion/Significance of Impact: This project will provide important insights into the long-term outcomes following critical illness of children with CRTN while utilizing an innovative methodology. This proposal will provide the necessary information to drive future clinical trials assessing potential interventions at a number of different points to improve outcomes.

Objectives/Goals: The Fanconi anemia (FA) pathway is responsible for faithful DNA damage repair. FA mutations are common in multiple types of cancer, including HPV-negative head and neck cancers. We sought to identify synthetic lethal genes within this pathway to target treatment of FA-mutant tumors through siRNA- and chemical-compound-based screens. Methods/Study Population: First, we completed siRNA-based and chemical compound-based screening assays to identify gene targets that reduce patient derived Fanconi pathway mutant cell (FA-D2) viability compared to Fanconi pathway proficient cells (FA-D2 + FANCD2). Five aurora kinase (AURK) inhibitors from the compound screen were chosen for further evaluation. Cell lines were treated with AURK inhibitors or siRNA-based AURK knockdown to assess viability, proliferation, DNA repair, and cell cycle progression differences. Patient mutational, mRNA expression, and outcome data were accessed through The Cancer Genome Atlas (TCGA) portal and the Caris CODEai portal. We stratified patients by tumor AURKA and AURKB mRNA levels and assessed differences in patient survival, tumor grade, and DNA repair proficiency. Results/Anticipated Results: In both screens, AURKA came up as a target to selectively reduce the growth of FA-D2 cells compared to FA-D2 + FANCD2 cells. All five AURK inhibitors identified showed selective growth inhibition (~50–75%) in FA-D2 cells at low nanomolar doses. We narrowed our selection to hesperadin, an AURKB-specific inhibitor, which showed the highest selectivity. siRNA knockdown of AURKA and AURKB decreased cell viability by 50% and 20%, respectively. Patients with FA-mutated tumors from the TCGA pan-cancer dataset had high AURKA (twofold) and AURKB (threefold) mRNA expression. AURKA and AURKB tumor mRNA expression was significantly associated with poor patient survival. Homologous recombination deficiency scores were increased ~5-fold (p Discussion/Significance of Impact: We hypothesize that in FA-deficient backgrounds, loss of AURKA or AURKB leads to heightened genomic instability due to cell cycle dysregulation and accumulated DNA damage. Our findings warrant investigation of the therapeutic potential for AURK inhibitors, specifically hesperadin, in FA-mutant head and neck cancers.

Objectives/Goals: Failure to achieve recruitment goals results in termination of ~20% of clinical trials and delays >85% of trial timelines. We aim to develop an electronic heath record (EHR)-based recruitment tool to ease identification of participants. We sought to determine whether criteria listed on clinicaltrials.gov could support selection of tool variables. Methods/Study Population: To inform the variables to include in the EHR-based recruitment tool, we data scraped clinicaltrials.gov to identify key inclusion and exclusion criteria common across a variety of diabetes clinical trials. We included actively recruiting or recently active phase 2 and 3 clinical trials of adults aged >18 years of age in the USA. We classified identified variables as clinically relevant or not and compared clinically relevant terms with inclusion and exclusion criteria (~20 variables) that were individually identified by three diabetes clinical trialists and two clinical research coordinators (CRCs). Results/Anticipated Results: We reviewed 203 clinical trials listed on clinicaltrials.gov. We identified 115 terms, 91 of which were clinically relevant. Three of 3 clinical trialists, 1 of 2 CRCs, and all trials listed age as a key variable. Consistent with data scraping, all trialists and CRCs identified glucose-lowering medications and kidney function as important criteria. Gender, ethnicity, and race were less commonly noted on clinicaltrials.gov and listed by 2 of 3 trialists and one CRC. Cardiovascular conditions (e.g., history of myocardial infarction), thyroid function tests, and contraceptive requirements were common criteria on clinicaltrials.gov, but only one trialist and one CRC identified these variables. Active infections (e.g., HIV) and c-peptide were not highlighted by trialists or CRCs but common on clinicaltrials.gov. Discussion/Significance of Impact: An EHR-based recruitment tool may facilitate identification of trial participants, but identifying key variables to include is essential. We found that data scraping for variables on clinicaltrials.gov mostly aligned with expert opinion, suggesting that automating variable selection via extraction from clinicaltrials.gov may be acceptable.

Objectives/Goals: The UCLA Clinical and Translational Science Institute (CTSI) training programs have been optimized by clinical research experts since 2013. They inculcate an interest in clinical and translational research careers. The acquisition of new skillsets and early exposure to potential career opportunities often influence lifetime decision-making. Methods/Study Population: The first program, in 2013, was the CTSI Research Associates Program (CTSI-RAP), which exposes undergraduate students to clinical research opportunities. RAP students are now mentoring high school students in the Mentoring and Advocacy in Teaching Clinical and Health-Related Research (MATCH) program. The Fiat Lux seminar is a research course designed to allow freshman students to explore diverse interests. The Leveraging Amazing Undergraduates in Clinical Research at UCLA Health (LAUNCH) program continues the workforce development pipeline by recruiting and training recent graduates to enter clinical research study coordinator careers. Each of these programs has their own stellar track records in terms of high interest and satisfaction and are assessed by annual evaluations from stakeholders. Results/Anticipated Results: CTSI-RAP is in its 11th year and a recent 10-year impact survey demonstrated the value of the program to students and their career decision-making especially those who are underserved and/or disadvantaged. The MATCH program arose from the interest of RAP students to mentor STEM high school students from local disadvantaged schools and is now in its 4th year across the state. The Fiat Lux freshman seminar began with a clinical research essentials emphasis, followed by an FDA/regulatory focus, and is now evolving to highlighting specific innovative areas of research with this year’s course spotlighting Cellular & Gene Therapy/Regenerative Medicine. LAUNCH is now in its third year, having been inspired by graduating RAP students wishing to continue in clinical research and feedback from their own focus groups. Discussion/Significance of Impact: The UCLA CTSI has supported these highly successful workforce development pipeline programs, which have had a demonstrated impact on students and the overall institutional clinical research infrastructure. Their stellar reputations generate high interest at UCLA and serve as model programs for implementation at other academic medical centers.

Objectives/Goals: The impact of the program on alumni students was measured in a 2023 survey, which assessed key factors and student perspectives on motivation to apply/remain in the program, their engagement activities, how they used the skills acquired in RAP upon graduating, and if they were currently serving in a health profession and/or clinical research. Methods/Study Population: Survey questions were based upon specific components of CTSI-RAP that make it unique. Covered topics related to motivation for participation, meaningful experiences, program effectiveness, future use of RAP knowledge/training, and current career roles in the health professions and/or clinical research. The survey was built and analyzed in REDCap and deployed May–July 2023. The study received exempt certification from the IRB. The survey was sent to 123 alumni from the 2013 to 2021 cohorts. Bounced e-mails were followed up on and two reminder e-mails were sent to initial non-responders. Identifiable demographic information was separated from program evaluation questions for analysis. A subanalysis was performed to determine program impact on students who identified as underserved or disadvantaged. Results/Anticipated Results: Respondents included 82/123 (66.7%) alumni. The survey took approximately 15 minutes. Most of the students 64/82 (78.0%) had 1 year or less research experience. The top three motivating factors for joining the RAP program were gaining clinical research experience, exposure to healthcare settings, and interest in pursuing a healthcare related career. Most alumni rated the overall effectiveness of the RAP program as very or somewhat valuable and the majority felt that the program ranked high or very high among their undergraduate experiences. The program was very influential or influential in defining their long-term plans and goals. Just under half felt that their career aspirations were changed or influenced by the program, which was especially true for those who identified as underserved/disadvantaged. Discussion/Significance of Impact: CTSI-RAP alumni highly value their experience in the program. They have benefitted professionally and are motivated to keep their connection to the program alive. With a decade of clinical research excellence and programming, CTSI-RAP’s impact is well established as a proven model benefiting both students and the clinical research infrastructure.

Objectives/Goals: Highlight the importance of community engagement: Showcase how the involvement of Promotoras de Salud is critical for fostering trust and encouraging participation in clinical trials. Cultural relevance and adaptation: Underline the importance of cultural and contextual relevance in developing and refining clinical research tools. Methods/Study Population: The theater test, an interactive evaluation approach akin to a dress rehearsal in theater, was conducted with approximately 60 Promotoras de Salud at a community center near the US-Mexico border. The Promotoras were divided into four groups, each focusing on one domain of the toolkit and facilitated discussions provided critical feedback on the materials and methods. A community engagement liaison with the University of New Mexico Health Sciences Center played a key role in introducing the EXPLORE team to these community leaders, leveraging long-standing relationships that predate this project. Results/Anticipated Results: Post-testing evaluations showed that 97% of the Promotoras were likely to encourage clinical trials in their communities, and 86% saw significant benefits for their community members. The Promotoras provided key insights and recommendations to enhance the toolkit’s cultural and contextual relevance. The community engagement liaison created a bilingual infographic to share these insights, which was presented at a Promotoras meeting, fostering meaningful discussion about clinical trials. Discussion/Significance of Impact: This project underscores the importance of community voices in research, transforming feedback into actionable insights for public health. Engaging Promotoras through theater testing validated the EXPLORE Toolkit and strengthened ties between clinical research and communities impacted by the opioid crisis.

Objectives/Goals: Our research goal is to translate medical guidelines for adolescent-centered contraceptive counseling into improved clinical practice. Here, we describe the process of co-designing a training program for adolescent-serving primary care clinicians with teen, caregiver, and clinician advisory boards. Methods/Study Population: We recruited teens, caregivers, and clinicians residing in North Carolina to participate in three virtual advisory boards separated by role. Eligible teen advisors were assigned female at birth and 15–19 years old; eligible clinicians provided care for teen patients; and all groups were purposively sampled to reflect diverse identities and experiences. At each advisor meeting, we used human-centered design techniques to elicit participant priorities, generate training content and engagement strategies, and obtain feedback on the final training program. We conducted a focus group at our final meetings and used rapid qualitative analysis to understand our advisors’ experiences participating in program co-development. Results/Anticipated Results: We partnered with 20 advisors with diverse identities across geographic location, race and ethnicity, sexuality, and experiences with disability. During 15 meetings from January to May 2024 (five with each advisor group), we developed a 3-hour virtual, synchronous training for adolescent-serving primary care providers to improve their contraceptive counseling skills. The curriculum includes five interactive modules and a resource toolkit. Advisors described motivations to participate (e.g., chance to share their perspective, desire to make change), positive experiences with the advisory boards (e.g., opportunities to learn, to connect with others), and opportunities for improvement (e.g., better technology orientation). Discussion/Significance of Impact: We describe developing a successful longitudinal partnership with three community advisory boards and co-creating a training program that incorporates community-led priorities and perspectives, including youth. This approach can be adapted for other clinician training programs seeking to center community voices.

Objectives/Goals: People experiencing homelessness (PEH) face excess cervical cancer burden and unique barriers to screening. As part of a broader study addressing cervical cancer disparities in homeless populations in Indiana, our goal was to engage unhoused women in a human-centered design process to inform a homeless shelter-based self-sampling intervention. Methods/Study Population: An established community-academic partnership enabled meaningful engagement of homeless communities in Indiana and informed the need to understand and address cervical cancer disparities in this population. Rapid assessment surveys (n = 202) and in-depth interviews (n = 30) were conducted with PEH at two major shelters in Indianapolis and Lafayette to understand cervical cancer screening coverage, knowledge, attitudes, and practices; barriers and facilitators; and acceptability of human papillomavirus (HPV) self-sampling for onsite shelter-based screening. A human-centered design session with (n = 12) unhoused women further explored motivators and concerns regarding self-sampling and informed key messages and informational materials to encourage uptake of screening. Results/Anticipated Results: At least 37% were overdue for screening (last screened >5 years ago; 50% were last screened >3 years ago), far greater than national (22%) or state (24%) averages. Despite common misconceptions regarding indifference toward preventive healthcare among homeless populations, most (87%) wanted to be screened and believed it is important for their health. Competing priorities for daily survival, transportation, cost, provider mistrust, stigma, and related trauma were common barriers to screening. Enthusiasm for HPV self-sampling centered on convenience, privacy, and comfort in taking one’s own sample at the shelter. Notable concerns included lack of confidence regarding ability to self-sample correctly, unhygienic conditions in shelter restrooms, preference to be seen by a doctor, and the need for education. Discussion/Significance of Impact: The unique challenges of PEH require human-centered strategies to improve cervical cancer screening access. Willingness to be screened and acceptability of HPV self-sampling is high. Identified concerns and preferences will guide implementation of HPV self-sampling delivered by trusted community health workers in homeless shelters in Indiana.

Objectives/Goals: 1. Examine structural, interpersonal, and health system factors that impact postpartum well-being for people who are racialized Black. 2. Differentiate components of postpartum well-being. 3. Design a model of postpartum care that addresses comprehensive well-being. Methods/Study Population: We conducted eight focus groups with participants in the Washington, D.C. area including four with Black birthing people who had given birth in the past two years (n = 23), and four with staff and providers from Community of Hope, a federally qualified health center, who provide care to birthing people (n = 19). We used an action-oriented qualitative approach informed by Black feminist theory. Our analysis was grounded in the 5D Cycle for Health Equity (reDefine, Discover, Dream, Design, and Deliver) and appreciative inquiry, which guide researchers to focus on strengths, be open to possibility, and engage radical imagination. Results/Anticipated Results: Participants reDefined postpartum health and wellness as physical, mental and social well-being, and material stability. Participants discovered that Black birthing people felt deeply unsupported navigating postpartum including difficulties with feeding, sleep, and mood and strongly believed that “postpartum” is at least a year, with different needs at different phases. Participants dreamed that postpartum care could be more accessible and trustworthy, have opportunities for social connection and creating a village, and have their basic needs (food, housing, clothing, and rest) met. Discussion/Significance of Impact: The participants’ conveyed that postpartum care must be designed and delivered to ensure that it is accessible, creates opportunities for connection, and promotes health, well-being, and joy. Postpartum care that can generate trust and engagement with healthcare, reduce morbidity and mortality, and increase thriving.

Objectives/Goals: Retention in care is vital for people living with HIV. We used human-centered design (HCD) to engage a community-based research panel over a 5-year period, allowing us to incorporate their insights on research guidance and interpretation of findings to investigate correlates of HIV care outcomes. Methods/Study Population: We recruited a diverse panel of individuals who were living with HIV, HIV clinicians, and/or providing non-clinical HIV services in Marion County, Indiana. We conducted biannual sessions using a variety of HCD tools and activities to engage participants. Each session took about three hours, and panelists were compensated for their participation. Due to the COVID-19 pandemic, sessions were initially held virtually. Sessions were designed for project discussion and to facilitate exploration of concerns and challenges facing receipt of HIV services. Our HCD approach put participants in the center of discussion and empowered them to externalize ideas and collaborate meaningfully with our team. Results/Anticipated Results: Since project inception, 48 individuals have joined the panel. Thirty-five are actively engaged, participating in one or more of six sessions conducted to date. We have learned much from the panel. One example is that a residential move might be a risk or protective factor for retention in care and the amount of time one had lived with HIV is a crucial factor. Panel insights have helped guide and prioritize analyses, aided in identification of data missing from our ecosystem, helped interpret results, provided feedback on future interventions, led to a quality improvement project with the local health department, and led to a presentation at a local health equity conference. Discussion/Significance of Impact: Community engagement is essential to impactful and sustainable research. HCD was a successful approach to engage our panel to inform interventions more relevant to the community. We anticipate these methods will be important for others conducting community-engaged research.

Objectives/Goals: Kentucky (KY) is a high priority ending the HIV epidemic state, with high rates of new HIV diagnoses tied to injection drug use. The overall goal of this pilot is to launch sentinel surveillance of bloodborne infections and drug compounds among people who inject drugs (PWID) to monitor trends in near-real time and inform rapid community response. Methods/Study Population: In collaboration with the Clark County, KY, syringe service program (SSP), the pilot study involves two 1-month waves of data collection: enrolling eligible SSP participants and conducting anonymous behavioral surveys, collection of participants’ syringes, laboratory testing of syringes to detect HIV and hepatitis C (HCV), drug residue testing through National Institute of Standards and Technology, and statistical modeling approaches to produce outputs of bloodborne infection and drug detection. Syringes are tested from each enrolled individual for: 1) HIV antibody; 2) HCV antibody; 3) HIV and HCV PCR; 4) HIV antigen; and 5) drug residue. Collaboration with community and PWID stakeholders will identify optimal messaging for reporting results. Results/Anticipated Results: The first wave community-facing pilot was conducted in September–October 2024. 29 survey responses were obtained; median age of the sample is 42 years, 55.2% are gender female; 37.9% reported unstable housing in the past week. Primary drugs of injection reported via survey in the prior month were methamphetamine (62.1%), heroin (13.8%), fentanyl (13.8%), buprenorphine (10.3%), meth and fentanyl in combination (3.4%). PWID reported returning 900 used syringes and a median of 15 per participant visit. At most recent testing, 69.0% reported a positive HCV test; 0% reported a positive HIV test. Some level of drug checking with fentanyl test strips in past month was reported by 51.7%. Initially, 20 syringes were tested for drug compounds; results are pending. HIV and HCV detection testing will be completed by early 2025. Discussion/Significance of Impact: Early results document proof of concept for our sentinel surveillance study; all individuals screened were willing to participate in surveys and syringe collection. New methods to identify risk for disease outbreaks and emerging drugs can inform rapid allocation of prevention resources at a community level, especially where testing is infrequent.

Objectives/Goals: The goal of this proposal is to better understand how informing African Americans of their genetic risk affects their behavior as part of a cardiovascular disease (CVD) risk reduction intervention. Aim 1: To determine the effect of genetic risk knowledge on CVD health behavior. Aim 2: To determine the effect of genetic risk knowledge on secondary variables. Methods/Study Population: Method: Fifty participants from the Baton Rouge metropolitan area will be recruited. Participants must be African American adults over the age of 18. Potential participants will be recruited using community-based efforts that have been successful in recruiting this population specifically. Participants will be randomized into one of two groups. Genetically Unblinded Group (GU) will be “genetically unblinded” after baseline orientation. Genetically Blinded Group (GB) will be “genetically blinded” until the end of the study. This study design ensures that we can measure the impact of knowledge of genetic risk on participant behavior. Results/Anticipated Results: Baseline participants’ characteristics (body mass index, blood glucose, and cholesterol) will be summarized by intervention group, with counts and percentages for categorical variables and means and 95% confidence intervals for continuous variables. Primary Outcomes: Attendance in intervention sessions will be counted across groups. Effect on genetic risk knowledge will be determined via comparing the difference between the increased healthy lifestyle behaviors at endpoint between Genetically Unblinded (Cases) and Genetically Blinded Groups (Control). Secondary and Tertiary Outcomes: Mean change in secondary outcomes in the GU group will be compared against the mean change in the GB group. Participant’s survey responses and changes in physical measurement from baseline to endpoint will be observed. Discussion/Significance of Impact: This study empowers African Americans in Baton Rouge by providing genetic risk knowledge for cardiovascular disease. By addressing social determinants of health, it promotes behavior change, improves health outcomes, and fosters trust, potentially reducing health disparities and advancing health equity.

Objectives/Goals: To create, train, and evaluate the FAST-PACE (Promoting Academic and Community Engagement) Toolkit that catalyzes academic-community translation science teams during a public health emergency. The toolkit is a road map based on the Research Readiness and Partnership Protocol (R2P2), which was developed from the Flint Water Crisis. Methods/Study Population: A literature review was conducted by the Michigan Institute for Clinical & Health Research Community Engagement (MICHR CE) program and the Community-Based Organization Partners (CBOP), to identify important and common elements in disaster response protocols with a set of key interviews (n = 31) to glean perspectives from community leaders. Key findings were extracted and reviewed to generate guidelines and recommendations for the R2P2 protocol. The co-developed FAST-PACE Toolkit launched its expansion statewide to address emergencies and health disparities of communities in crisis. The iterative process consisted of community report-outs, gathering input from stakeholders, via discussion, and evaluation surveys. The feedback was used to develop, enhance, and tailor the toolkit and training content. Results/Anticipated Results: Data from training (n = 8) of the critical elements of the FAST-PACE Toolkit, which provides guidance for academic and community team members that includes 1) assessing community assets and needs; 2) engaging in clear and bidirectional communication; 3) facilitating transparency and equitable partnering; 4) identifying health equity and justice issues; and 5) conducting the evaluation of research. The training will be disseminated in-person and virtually across the state of Michigan resulting in participants sharing community-identified health issues and social determinants of health to assist MICHR CE to suggest resources to address health impacts. Discussion/Significance of Impact: The FAST-PACE Toolkit borne from the flint water crisis and confounded by other crises used CEnR principles to create a translation science roadmap. It equips communities and collaborating academic institutions across the state to respond to public health crises and fosters equitable translation science partnerships built on respect and trust.

Objectives/Goals: This study evaluates the role of visual machine learning algorithms (VMLA) in automating a predictive model of central sarcopenia in geriatric trauma patients based on the psoas:lumbar vertebral index (PLVI) and trauma-specific frailty index (TSFI). Methods/Study Population: 150 trauma patients seen at Jon Michael Moore Trauma Center within J.W Ruby Memorial Hospital in rural West Virginia were included in this investigation across the life spectrum. The VMLA was trained on their standard of care trauma panoramic CT scans. Five expert reviewers segmented bilateral psoas muscles and the L4 vertebrae of each CT image at one slice inferior to the posterior elements of the L4 vertebrae. The data were read into a U-net convoluted neural network as ground truth. Labels were preprocessed to focus on the regions of interest and standardized into four classes: right psoas, left psoas, L4 vertebrae, and background. Performance was evaluated using accuracy, Dice coefficient, and F1 score. Results/Anticipated Results: Between our expert reviewer segmentations, we had significant inter-reader reliability with a Kappa greater than 0.8 and a mean standard deviation of the PLVI of 0.10mm^2. Preliminary VMLA testing on a subset of 70 patients yielded a validation accuracy of 88.5%, a Dice coefficient of 0.86, and an F1 score of 0.87 after 20 epochs. There was a moderate interclass correlation between PLVI and TSFI even though the TSFI lacks sensitivity. In fact, the PLVI is a more accurate predictor of frailty in trauma patients based on various outcome measures such as corrected length of stay. Our ongoing efforts are centered around improving the VMLA. Discussion/Significance of Impact: Our VMLA outperforms the current clinical standard, TSFI. Integration of our VMLA into the clinical workflow has the potential to revolutionize geriatric trauma care by providing rapid, accurate, identification of high-risk frail patients.

Objectives/Goals: In recent years, there has been growing interest in the development of air pollution prediction models, particularly in low- and middle-income countries that are disproportionately impacted by the effects of air pollution. Recent methodological advancements, particularly in machine learning, provide novel opportunities for modeling efforts. Methods/Study Population: We estimate daily ground-level fine particulate matter (PM2.5) concentrations in the Mexico City Metropolitan Area at 1-km2 grids from 2005 to 2023 using a multistage approach. Spatial and temporal predictor variables include data from the moderate resolution imaging spectroradiometer (MODIS), Copernicus Atmosphere Monitoring Service (CAMS), and additional meteorological and land use variables. We employed machine-learning-based approaches (random forest and gradient boosting algorithms) to downscale satellite measurements and incorporate local sources, then utilized a generalized additive model (GAM) to geographically weight predictions from the initial models. Model performance was evaluated using 10-fold cross-validation. Results/Anticipated Results: On average, the random forest, gradient boosting, and GAM models explained 75, 82, and 83% of variations measured in PM2.5 concentrations. PM2.5 levels were generally higher in densely populated urban centers and lower in suburban and rural areas. Important predictors of ground-level PM2.5 included wind (both u and v components), 2-meter mean air temperature, elevation, and the normalized difference vegetation index (NDVI). Discussion/Significance of Impact: Using novel machine learning-based approaches, we developed robust models with fine-scale spatial (1-km2) and temporal (daily) variations of PM2.5 in Mexico City from 2005 to 2023. The predicted PM2.5 concentrations can further advance public health research on air pollution in Mexico City and beyond.

Objectives/Goals: Idiopathic inflammatory myopathies (IIMs) are autoimmune diseases influenced by genetic and environmental factors. This study aims to explore infection patterns preceding IIM onset by applying temporal data mining and machine learning to deidentified patient records and corroborate results from molecular analysis. Methods/Study Population: The dataset used in this work was extracted from TriNetX with a focus on patients who have IIM. Risks for developing the outcomes were assessed using case–control cohorts. For each participant, information was extracted about diagnosis code, date of infection, and study visit in which the infection was reported. This data were then temporally encoded and used to generate sequence files for each of the outcomes. Unsupervised temporal machine learning was then preformed on these files to detect frequent subsequences of infections. Python library scikit-learn was used to perform the unsupervised machine learning with k-means clustering. Results/Anticipated Results: The results of this study identify infections associated with the onset of IIM by analyzing temporal infection patterns. Frequent sequences of infections uncovered, with specific patterns linked to different cohorts, offer insights into the etiology of IIM. Common and cohort-specific infection sequences will help validate existing research and provide new avenues for exploring the disease mechanisms. The findings will highlight significant infection patterns, which will inform our understanding of IIM onset across various patient populations. Discussion/Significance of Impact: The results will provide key insights into pre-symptomatic infection sequences related to IIM onset, enhancing understanding of its etiology and pathogenesis. These findings may aid in developing more precise screening methods for early detection and confirm previous results from analyzing immune signatures of infections in IIM.

Objectives/Goals: The objective of this study is to explore strategies for AI-physician collaboration in diagnosing acute respiratory distress syndrome (ARDS) using chest X-rays. By comparing the diagnostic accuracy of different AI deployment methods, the study aims to identify optimal strategies that leverage both AI and physician expertise to improve outcomes. Methods/Study Population: The study analyzed 414 frontal chest X-rays from 115 patients hospitalized between August 15 and October 2, 2017, at the University of Michigan. Each X-ray was reviewed by six physicians for ARDS presence and diagnostic confidence. We developed a deep learning AI model for detecting ARDS and explored the strengths, weaknesses, and blind spots of both physicians and AI systems to inform optimal system deployment. We then investigated several AI-physician collaboration strategies, including: 1) AI-aided physician: physicians interpret chest X-rays first and defer to the AI model if uncertain, 2) physician-aided AI: the AI model interprets chest X-rays first and defers to a physician if uncertain, and 3) AI model and physician interpreting chest X-rays separately and then averaging their interpretations. Results/Anticipated Results: While the AI model (84.7% accuracy) had higher accuracy than physicians (80.8%), we found evidence that AI and physician expertise are complementary. When physicians lacked confidence in a chest X-ray’s interpretation, the AI model had higher accuracy. Conversely, in cases of AI uncertainty, physicians were more accurate. The AI excelled with easier cases, while physicians were better with difficult cases, defined as those where at least two physicians disagreed with the majority label. Collaboration strategies tested include AI-aided physician (82.4%), physician-aided AI (86.9%), and averaging interpretations (86%). The physician-aided AI approach had the highest accuracy, could off-load the human expert workload on the reading of up to 79% chest X-rays, allowing physicians to focus on challenging cases. Discussion/Significance of Impact: This study shows AI and physicians complement each other in ARDS diagnosis, improving accuracy when combined. A physician-aided AI strategy, where the AI defers to physicians when uncertain, proved most effective. Implementing AI-physician collaborations in clinical settings could enhance ARDS care, especially in low-resource environments.

Objectives/Goals: This study aimed to enhance clinical trial data management through large language model information retrieval and generation techniques within the clinical trial reporting workflow. We focused on improving compliance with reporting, reducing human labor, and promoting standardized reporting structure and data quality oversight. Methods/Study Population: We used approved study protocols from UC Davis IRB-approved investigator-initiated studies compared to the same studies reported to ClinicalTrials.gov. Our baseline data extraction system employs commercial large language models (LLMs) and retrieval augmented generation (RAG) to isolate data sources within the secure extraction environment. We stratified protocol documents into easy, complex, and random categories based on study focus, document complexity, the extent of amendments or modifications, and completion metrics from ClinicalTrials.gov. We developed a pilot web-based architecture to capture variations in categorization, labeling, and reporting style and compared generated extraction data. We primarily focused on qualitative evaluation through a review of expert staff. Results/Anticipated Results: Our results revealed significant variations in reporting quality, with dependencies stemming from multiple authors and stages throughout the clinical trial protocol lifecycle. Based on these variations, we used prompt engineering to improve the pilot application’s output compliance with the protocol registration and results system (PRS) structured data format for various study types. We piloted the assisted workflow with prospective studies by partnering with study investigators and the clinical trial office staff to assist in review and clinical trial reporting creation. Initial studies reported by our system were approved and released to the public by PRS staff. We are refining content generation and workflows to different components of studies and evaluating their use in quality and training areas. Discussion/Significance of Impact: Our system fosters collaboration, efficient review, and compliance with clinical trial reporting standards. It supports the promise of AI-driven assistance in clinical trial management, design, and reporting. We focus on the multiple stakeholders, expertise, and data flows in the organizational management of clinical and translational science.

Objectives/Goals: Magnetic resonance imaging (MRI) reports are stored as unstructured text in the electronic health record (EHR), rendering the data inaccessible. Large language models (LLM) are a new tool for analyzing and generating unstructured text. We aimed to evaluate how well an LLM extracts data from MRI reports compared to manually abstracted data. Methods/Study Population: The University of California, San Francisco has deployed a HIPAA-compliant internal LLM tool utilizing GPT-4 technology and approved for PHI use. We developed a detailed prompt instructing the LLM to extract data elements from prostate MRI reports and to output the results in a structured, computer-readable format. A data pipeline was built using the OpenAI Application Programming Interface (API) to automatically extract distinct data elements from the MRI report that are important in prostate cancer care. Each prompt was executed five times and data were compared with the modal responses to determine variability of responses. Accuracy was also assessed. Results/Anticipated Results: Across 424 prostate MRI reports, GPT-4 response accuracy was consistently above 95% for most parameters. Individual field accuracies were 98.3% (96.3–99.3%) for PSA density, 97.4% (95.4–98.7%) for extracapsular extension, 98.1% (96.3–99.2%) for TNM Stage, had an overall median of 98.1% (96.3–99.2%), a mean of 97.2% (95.2–98.3%), and a range of 99.8% (98.7–100.0%) to 87.7% (84.2–90.7%). Response variability over five repeated runs ranged from 0.14% to 3.61%, differed based on the data element extracted (p Discussion/Significance of Impact: GPT-4 was highly accurate in extracting data points from prostate cancer MRI reports with low upfront programming requirements. This represents an effective tool to expedite medical data extraction for clinical and research use cases.