Objectives/Goals: Citizen Science (CS) recognizes the vital role that community members play in research, centering their unique lived experiences and perspectives across the research cycle. We aim to enhance community-engaged research (CEnR) by adapting a CS Program at the University of Illinois Chicago (UIC) Center for Clinical and Translational Science (CCTS). Methods/Study Population: The CS Program, launched in response to COVID-19, was designed/piloted for Chicago community members interested in research careers, developing evidence-based practice skills, and/or partnering with academic, community, and/or public health organizations. To inform program adaptation, we are conducting a landscape assessment, including 1) inventory/annotation of existing curricular materials, 2) review of peer-reviewed literature, 3) website extraction of existing CS programs’ key components, and 4) interviewing key informants. An Advisory Board of prior CS instructors/alumni will guide curriculum adaptation, coordination, and fidelity. We will also identify strategic internal/external UIC organizational partnerships to collaborate on establishing, developing, and conducting the program. Results/Anticipated Results: Literature describes common CS program typology as a continuum, from research done “with the people” to research conducted “by the people” (King et al, 2016). Our program will equip CS to engage across these conceptual continuums. We plan to launch the UIC CCTS CS Program by Fall 2025 and have 10 online modules with a disability justice lens. Topics will range from Critical Thinking and the Research Process to Structural Violence and Evaluation Frameworks. Grounded in liberatory pedagogy, sessions will be taught by UIC faculty, staff, and community partners, each containing a lecture, interactive activities, and assessments. Participants will earn a certificate applicable to related jobs (e.g., academic/community research), supplement community health worker training, precursor to health degrees, and more. Discussion/Significance of Impact: Through the CS Program, we aim to center community expertise and lived experience within research, foster bi-directional collaborations and relationships, and build community capacity. We are evaluating this project adaptation and implementation to create a blueprint for institutions to enhance their community-engaged research.

Objectives/Goals: A sample of 1,073 hypertensive adults in Bangladesh showed unusually high rates of hypokalemia. We analyzed sociodemographic and clinical factors – including age, sex, weight, body mass index, blood pressure, creatinine clearance, and urine protein concentration – to identify key predictors of hypokalemia. Methods/Study Population: A cross-sectional analysis was conducted on 1,073 hypertensive adults from the OK study in Dhaka, Bangladesh (2022–2023). Hypertension was defined as blood pressure >140/90 mmHg, and none of the participants were on any antihypertensive medication prior to the study. Hypokalemia was defined as serum potassium Results/Anticipated Results: The prevalence of hypokalemia was 21.5%. In univariate analysis, age (OR 0.975, 95% CI [0.959, 0.990], p  =  0.00189), systolic blood pressure (OR 1.02, 95% CI [1.00, 1.03], p  =  0.00568) and diastolic blood pressure (OR 1.03, 95% CI [1.01, 1.04], p  =  0.000272) were significantly associated with hypokalemia. In multivariate analysis, age (OR 0.961, 95% CI [0.936, 0.985], p  =  0.00167) remained significant, and creatinine clearance (OR 0.986, 95% CI [0.974, 0.999], p  =  0.0386) became significant. BMI, weight, systolic and diastolic blood pressure, sex, and urine protein concentration were not significant. Discussion/Significance of Impact: In the multivariate analysis, age and creatinine clearance was statistically significant; however, their effect sizes were small and unlikely to be clinically meaningful. The underlying reasons for the high prevalence of hypokalemia in this population remain unclear, warranting further investigation to identify contributing factors.

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: We assessed the feasibility of using a large language model (LLM) to create lay language descriptions of study protocols for recruitment, which has the potential to improve accessibility and transparency of clinical studies and enable participants to make informed decisions. Methods/Study Population: All studies from a clinical research recruitment platform were included, which features human-written lay descriptions and titles for study recruitment. Corresponding protocol summaries in the IRB system were extracted and translated into lay language using a LLM (gpt-35-turbo-0613). A subset was used to develop prompt variations through an iterative process. Prompt strategies evaluated include chain-of-thought and few-shot prompting techniques. LLM-generated and human-written descriptions were compared for readability using Flesch–Kincaid and Simple Measure of Gobbledygook (SMOG) reading grade levels and information completeness using Word Movers’ Distance (WMD). Results/Anticipated Results: A total of 55 study descriptions were included – 10 were used to develop prompts and 45 were used for evaluation. The final LLM instructions included multistep prompts. The LLM was first instructed to produce a two- to three-sentence long description without using scientific jargon and included two pairs of examples. The LLM was then asked to shorten the description and finally to provide an engaging title. LLM-generated and human-written summaries were similar in length (median (IQR) 328 (278.5–360.5) vs. 342 (203–532.5) characters, respectively). LLM-generated summaries had lower Flesch-Kincaid grade level (5.15 vs. 8.28, p Discussion/Significance of Impact: An LLM can be used to generate lay language summaries that are readable at a lower grade level while maintaining semantic similarity. This approach can be used to improve the drafting of summaries for recruitment, thereby improving accessibility to potential participants. Future work includes human evaluation and implementation into practice.

Objectives/Goals: To identify the genomic mechanisms underlying cross-species regulation of longevity among mammals and birds and to characterize the impact of those conserved pathways on human aging. More broadly, this study aims to develop a novel evolutionary approach to understand the genetics of complex traits. Methods/Study Population: High-quality genome sequences for 194 bird species and 295 mammal species with reliable longevity and body size data were obtained from publicly available resources. The data include coding sequence alignments of 16,863 mammalian and 14,565 avian one-to-one orthologous genes. Gene-wise relative evolutionary rates (RERConverge) and maximum likelihood phylogenetics (PAML) were computed to assess for evidence of purifying selection and positive selection for longevity. As part of ongoing analysis, human orthologs of selected results will be examined in the UK Biobank for validation. Results/Anticipated Results: Preliminarily, we have found a signal of concordant positive selection between two classes of vertebrates separated by hundreds of millions of years. Several genes show signals of positive selection in long-lived species of both birds and mammals. Ongoing work focuses on elucidating the relationship between relative evolutionary rates and positive selection, the overlap in selection signature between long-lived animals with large body sizes and those who are exceptionally long lived for their body size, and further elaborating on convergence between mammals and birds. Discussion/Significance of Impact: Currently, most scientific knowledge about aging is from experiments on short-lived model organisms. By systematically studying the genomes of long-lived mammals and birds, we aim to develop a new method for studying complex traits and uncover novel insights into the mechanisms of longevity.

Objectives/Goals: The clinical research professional (CRP) workforce suffers from high turnover. Stay interviews have led to increased satisfaction and reduced turnover in other industries. We describe a multi-institutional project to develop, disseminate, and evaluate a CRP-tailored Stay Interview tool reimagined as the Individual Retention Conversation (IRC) toolkit. Methods/Study Population: In August 2022, following on the heels of a series of un-meeting conversations focused on CRP workforce development, the CRP taskforce initiated a working group to tackle issues related to CRP workforce retention. As a first initiative, this multi-institutional working group set out to develop, disseminate, and evaluate a Stay Interview tool tailored for a CRP audience and reimagined as the IRC toolkit. A 2-phase pilot study was initiated across six academic medical centers (AMCs: ASU, Duke, MUSC, UAB, UPenn, VCU) to: 1) optimize the toolkit for the CRP audience and 2) evaluate the impact of the toolkit using a standardized CRP satisfaction survey. Quantitative and qualitative data were collected via surveys using the REDCap platform. Results/Anticipated Results: The optimization phase of the pilot included 69 participants (16 managers and 53 of their CRP team members) from 6 AMCs. Respondents identified most and least useful questions for stimulating meaningful conversations regarding job satisfaction and retention issues with additional feedback on the IRC experience and tools. CRPs and managers represented a variety of roles, with 77% patient facing. The majority were satisfied with the IRC experience (82%) and found the experience personally beneficial (76%). Managers were satisfied with the manager’s guide (90%). Quantitative and qualitative feedback was used to optimize the toolkit prior to launch of phase 2 in September 2024, which includes a longitudinal survey-based assessment of CRP job satisfaction and IRC-consequent work environment changes. Discussion/Significance of Impact: CRP retention is impacted by complex factors, many related to job satisfaction, supervisor /employee relationships, and beneficial work environments. Initial evaluation of the IRC suggests that this intervention fosters positive supervisor/employee relationships and beneficial work environment changes, which may lead to improved retention.

Objectives/Goals: The bromodomain PHD finger transcription factor (BPTF) is an oncogenic driver of neuroblastoma. Our objective is to pioneer the discovery of the first class of chemical compounds that engage the PHD finger of BPTF and inhibit its biological function in cellulo, thereby establishing first-in-class chemical probes for this epigenetic reader. Methods/Study Population: Our previous work has identified a collection of small molecules that engage BPTF PHD in vitro. Following structure–activity relationships analysis, candidates will be used in a neuroblastoma cell model to validate BPTF PHD interaction in cellulo and predict therapeutic potential. Nanoluciferase bioluminescence resonance energy transfer (NanoBRET) will be used to confirm BPTF PHD engagement by compounds. Selective toxicity in neuroblastoma cells upon inhibitor treatment will be gauged by comparing cell growth and viability in the IMR-32 cell line against the HEK293 cell line. Treated HEK293 cells will be subjected to the assay for transposase-accessible chromatin (ATAC) and RNA sequencing methods to monitor changes in chromatin structure and transcriptional signatures against untreated cells. Results/Anticipated Results: We hypothesize that compounds with low micromolar potency for BPTF PHD in vitro will engage the target in cellulo and displace NanoLuciferase tagged protein from its HaloTagged® peptide binding partner. Additionally, we anticipate that our inhibitors will show cytotoxicity for IMR-32 cells with limited effects on HEK293 cells. We envision that inhibitor treatment in HEK293 cells will correlate with reduced chromatin exposure, suggesting that blocking the BPTF–histone interaction via PHD finger inhibition hinders the remodeling of transcriptionally silent heterochromatin into a transcriptionally active state. Finally, we expect that inhibitor treatment will result in diminished gene expression of oncogenic transcription factors, including N-Myc, a biomarker of neuroblastoma. Discussion/Significance of Impact: These first-in-class chemical probes for BPTF PHD will enable further investigation of BPTF and high-risk neuroblastoma progression, as well as its role in other diseases. In addition, these compounds will serve as a platform for the development of new anticancer agents that may improve outcomes for children that suffer from high-risk neuroblastoma.

Objectives/Goals: Predictive performance alone may not determine a model’s clinical utility. Neurobiological changes in obesity alter brain structures, but traditional voxel-based morphometry is limited to group-level analysis. We propose a probabilistic model with uncertainty heatmaps to improve interpretability and personalized prediction. Methods/Study Population: The data for this study are sourced from the Human Connectome Project (HCP), with approval from the Washington University in St. Louis Institutional Review Board. We preprocessed raw T1-weighted structural MRI scans from 525 patients using an automated pipeline. The dataset is divided into training (357 cases), calibration (63 cases), and testing (105 cases). Our probabilistic model is a convolutional neural network (CNN) with dropout regularization. It generates a prediction set containing high-probability correct predictions using conformal prediction techniques, which add an uncertainty layer to the CNN. Additionally, gradient-based localization mapping is employed to identify brain regions associated with low uncertainty cases. Results/Anticipated Results: The performance of the computational conformal model is evaluated using training and testing data with varying dropout rates from 0.1 to 0.5. The best results are achieved with a dropout rate of 0.5, yielding a fivefold cross-validated average precision of 72.19% and an F1-score of 70.66%. Additionally, the model provides probabilistic uncertainty quantification along with gradient-based localization maps that identify key brain regions, including the temporal lobe, putamen, caudate, and occipital lobe, relevant to obesity prediction. Comparisons with standard segmented brain atlases and existing literature highlight that our model’s uncertainty quantification mapping offers complementary evidence linking obesity to structural brain regions. Discussion/Significance of Impact: This research offers two significant advancements. First, it introduces a probabilistic model for predicting obesity from structural magnetic resonance imaging data, focusing on uncertainty quantification for reliable results. Second, it improves interpretability using localization maps to identify key brain regions linked to obesity.

Objectives/Goals: We designed a forum to educate participants about bioethical issues in the application of big data (BD) and artificial intelligence (AI) in clinical and translational research (CTR) in underrepresented populations. We sought to determine changes in participants’ interests in ethics, bias, and trustworthiness of AI and BD. Methods/Study Population: 141 individuals registered for the forum, which was advertised to our partner institutions, minority-serving institutions, and community organizations. Registrants received email instructions to complete an AI Trustworthiness (AI-Trust) survey, a questionnaire with integrated qualitative and quantitative measures designed to better understand learners who engaged with the institution-specific AI/Data Science curriculum. Respondents completed the survey using personal devices via a link and QR code, with anonymized responses and enhanced privacy features. 82 people attended; 22 responded to the survey pre-forum and 22 post-forum. Pre- and post-forum responses were qualitatively compared to assess shifts in attitudes toward AI and BD and related interests in ethics, bias, and trustworthiness. Results/Anticipated Results: We found increased interests post- vs. pre-forum in the use of AI for CTR, AI bias and its effects on underrepresented populations, and ethical risk assessment and mitigation strategies for the use of BD to empower research participants. In contrast, trust in AI was lower post- vs. pre-forum. Moreover, respondents also indicated that the current application of AI in healthcare practice would result in increased racial, economic, and gender bias. In comparison, interest in ethical challenges, bioethical considerations, and trustworthiness regarding use of BD and AI in health research and practice did not differ pre- vs. post-forum. Discussion/Significance of Impact: Interest in the application of BD/AI in CTR increased post-forum, but AI distrust and bias expectations also increased, suggesting that learners become more skeptical and discerning as they become more knowledgeable about the complexity of the ethics of AI and BD use in healthcare, especially its application to underrepresented populations.

Objectives/Goals: Large-scale tumor sequencing efforts have led to annotations of novel cancer hotspot mutations that may underlie driver or cooperative function. We have sought to define the molecular consequences of such hotspots associated with pediatric DICER1 syndrome cancers, with the ultimate goal of revealing novel targets that may inform new standards of care. Methods/Study Population: We have performed genomic analysis to identify tumor types (in TCGA and MSK-IMPACT patient data) for which mutations in the Dicer1 gene (encoding Dicer protein) emerge as the dominant signature of driver function. As Dicer is a critical RNA processing factor responsible for the generation of microRNAs, which are posttranscriptional gene regulatory molecules, we have modeled these mutations in human embryonic stem cells in order to study the direct effects on miRNAs and their target genes in an isogenic background. In addition to providing the required setting for unambiguous attribution of function to specific mutations, clonal human ES cells offer an opportunity for modeling of both developmental and cancer requirements associated with altered Dicer function. Results/Anticipated Results: Through generation of genomics and functional datasets from matched genotypes in Dicer mutated human ES cells, we have identified specific alterations in miRNAs and their effects on target genes. Unexpectedly, we found direct evidence for both loss of function and gain of function attributable to Dicer mutations. In addition, through integrated analysis of genomic data from tumor sequencing datasets and our human ES cell models, we have identified potential miRNA and target gene alterations that underlie tumorigenic potential, nominating gene candidates for targeted therapy in DICER1 syndrome. Direct mouse modeling of such candidate gene targets has revealed evidence for driver function of identified miRNA and their targets. Discussion/Significance of Impact: DICER1 syndrome cancers comprise a wide variety of rare pediatric tumor types. Presently, we still lack an effective standard of care. Furthermore, the previous lack of molecular profiling precluded targeted therapy opportunities. Our precise knock-in modeling of Dicer hotspots and deep profiling of relevant tumors now provide candidate targets.

Objectives/Goals: Digital recruitment can improve participant engagement in medical research, but its potential to introduce demographic and socioeconomic biases is unclear. This study investigates pathways participants took during a digital recruitment workflow in neurology, examining potential associations with socioeconomic and demographic factors. Methods/Study Population: As part of an ongoing study aiming to remotely capture speech from patients with neurologic disease, most participants seen in neurology on our campus are invited to complete a self-administered speech examination. We exported participant data from Epic (semi-automated identification and invitation), Qualtrics (eligibility screening), the participant tracking database (consent), and the recording platform (completion) for March to July 2024. Data visualization was performed using a Sankey diagram. Socioeconomic status was assessed using the housing-based socioeconomic status (HOUSES) index and area deprivation index (ADI) national rank. Kruskal–Wallis and Wilcoxon rank-sum tests were used to compare the median age, socioeconomic indices, and time taken to reach different steps of the study. Results/Anticipated Results: Of the 5846 invited participants, 57% were from urban areas, 23% from rural areas, and 20% from urban clusters. Most did not read/respond (2739) or declined (1749) the initial invitation via Epic. Of the 1358 interested participants, 415 completed the study. Participants from urban areas completed enrollment steps faster than those from rural areas and urban clusters, though the variance was large (42.6 ± 41.4 days vs. 50.6 ± 42.2 days and 50 ± 43.9 days, respectively; p  =  0.030). Female participants took longer to complete enrollment than males (48.7 ± 44 days vs. 40.5 ± 38.8 days; p  =  0.026). Participants who successfully finished the study had significantly lower ADI national ranks compared to other common pathways (40.6 ± 19; p  =  0.0021). No associations were found with the HOUSES indices. Discussion/Significance of Impact: Our findings support differences in participant engagement, with urban participants and males more likely to complete enrollment steps. Those who finished the study were less disadvantaged suggesting potential bias in digital recruitment. These findings can inform strategies to improve digital recruitment in neurology research.

Objectives/Goals: This study aims to harmonize quality indicators (QIs) across University of Toronto-affiliated microbiology labs to establish universal benchmarks that enhance performance, patient safety, and health outcomes. Harmonized QIs will enable effective comparisons and enhance the consistency of care. Methods/Study Population: The study employed the Delphi method, a structured and iterative process to build consensus. An expert panel of clinical microbiology trainees, medical microbiologists, trainees, and site leads from five University of Toronto-affiliated microbiology labs was assembled. Initial insights were gathered through surveys and a comprehensive scoping review of the literature. The study involved two rounds of feedback, a SurveyMonkey-based survey, with a defined consensus of 75% agreement among participants. Followed by an implementation survey conducted through REDCap to assess how these QIs were adopted in practice and identify barriers to implementation. Results/Anticipated Results: The study achieved consensus on nine high-impact quality indicators, including blood culture volume and contamination rates, cerebrospinal fluid transport time, and turnaround times for Gram stain results. Blood culture contamination and positivity rates garnered the highest agreement, at 100% and 91%, respectively. While some indicators were widely accepted and implemented, others faced resistance due to feasibility concerns. The study also identified significant variability in the level of adoption across the participating laboratories, pointing to operational challenges and the need for further efforts to address these barriers. Discussion/Significance of Impact: This study highlights the importance of QI harmonization in improving lab services and patient safety. It reveals challenges in standardizing practices but promotes uniformity in QIs, laying the groundwork for better inter-lab collaboration, consistent outcomes, and improvements in microbiology.

Objectives/Goals: Despite significant advancements, adolescent and young adult (AYA) patients with hematologic malignancies continue to have inferior improvement in survival over time compared to their younger and older peers. This project assesses which patient and neighborhood characteristics are associated with clinical trial enrollment in this population. Methods/Study Population: We will perform a retrospective study of individuals, aged 15–39, diagnosed and treated at Children’s Healthcare of Atlanta (CHOA) or Winship Cancer Institute for hematologic malignancies between 2011 and 2023. Our primary exposure variables will be race/ethnicity, the area deprivation index (ADI), and the index of concentration at the extremes (ICE). The primary study outcome will be enrollment in an open frontline therapeutic clinical trial (yes vs. no). Our analyses will estimate the crude and adjusted odds ratio of clinical trial enrollment according to race/ethnicity, ADI, and ICE; these analyses will be adjusted for co-variables of interest (e.g. patient primary language, and insurance provider). As a secondary analysis, we will further subdivide the patients by treatment location and by age tertiles. Results/Anticipated Results: Our study team completed preliminary work looking at institutional clinical trial enrollment in a pediatric-only (Discussion/Significance of Impact: We expect that this study conducted in a large, diverse AYA cohort will reveal key associations about likelihood of clinical trial enrollment. Once these associations are known, we can develop and test interventions –such as augmented social work involvement and assistance with transportation– to mitigate the effect of amenable risk factors.

Objectives/Goals: Global surgical education is largely driven by high-income countries (HICs), with curricula not tailored to the needs of low- and middle-income countries (LMICs). This study assessed country-specific needs for global surgical curricula and used generative AI to develop tailored curricula. Methods/Study Population: A curriculum framework was developed using expert opinion. Using a focused needs assessment survey, we evaluated international medical students’ and trainees’ needs for structured global surgery curricula, covering research, education, data and develop tailored curriculum templates for each country, ensuring alignment with the distinct needs of respective LMIC and HIC respondents. The AI-generated curricula were then compared across countries to identify variations in content and focus areas. Results/Anticipated Results: A total of 145 respondents from 18 countries and 6 continents participated, with 94 from LMICs and 51 from HICs. Four countries [Uganda (n = 31), Nigeria (n = 34), the USA (n = 23), and the UK (n = 23)] had more than 10 respondents, with the creation of a country specific global surgery curriculum. Curricula developed by HIC trainees focused on access to resources and infrastructure, future directions of global surgical research, and the role of medical students and early career development with a decreased focus on the history of global surgery. LMIC country-based curriculum focused on introducing the concepts of global surgery, quantifying the burden and epidemiology of surgical disease and had a greater emphasis on case studies and use cases, with decreased focus on resources and collaboration. Discussion/Significance of Impact: The research introduces a “precision education” approach that could help close the surgical education access gap globally. Further pilot and qualitative studies are necessary to validate the feasibility of AI-generated needs-based curricula.

Objectives/Goals: The study is designed to co-develop a genetics education digital platform with community participants. Diverse populations, especially African American communities, are less likely to participate in genetic testing and clinical trials. To increase participation and community input, we want community participants across Louisiana. Methods/Study Population: A cross-sectional, mixed-methods study will be conducted to assess interest in learning about genetics through a digital education platform and to adapt the platform based on participant feedback. Specific Aim 1 will be achieved by recruiting a diverse cohort and collecting demographic data to identify participants’ characteristics. For Specific Aim 2, 35 community participants will be enrolled as a co-design team to complete 5-week educational modules. Feedback from focus groups will guide iterative platform refinements, ensuring the platform is culturally tailored and user-friendly. Results/Anticipated Results: For Specific Aim 1, we anticipate that the majority of participants will express interest in learning about genetics through the digital platform, with demographic data revealing a diverse participant pool, predominantly from African American and Hispanic communities. For Specific Aim 2, we expect that all 35 co-design team members will complete the 5-week modules. Feedback from the focus groups is anticipated to highlight the need for more user-friendly navigation, culturally tailored content, and enhanced visuals. These insights will guide the refinement of the digital platform for improved engagement and accessibility. Discussion/Significance of Impact: This study addresses a critical translational barrier – underrepresentation of African descended communities in genetic testing. By developing a culturally tailored, digital platform to engage these populations, the project aims to reduce health disparities, enhance genetic literacy, and foster inclusivity in genomic research.

Objectives/Goals: Endometrial cancer is one of the few cancers that has both a rising incidence and mortality rate. Molecular classification is becoming more important for the management of endometrial cancer but the ability to translate this into clinical practice remains constrained. Our goal is to use AI to predict the molecular subtype from histopathology slides. Methods/Study Population: We utilized the open source endometrial cancer datasets from The Cancer Genome Atlas (TCGA) (N = 387) and Cancer Proteomics Transcriptomic Tumor Analysis Consortium (CPTAC) (N = 135) to develop and train a vision transformer AI model. We used a proprietary cohort of patients (N = 548) for external validation. Whole slide images (WSI) and molecular subtype data were collected. Subtypes include POLE ultramutated (POLE), microsatellite instability (MSI-H), copy-number low (CNV-L), and copy-number high (CNV-H). WSI were preprocessed, and features were extracted. Modified STAMP protocol was used in training, utilizing a pretrained foundation transformer model (Virchow2). Cross-validation of the TCGA was used for initial training, followed by testing on the CPTAC dataset and validation on our proprietary cohort. Results/Anticipated Results: Fivefold cross-validation of the TCGA database (60% training, 20% testing, and 20% validation) developed a best overall model with a mean AUC of 0.74 (POLE 0.78, MSI-H 0.76, CNV-H 0.86, CNV-L 0.77). Overall precision 0.58, recall 0.55. CNV-H was the subtype with the most accurate prediction. CPTAC holdout testing revealed moderately high AUC (POLE 0.63, MSI-H 0.62, CNV-H 0.98, and CNV-L 0.76). Overall precision 0.54 and recall 0.58. Again, CNV-H was the most accurate prediction. Validation on our proprietary cohort revealed a drop in performance with overall mixed results by AUC (POLE 0.50, MSI-H 0.69, CNV-H 0.78, and CNV-L 0.61). Overall precision 0.57, recall 0.45. Again, CNV-H with the most accurate prediction but F1 score dropped from 0.77 in the CPTAC to 0.47 on validation. POLE was the least accurate prediction subtype. Discussion/Significance of Impact: The CNV-H subtype demonstrated robust performance, suggesting the model effectively captures the features associated with this subtype. CNV-L had moderate performance. MSI-H and POLE were notably lower. WSI-based AI models show translational potential for subtype prediction in the management of endometrial cancer but more work is necessary.

Objectives/Goals: To evaluate equity in utilization of free initial health evaluation (IHE) services among members of a limited health care program, the World Trade Center (WTC) Health Program (Program), to inform intervention development and provide insights for similar healthcare programs. Methods/Study Population: We included Program members who newly enrolled during 2012–2022, and who had an IHE or were alive for ≥ 1 year after enrollment. Program administrative and surveillance data collected from January 2012 to February 2024 were used. We evaluated two outcomes: timely IHE utilization (proportion of members completing an IHE within 6 months of enrollment) and any IHE utilization (proportion completing an IHE by February 2024). We described IHE utilization by enrollment year and various members’ characteristics and conducted multivariable logistic regression models to estimate adjusted odds ratios for IHE utilizations to identify factors related to potential inequities for the two member types: Responders, who performed support services, vs. Survivors, who did not respond but were present in the New York disaster area. Results/Anticipated Results: A total of 27,379 Responders and 30,679 Survivors were included. Responders were 89% male, 70% 45–64 years old at enrollment and 76% White. Survivors were 46% female, 54% 45–64 years old at enrollment, and 57% White. Timely IHE utilizations remained relatively stable (~65%) among Responders across time and increased from 16% among Survivors who enrolled in 2017 to 68% among Survivors who enrolled in 2021. Timely IHE utilization was lower for younger members (enrolled Discussion/Significance of Impact: This study highlights Program achievements and gaps in providing equitable IHE services. Strategies to improve members’ equitable IHE utilization can include: adopt/expand flexible scheduling; increase non-English language capacity and cultural competency; and facilitate transportation/assistance for members with accessibility barriers.

Objectives/Goals: Physical activity (PA) is a well-documented protective factor against many cardiovascular diseases. PA guidelines to reduce these risks and the impact of variability are unclear, and most studies only examine a 7-day activity window. This study aimed to examine factors related to variability in step counts in a 3-year study of adults aged ≥18 years. Methods/Study Population: Included were 6,525 participants from the Michigan Predictive Ability and Clinical Trajectories study, a prospective cohort of community-dwelling adults enrolled between 8/14/2018 and 12/19/2019 who received care at Michigan Medicine and were followed for 3 years. Data were collected from Apple Watches provided to participants via the HealthKit. This secondary analysis included those with ≥4 valid weeks of data (≥4 days with at least 8 hours of wear time). Season was defined as Spring (March 20–June 20), Summer (June 21–September 21), Fall (September 22–December 20), and Winter (December 21–March 19). GEE models against the outcome of variability, defined as weekly standard deviation of step counts, and the predictor of season were adjusted for age, sex, race/ethnicity, weekly average step count, diabetes, and body mass index. Results/Anticipated Results: The average (standard deviation (SD) step counts by season were 7101 (3434) in Spring, 7263 (3354) in Summer, 6863 (3236) in Fall, and 6555 (3211) in Winter. Compared to winter, there was statistically significantly higher variability in all other seasons (p Discussion/Significance of Impact: In this cohort of community-dwelling adults, we found significant differences in variability of physical activity by season, age, and BMI. Future work will examine how this variability impacts the risk of development of cardiovascular disease, incorporating the impact and recovery trajectories of COVID-19 and other acute respiratory infections.

Objectives/Goals: Radiation nephropathy results in morbidity and mortality in patients receiving cancer treatment. In addition, low birth weight and low nephron number are associated with increased risk for chronic kidney disease. This study examined the development and severity of radiation-induced renal hemodynamic dysfunction in a low renal mass mouse model. Methods/Study Population: Male mice (C57Bl/6, 8–12-weeks) were used to determine a suitable radiation dose regimen. Mice were subjected to fractionated bilateral kidney irradiation with 5–6 fractions of an X-ray dose of 0, 6, 8, and 10 Gy at 24-hr intervals using a CT-image-guided irradiator. Body weight and mortality were monitored for 5 weeks in mice. In a separate set of experiments, the low renal mouse model, ROP Os/+, and their normal counterpart, ROP +/+ mice were subjected to 5 fractionated bilateral kidney irradiations at 24-hr intervals with an X-ray dose of 6 Gy. Renal blood flow was assessed from renal artery resistive index (RRI) over 5 weeks post-irradiation using an ultrasound system. Transcutaneous measurement of FITC-sinistrin clearance was used to determine glomerular filtration rate (GFR). Results/Anticipated Results: The C57Bl/6 mice that received 5–6 fractions of 8 and 10 Gy had more than 50% mortality, while 100% of the mice exposed to 5 fractions of 6 Gy survived for 5 weeks. Body weight was also significantly decreased in mice exposed to 5 or 6 fractions of 8 or 10 but not 6 Gy radiation. Nonirradiated C57Bl/6, ROP +/+, and ROP Os/+ mice had similar baseline GFR and RRI. Irradiation of 5 fractions at 6 Gy decreased GFR and increased RRI in C57Bl/6 and ROP +/+ mice. Interestingly, following 5 fractions at 6 Gy irradiation ROP Os/+ mice had 25% lower GFR than wild-type ROP +/+ mice (946.3 ± 50.3 vs. 1232.9 ± 69.3 µL/min/100g BW, p Discussion/Significance of Impact: Our study determined a suitable fractionated bilateral kidney irradiation dose regimen to evaluate radiation nephropathy. Data demonstrated that fractionated bilateral kidney irradiation leads to decreased renal hemodynamics in mice. We also demonstrated that irradiation caused greater renal hemodynamic dysfunction in low renal mass mice.

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.