Objectives/Goals: The goal of this study is to resolve the complexity of the adipose precursor cells and identify potential therapeutic targets/mechanism to treat obesity, diabetes, cancer cachexia, and related metabolic conditions in both white and brown adipose tissues. Methods/Study Population: White and brown adipose precursor cells were isolated from neonatal P0 mice and expanded in culture for single-cell RNA sequencing analysis. Unsupervised machine learning was used to unbiasedly cluster and categorize sequenced cells. Differentially expressed genes were used to identify populations via pathway analysis. Populations were then validated with published datasets via integration, reference mapping, and module scoring to ensure our dataset is reflective of known literature. Then, white and brown datasets were combined and unbiasedly clustered. Finally, signaling inferences using CellChat was used to identify significant signals being sent to and received from each cluster based on ligand–receptor pairs. Results/Anticipated Results: ScRNAseq revealed 7 subclusters in both white and brown adipose tissues. Differential expression and trajectory inferences revealed that white and brown precursors develop into two distinct fates: committed adipogenic precursors (CAPs), where these cells will be mature lipid-laden adipocytes; or fibro-adipogenic precursors-like (FAPLs), where these cells preferably stay in a fibroblast-like, antiadipogenic phenotype. Integrating white and brown cells with subsequent reclustering reveals that white and brown FAPLs are highly similar to one another by being clustered together. Cell signaling inferences and pathway analysis reveal that white and brown FAPLs may participate in the regulation of adipogenesis and angiogenesis of the adipose tissue. Discussion/Significance of Impact: Our results demonstrated that brown and white precursor cells share a common regulatory subpopulation with similar gene expression profiles, highlighting a more interconnected regulatory landscape in adipose tissue than previously understood. These findings reveal novel mechanisms of systemic metabolism and provide new therapeutic targets.

Objectives/Goals: We aim to predict and rank conserved, immunogenic targets within key malaria proteins using computational tools. These tools incorporate parasite protein diversity and regional HLA allele frequencies to prioritize antigens for further validation and inclusion in a malaria vaccine targeting circulating strains. Methods/Study Population: We identified 42 conserved malaria proteins with nonredundant functions for P. falciparum invasion and transmission as vaccine targets. Protein sequence datasets were constructed from samples collected in highly endemic areas. We predicted targets most likely to be presented to CD4+ and CD8+ T cells. We designed and used heuristic-based and AI-weighting models that integrated predicted binding affinities to HLA alleles, HLA allele frequency data, and sequence conservation to score and rank targets. We validated our model by comparing predicted epitope distributions with published in vitro and in vivo immunogenicity data available in the Immune Epitope Database and Tools repository. Results/Anticipated Results: We successfully predicted and ranked targets within the vaccine candidate proteins, identifying conserved and HLA-nonspecific targets that correspond to positive immunogenicity data, validating our approach. We are currently analyzing model performance by comparing predictions to over 5,800 experimentally validated P. falciparum targets from clinical trials and immune assays. We will evaluate each models’ accuracy and ability to prioritize targets and compare their performances as measured quantitatively by precision and area under the curve metrics. We expect the AI-based model to significantly outperform the heuristic approach, improving the identification of effective vaccine targets. Discussion/Significance of Impact: By incorporating parasite diversity and regional HLA allele frequencies, our approach addresses the challenge of directing the human immune response against genetically diverse P. falciparum strains in highly endemic areas. This strategy could significantly enhance malaria vaccine efficacy and can be adapted for use against other pathogens.

Objectives/Goals: To develop an informatics framework that will allow study of environmental effects on stillbirth at large scale (i.e., US-level) and leverage recent advances in machine learning and artificial intelligence to produce reproducible results that can be compared across multiple institutional settings. Methods/Study Population: Experimental exposure data are often available in “absolute time,” where a clinical event can be anchored using a timeline transformation. We associate each stillbirth event with a set of {ti…ti+1}L shapelets [1] associated with a location, L, and time intervals for the entire dataset. These shapeless are aggregated using a state-of-the-art shapelet classifier [2]. An autoencoder is used to reduce the dimensionality of the stillbirth classification and to cluster stillbirth events according to their corresponding exposure patterns. The stillbirth cluster can be analyzed for other nonexposure (i.e., genetic, SDoH, and demographics) factors, which may be enriched and/or depleted. Results/Anticipated Results: The framework we are developing leverages a shapelet-based approach to produce clusters of stillbirth events according to their corresponding exposure patterns. These clusters can be analyzed for depletion or enrichment of nonenvironmental factors. This analysis will inform how to formulate (or not) class models of exposure that can be more informative and have better predictive power than overall population models. Moreover, the finding of depletion and enrichment of physiological properties of the individuals may lead to novel physiological hypotheses to better understand the injury mechanisms that the environmental exposure profile produces. Discussion/Significance of Impact: Nearly 20,000 babies are stillborn in the USA each year [3]. Environmental exposures, usually studied as time averages over certain periods of time, have produced mixed results for stillbirth risk [4]. However, temporal profiles matter [1], and we argue that they can be assessed using shapelet technology.

Objectives/Goals: Intra-amniotic inflammation (IAI) is one of the leading causes of maternal/fetal morbidity globally, yet it is undiagnosed in 90–95% of cases. The purpose of this study was to assess precision and accuracy of a novel microsampling device for measuring cytokines in amniotic fluid (AF) to enable noninvasive evaluation of localized inflammation. Methods/Study Population: AF was obtained from discarded amniocentesis samples from 3 deidentified patients without known inflammation. Samples were spiked to 5 concentrations of interleukin-6 (IL-6) and tumor necrosis factor-a (TNF-a), then sampled using the Neoteryx Mitra volumetric microsampling device (20 µL). Dried/reconstituted samples were analyzed using the Luminex R&D Mag XL multiplex (IL-6, TNF-α) and compared to free-flowing AF. Inter-and intra-assay performances were evaluated across 5-runs in 3 standard cytokine concentrations. Recovery/linearity was assessed by a recovery curve and parameter estimates. Precision was assessed between-run and within-run using coefficients of variance (%CV). Accuracy was evaluated as agreement between microsampled and free-flowing AF using Bland–Altman plots. Results/Anticipated Results: TNF-α results were linear for all 3 patients across 5 concentrations. However, accuracy and recovery consistently failed (mean±SD percent recovery 176±21%). TNF-α results had acceptable precision with %CV within-run of 6.8–12.1% and across-runs of 14.0–15.9%. Microsampled TNF-α agreed with free-flowing sample: 16 of 18 (89%) were within 1SD of the mean difference (-24±36 pg/ml). IL-6 results were linear for 1/3 patients and had unacceptable accuracy and recovery for 13/15 samples (mean±SD percent recovery 764±469%). IL-6 results had acceptable precision (%CV within-run 6.2%, 7.5% and 11.2%; across-run .9–15.2%). Microsampled IL-6 agreed with free-flowing sample; 17 of 18 (94%) were within 1SD of the mean difference (-148±180pg/ml). Free-flowing vs. microsampling methods agreed best at low concentration. Discussion/Significance of Impact: This study provides preliminary support for noninvasive measurement of cytokines leveraging small amounts of leaking AF providing a promising alternative to amniocentesis and potential for assessing inflammation intrapartum. Clinical application requires development of reference ranges and association between cytokine levels and outcomes.

Objectives/Goals: Patients with multiple chronic conditions (MCCs) face care coordination challenges and poorer health outcomes. Outpatient telehealth may be an effective way to enhance MCC patient care given the need for multiple visits and specialists. This study seeks to describe telehealth utilization between 2013 and 2023 in Arkansas. Methods/Study Population: We utilized the Arkansas All-Payer Claims Database (APCD) to identify patients diagnosed with high-prevalence MCCs comprising diabetes with comorbid hypertension, hyperlipidemia, or asthma. We then measured telehealth utilization defined as any claim associated with a telehealth modifier code, a place of service code defining the service as occurring in the patient’s home, or remote patient monitoring. Finally, we created payer-specific (e.g., commercial or Medicaid) yearly measures of the number of any telehealth claims among MCC patients divided by the number of MCC patients for that year. Linear regression was used to measure the difference in utilization during the COVID-19 pandemic (i.e., 2020–2023) versus prior to the pandemic (i.e., 2013–2019). Results/Anticipated Results: Overall, the COVID-19 pandemic era was associated with an increase of telehealth utilization among commercial patients by 1.01 telehealth claims per MCC patient (95% CI: 0.39 to 1.62, p Discussion/Significance of Impact: Variations in telehealth uptake among MCC patients suggest heterogeneity in its suitability and necessity. We will later evaluate whether telehealth use is associated with different levels of inpatient and emergency department utilization. We expect the findings to provide clarity on the suitability of telehealth use by MCC disease status.

Objectives/Goals: Engage the research professional (RP) workforce in assessing job satisfaction, motivators, barriers, and levels of support throughout the research enterprise. The goal of this collaboration is to foster a positive culture, inform manager training, ensure RP retention, and enhance career mobility pathways. Methods/Study Population: Methods include a HR data compilation/analysis and focus groups for new RP’s (Results/Anticipated Results: This initiative will articulate the current culture and climate of the research enterprise and identify key strategic areas for growth. The UMN Clinical and Translational Science Institute (CTSI) will build off the design of an internal survey at Vanderbilt (2018) to encompass organization-specific challenges, the post-pandemic research landscape, and the UMass Diversity Engagement Survey. This process will also generate specific insights including RP sentiment statements, trends in how RP’s describe their day-to-day work, assessment of barriers, analysis of retention benchmarks, and defining employee hopes/motivators. The CTSI will also identify salient RP growth opportunities, leadership competencies, and areas of non-monetary compensation to improve satisfaction and career mobility. Discussion/Significance of Impact: Targeted interventions will be developed to address RP satisfaction barriers and leverage opportunities for KPI improvement. Results will be disseminated to managers, administrators, and the CTSI network. Resource development will include RP personas, job description/hiring templates, and strategic guides for key operational challenges.

Objectives/Goals: Nearly 42% of adults in the USA have obesity; women are disproportionately affected. Women with obesity that become pregnant are especially prone to developing health condition; thus, aid is needed to achieve appropriate gestational weight gain (GWG). GWG interventions would benefit from examining the effects of social support and stress has on GWG. Methods/Study Population: The proposed study will examine whether expecting mothers’ social support predicts their perceived stress. Also, examine whether receiving aid, in the form of weekly meal delivery, changes perceived stress. Lastly, this study will explore if social support mediates the relationship between meal delivery and perceived stress. The study will use data gathered from a pilot GWG intervention focused on providing pregnant women weekly meal delivery. Participants (N = 14) will complete 2 visits at 16–20- and 35–36-weeks gestation, while receiving weekly meal deliveries. Data from both visits will be used for the purpose of this study. Women’s social support will be measured using the Multidimensional Scale of Perceived Social Support. While stress will be measured via the Perceived Stress Scale. Results/Anticipated Results: Previous behavioral weight loss studies have found that individual who endorse experiencing social support report less perceived stress. Although the relationship has seldomly been examined in pregnant women, similar results are anticipated. Often aid, such as meal delivery, can impact perceived stress and is likely to cause a positive change. To our knowledge, this is the first study to explore whether social support mediates the changes in perceived stress after receiving weekly meal delivery. Therefore, there is no known literature to suggest anticipatory results. Discussion/Significance of Impact: Few studies have examined the association between social support and perceived stress in pregnant women. This study will examine the effects social support has on a pregnant women’s stress. The proposed study will aim to identify if meal delivery changes perceived stress. If so, the study will explore if perceived social support mediates this change.

Objectives/Goals: This study aims to evaluate common features of mobile health (mHealth) apps and their role in helping caregivers make health decisions for children. Methods/Study Population: A scoping review of literature on caregivers’ use of mHealth apps (published since 2008) was conducted across 5 databases (i.e., Embase, PubMed, CINAHL, Clinicaltrials.gov, and IEEE Xplore). Selected papers were categorized based on app purposes, target users, and mHealth agile development phases. Common features were also identified and analyzed along with users’ pros and cons. Further, primary feature requests were summarized to inform future development. Results/Anticipated Results: This review included 62 studies. Most apps were about maternity and infant care and specific diseases. Major users were caregivers and pregnant women. Around 20% of papers covered multiple phases in the mHealth agile development lifecycle. The effectiveness/clinical trial (phase III) was the most common. E-learning, personalization and customization, and health tracking features were the three most common features of mHealth apps included in this review. More positive feedback was found regarding features than concerns. Caregivers perceived apps as helpful and empowered them to make informed decisions. Concerns were mainly over 1) technical issues, 2) inappropriate design, and 3) ambiguous terms. Requested new features included content comprehensiveness, user engagement, and usage flexibility. Discussion/Significance of Impact: To our knowledge, this is the first review to investigate the usability of mHealth app features in this area. The results offer feasible strategies for developers to improve the effectiveness of apps for caregiver decision-making.

Objectives/Goals: Our study team won a Public Health Answers to Speed Tractable Results (PHASTR) contract to conduct a target trial emulation to answer “Does metformin show a reduction of severe outcomes of COVID-19 or of Long COVID in the N3C Data Enclave?” We quickly delivered an answer due to productive technical and collaboration support in the N3C. Methods/Study Population: Our analytic plan was updated based on helpful feedback from the PHASTR program. We performed a trial emulation analysis using the N3C data, comparing adult new users of metformin to controls prescribed fluvoxamine, fluticasone, ivermectin, or montelukast. The composite outcome was Long COVID or Death (LC/D) within 180 days of COVID infection. We used entropy balancing to estimate the average treatment effect with a weighted log-linear model. Productivity was enhanced by reusing code workbooks and validated codesets from related N3C projects. The team of 4 (physician, informaticist, data programmer, and statistician) and key unpaid advisors spent 10 weeks developing and analyzing the data. Results/Anticipated Results: Totally, 9,660 patients were identified for analysis. After weighting, there were 248 in the metformin and control groups. In the metformin group, 4.0% developed LC/D vs. 8.5% in the control group, with an adjusted risk ratio (aRR) of 0.47 (95% CI 0.25 to 0.89). Results were consistent across subgroups and sensitivity analyses. The PHASTR contract structure helped produce high-quality results quickly by not only providing funding but also requiring a compressed timeline for a small team to focus on the study. The most time was spent on contract execution, enclave provisioning, and too many last-minute download requests. A project final report was submitted in March and a full manuscript was submitted in September. Discussion/Significance of Impact: The analysis was productive because the environment made reuse easy and supported rich collaborations among clinicians, informaticists, epidemiologists, statisticians, and data developers. Advice from PHASTR advisors (Axel) and N3C diabetes domain team members was also key to a faster completion.

Objectives/Goals: To strengthen postdocs’ skills in developing and reviewing competitive proposals, advancing translational research by leveraging core facilities at Indiana University, Purdue University, and the University of Notre Dame, fostering collaboration, and preparing participants of the program for future funding success. Methods/Study Population: The Postdoc Challenge is a state-wide program for postdoctoral scholars across Indiana to gain hands-on experience in developing and reviewing competitive grant proposals. Participants compete for a $5,000 award to use any of the Indiana Clinical and Translational Science Institute (CTSI)-approved core facilities. Through workshops and following NIH guidelines for the review process, participants refine their proposal-writing skills and serve as reviewers for peers’ proposals. The program is designed to support translational research, utilizing the core facilities at Indiana University, Purdue University, and the University of Notre Dame. Participants are trained in grant proposal writing, reviewing using NIH criteria, and engaging in peer discussions, developing critical skills necessary for future funding success. Results/Anticipated Results: Since its launch in 2014, the Indiana CTSI Postdoc Challenge has funded 54 postdoctoral researchers, with 276 applications reviewed. The program has strengthened participants’ grant proposal writing skills and peer review capabilities. Career outcomes include several postdocs securing assistant professor positions and other prestigious roles, such as an Associate Principal Investigator at the National Biodefense Analysis and Countermeasures Center, and a Toxicologist at the CDC. Participants also report enhanced collaboration, greater access to core facilities, and significant career advancement, including support for international postdocs seeking permanent residency. Discussion/Significance of Impact: The Postdoc Challenge has significantly improved postdoctoral researchers’ grant proposal writing and peer review skills, helping them secure faculty and research positions. By fostering collaboration across Indiana’s top universities and utilizing core facilities, the program accelerates translational research and career success.

Objectives/Goals: Port-site metastasis (PSM), defined as the spread of malignancies to the abdominal wall at the site of surgical ports, poses a significant challenge in cancer management. The objective of this summary overview is to describe the prevalence of and risk factors associated with PSM in various gynecological cancers after laparoscopic surgery. Methods/Study Population: Study design: Systematic Review and Meta analysis Search strategy: All international databases, without language limitations, from January 1990 to December 2023. Inclusion/exclusion criteria: Cohort, case–control, or cross-sectional observational studies reporting the frequency of, or risk factors for PSM in young and middle-aged women will be included (using the PRISMA checklist). Data extraction: two reviewers independently extracting pertinent data (using the STROBE checklist). Quality assessment and risk of bias: The quality of each study will be assessed according to the Quality Assessment Tool for Observational Studies. Results/Anticipated Results: This meta-analysis of 36 studies evaluated the proportion of successes across various populations, with a pooled proportion of 0.02 (95% CI: 0.01–0.02) based on a random-effects model. Significant heterogeneity was identified (I²  =  88.12%), reflecting notable variability between studies. Despite this, the overall effect was statistically significant (p  =  0.00). A subgroup analysis will be conducted to explore potential sources of heterogeneity, considering factors such as cancer stage, diagnostic methods, surgical approach (conventional or robotic), and study type (retrospective/prospective). Discussion/Significance of Impact: By identifying the prevalence of, and the risk factors for, PSM, this study will better inform personalized treatment approaches, surveillance strategies, and surgical decision-making to improve patient-related outcomes and long-term survival in women with gynecological malignancies.

Objectives/Goals: Inclusive physical activity (PA) interventions could improve trans and gender diverse (TGD) adolescents’ PA levels, perceived social support from peers and adults, and mental health, but no stakeholder-informed interventions exist. We describe parents’ impressions of TGD adolescent children’s PA experiences and advice for a PA intervention. Methods/Study Population: We conducted individual Zoom interviews with parents of 13- to 20-year-old TGD adolescents (n = 15). All parents were recruited from a gender healthcare clinic. All children self-identified as TGD, an umbrella term including people who have a gender identity different from social expectations for their assigned sex. We asked questions regarding children’s current and historical participation in PA, parents’ perceptions of barriers to PA for their TGD children, and parents’ desired intervention components. After each interview, parent participants were compensated $100 for their time. We analyzed interview transcripts, focusing on insights to incorporate in an intervention. This study was approved by the University’s Institutional Review Board. Results/Anticipated Results: Parents shared rich histories of their children’s PA participation, compounding barriers to PA, numerous benefits of PA, and a range of preferences for program activities and inclusive practices (e.g., safety protocols, training for adult leaders). They also emphasized the need for TGD youth to build social connectedness through PA. Discussion/Significance of Impact: We gathered concrete advice from parents on creating a PA intervention, which we will use to build a social PA program that meets TGD adolescents’ needs. Addressing health disparities and improving PA, social support, and mental health among TGD adolescents will require such stakeholder input to improve upon existing PA and sports opportunities.

Objectives/Goals: Here, we utilize deep learning to automate the analysis of dual X-ray absorptiometry (DEXA) scans in the UK Biobank (UKB) imaging dataset to enable a large-scale assessment of lumbar spine disc degeneration, low back pain, and socioeconomic status. Methods/Study Population: Study Population: The UKB is a biomedical database that includes lateral spine DEXA imaging for 50,000 participants. Deep Learning Model Development: A computer vision model was developed that receives a DEXA scan as input and outputs a quadrilateral that corresponds to the corners of 5 lumbar vertebral bodies. The model is a deep, fully convolutional, encoder–decoder network using DeepLabV3. Statistical Analysis: To determine our preliminary model accuracy, we used the intersection over union (IoU) metric.We analyzed data using an ordinal regression model to determine the relationship between income/ neighborhood level multiple deprivation index (MDI) and low back pain (LBP), as well as a mixed effects model to estimate the relationship between income/MDI and disc height index (DHI). Results/Anticipated Results: Our model predicted vertebral body quadrilaterals in training and unseen test data (train IoU  =  0.96, test IoU  = .91) and was used to infer data for 10,440 participants. Confirming previous studies, there were significant relationships (p0.05) between income or MDI and DHI (Figure 2). Discussion/Significance of Impact: Low back pain is the world’s leading cause of disability, and socioeconomic factors play an important role. We found no relationship between disc height index and socioeconomic status. Thus, disc degeneration may not be a factor in this low back pain phenotype.

Objectives/Goals: The identification of the cascade of molecular and cellular events occurring during the progression of focal segmental glomerulosclerosis in human kidney biopsies from kidney transplant (KTx) recipients (KTR) with normal function or recurrent FSGS to determine potential targets of intervention and therapy. Methods/Study Population: In this study, we evaluate the molecular and cellular events associated with primary FSGS in both native and transplant kidneys. We collected biopsy samples from the native normal kidney (nNK, n = 3), normal functioning allografts (NKTx, n = 3), primary FSGS in the native kidney (nFSGS, n = 1), recurrent FSGS (KTxFSGS, n = 5). KTxFSGS comprises a collection of longitudinal samples with biopsy also collected at the subsequent recurrence. Blood samples were collected during biopsy collection. Biopsies were preserved in RNAlater at the time of collection. 10X genomics chromium single nuclei RNA sequencing (snRNAseq) was performed using isolated nuclei. Data was analyzed using Seurat on R. Conditionally immortalized podocytes were treated with a patient serum to determine the change in expression observed in snRNAseq data. Results/Anticipated Results: Recurrence rates of primary FSGS are high in kidney allograft recipients up to 25–50% in first, and up to 80% in second transplants, often leading to graft loss. Our findings reveal that podocyte detachment is driven by metabolic and structural dysregulation rather than cell death, increasing VEGFA expression and disrupting glomerular endothelial cell growth and permeability. Parietal epithelial cells initially compensate by dedifferentiating toward podocytes but later increase collagen deposition, contributing to glomerular sclerosis. Increased interactions of glomerular cells with B cells exacerbate extracellular matrix deposition and scarring. We also observed tubular sclerosis and disruption of the regenerative potential of proximal tubular cells, with increased interaction with T cells. Discussion/Significance of Impact: These findings offer new insights into the pathogenesis of recurrent FSGS and suggest potential therapeutic targets and establishes a foundation for future studies to further evaluate the role of metabolic dysfunction as the cause of podocyte injury and loss.

Objectives/Goals: Although several studies have identified significant associations between specific social determinants of health (SDoH) and adverse outcomes, little is known about how SDoH co-occur to form subtypes and their outcome-based risks. Here we analyze how SDoH co-occur across all participants with a cancer diagnosis in the All of Us program. Methods/Study Population: Data: All participants (n = 3361) with cancer and their responses to 110 survey questions related to SDoH. Independent variables: 18 SDoH factors aggregated from the questions to address uneven granularity. Dependent variables: depression, delayed medical care, and ER visits in the last year. Analytical Method. (1) Bipartite network analysis with modularity maximization to identify participant-SDoH biclusters, measure the degree of their biclusteredness (Q), and estimate the significance of Q. (2) Visualization of the results using the ExplodeLayout force-directed algorithm. (3) Multivariable logistic regression (adjusted for demographics and corrected through FDR) to measure the odds ratio (OR) of each bicluster compared pairwise with the other biclusters to estimate their risk for the 3 outcomes. Results/Anticipated Results: As shown in Fig. 1A (http://www.skbhavnani.com/DIVA/Images/Cancer-SDoH.jpg), the analysis (n = 3361, d = 18) identified 4 biclusters with significant biclusteredness (Q = 0.13, random-Q = 0.11, z = 9.94, P Discussion/Significance of Impact: Currently, many health equity policies allocate resources based on sociodemographic factors like race and income to address disparities. The 4 distinct subtypes and their outcome-based risks suggest that such policies could be more precise if they were based directly on combinations of need using SDoH subtypes and their risk stratification.

Objectives/Goals: This study aims to evaluate the performance of a third-party artificial intelligence (AI) product in predicting diagnosis-related groups (DRGs) in a community healthcare system. We highlight a use case illustrating how clinical practice leverages AI-predicted information in unexpected yet advantageous ways and assess the AI predictions accuracy and practical application. Methods/Study Population: DRGs are crucial for hospital reimbursement under the prospective payment model. The Mayo Clinic Health System (MCHS), a network of clinics and hospitals serving a substantial rural population in Minnesota and Wisconsin, has recently adopted an AI algorithm developed by Xsolis (an AI-focused healthcare solution provider). This algorithm, a 1D convolutional neural network, predicts DRGs based on clinical documentation. To assess the accuracy of AI-generated DRG predictions for inpatient discharges, we analyzed data from 930 patients hospitalized at MCHS Mankato between March 2 and May 13, 2024. The Xsolis platform provided the top three DRG predictions for the first 48 hours of each inpatient stay. The accuracy of these predictions was then compared against the final billed DRG codes from the hospital’s records. Results/Anticipated Results: In our validation set, Xsolis achieved a top-3 DRG prediction accuracy of 71% at 24 hours and 81% at 48 hours, which is lower than the originally reported accuracy of 81.1% and 83.3%, respectively. Interestingly, discussions with clinical practice leaders revealed that the most valuable information derived from the AI predictions was the expected geometric mean length of stay (GMLOS), which Xsolis was perceived to predict accurately. In the Medicare system, each DRG is associated with an expected GMLOS, a critical factor for efficient hospital flow planning. A subsequent analysis comparing predicted GMLOS with the actual length of stay showed variances of -0.10 days on day 1 and 0.14 days on day 2, indicating a high degree of accuracy and aligning with clinical practice perceptions. Discussion/Significance of Impact: Our research underscores that clinical practice can leverage AI predictions in unexpected yet beneficial ways. While initially focused on DRG prediction, the associated GMLOS emerged as more significant. This suggests that AI algorithm validation should be tailored to specific clinical needs rather than relying solely on generalized benchmarks.

Objectives/Goals: The NIH Common Fund launched Community Partnerships to Advance Science for Society (ComPASS) to study ways to reduce health disparities by addressing underlying structural factors within communities. ComPASS was designed for community organizations to lead research that addresses community needs. Methods/Study Population: ComPASS awarded five health equity research hubs (Hubs) to provide specialized technical support to ComPASS research projects led by community organizations. Expertise provided by the Hubs to the community-led projects will focus on specific facets of community health, including nutrition access, health care access, and built environment. The Hubs support community-led piloting and testing of structural interventions within community settings by providing subject matter expertise in areas including structural and multilevel intervention study design and methods, implementation science, and community engagement. Results/Anticipated Results: The Hubs will provide expertise and support to the community-led research projects around one or more social determinants of health domains: health care access and quality, education access and quality, economic stability, social and community context, and neighborhood and built environment. The Hubs will help identify strategies for measuring health outcomes and assessing the effects of structural and contextual factors on intervention outcomes. We anticipate the ComPASS program will lead to a better understanding of how structural interventions that leverage multi-sectoral partnerships can advance health equity. Discussion/Significance of Impact: Through community-led research, ComPASS projects are implementing structural interventions to address social determinants and advance health equity. The technical scientific support rooted in health equity provided by the Hubs is essential to the success of these research projects.

Objectives/Goals: Gait performance (GP) and global cognitive functions (GCF) are both critical for maintaining independence and quality of life in senior adults. Recent studies have explored the potential link between GP and GCF, encompassing executive functions. Methods/Study Population: PRISMA guidelines will govern this systematic review. This systematic review synthesizes published research from 2000 to 2024, including peer-reviewed articles, pilot studies, and randomized controlled trials, to examine the relationship between GP (how a person walks and stands) and GCP in older adults. The exclusion criteria will be based on studies focused on physical activities unrelated to balance, meta-analysis, and systematic reviews and those published in languages other than English or Spanish. Results/Anticipated Results: Our preliminary data indicate that gait, or walking speed, is significantly correlated with GCP in older adults, with slower walking associated with poorer global cognition. Specifically, gait speed during dual-task walking shows a strong correlation with working memory (p < .001) and processing speed (p < .05) in individuals aged over 60 years. Gender differences were observed, with women over 80 walking slower than men over 85 years, who walked faster, and women exhibited poorer global cognition than men. Discussion/Significance of Impact: Overall, a gait slowing between 0.68 and 1.1 m per second could predict a marker for the risk of developing dementia, indicating that monitoring gait speed in older adults may provide early warning signs, allowing for timely interventions. Enhancing GP and GCF can improve the quality of life and independence in older adults. Acknowledgments: Research supported by NIH: Award Number HCTRECD R25MD007607 from the NIMHD.

Objectives/Goals: Second-generation antipsychotics (SGA) are used to treat mental disorders in youth but are linked metabolic syndrome (MetS). Most data on prescribing practices and risk factors are from short-term studies (6–12 months). We aim to characterize prescribing and identify clinical and genetic predictors of MetS using electronic health records (EHR). Methods/Study Population: EHR data were extracted from Cincinnati Children’s Hospital Medical Center (CCHMC) for patients aged ≤21 years prescribed SGAs from 7/1/2009 and 7/1/2024, identifying prescribing prevalence. Next steps are to create an SGA-MetS case–control dataset 8 weeks after an SGA prescription. A case will be defined by meeting 3 of 5 criteria: 1) BMI ≥95th percentile for age/sex; 2) fasting glucose ≥100 mg/dL or use of anti-diabetics; 3) triglycerides ≥110 mg/dL; 4) HDL-C ≤40 mg/dL; 5) systolic/diastolic BP ≥90th percentile for age/sex or use of antihypertensives. The prevalence of SGA-MetS will be calculated by dividing SGA-MetS cases by total SGA users. Logistic regression will identify clinical predictors of MetS, and we will evaluate the association of polygenic risk scores (PRS) of BMI and type 2 diabetes with SGA-MetS risk. Results/Anticipated Results: Our preliminary analysis identified 30,076 patients who were prescribed SGAs (mean age 12 years, SD = 4; 58.8% female; n =  17685). Most self-identified as non-Hispanic (95%, n = 28,595) and of White race (76%; n =  22,935), with 18.5% self-identifying as Black or African American (n = 5,579). The most commonly prescribed SGAs were risperidone (n = 12,382, 41.1%), aripiprazole (n = 9,847, 32.7%), and quetiapine (n = 5,263, 17.5%), with much lower prescribing rates of other SGA known of their low risk of MetS (e.g., ziprasidone 5.5%, lurasidone 1.4%, paliperidone (n = 316, 1.1%), or others cariprazine (n = 72), asenapine (n = 43), brexipiprazole (n = 39), iloperidone (n = 24), and clozapine (n = 20). Discussion/Significance of Impact: Our analyses found that risperidone, quetiapine, and aripiprazole were the most prescribed SGA, with risperidone/quetiapine linked to a higher risk of MetS. We will present ongoing work identifying risk factors for SGA-MetS and examining the association with PRS. Our work has the potential to identify high-risk patients for personalized treatment.

Objectives/Goals: This study aimed to explore Puerto Rican adolescents’ mental health experiences, focusing on risk and protective factors, and cultural perspectives on mental health. Methods/Study Population: Three focus groups were conducted: two with 20 adolescents aged 12 to 18 years of both genders and one with five adults who work with adolescents. Data were analyzed using interpretative phenomenological analysis. Results/Anticipated Results: The majority of participants in both groups of adolescents identified five key themes: social pressures, barriers to discussing mental health, the impact of social media, coping strategies, and institutional interventions. The adult focus group highlighted adolescent mental health problems, support systems, family and social factors, the church’s role, and recommended interventions. Discussion/Significance of Impact: The findings emphasize that social and familial pressures, mental health stigma, and social media significantly impact adolescent mental health. Coping strategies, such as sports, art, and nature, were also identified. These themes underscore the need for safe, supportive spaces, and targeted approaches to address youth mental health.