ABSTRACT IMPACT: Knowledge of which aspects of social connectedness most strongly associate with caregiver health and health behaviors can inform intervention targets to improve caregiver health OBJECTIVES/GOALS: Stressed dementia caregivers are at risk of poor health. Social connectedness may reduce adverse health effects, yet it is unknown about which aspects relate most strongly to health. This is a barrier to intervention development. Our study identifies aspects of social connectedness most strongly associate with caregivers’ daily health behaviors. METHODS/STUDY POPULATION: Data. Enrolled spousal caregivers completed 14 consecutive days of online surveys. Measures. We examined multiple health behaviors each day, which included: 1) number of occurrences of 3 potential binge-eating behaviors (range 0 to 30), 2) whether participants engaged in at least 30 minutes of physical activity, and 3) perceived sleep quality, rated 1 (very bad) to 5 (very good). We also examined a count of health symptoms caregivers experienced (e.g., backache; range: 0 to 7). Measures of social connectedness included: spousal emotional support, perceived spousal appreciation, emotional support from any source, and loneliness. Analysis. We applied bivariate multi-level mixed effects models to examine the association between each aspect of social connectedness and health behaviors day-to-day. RESULTS/ANTICIPATED RESULTS: Since November 2020, 5 of N=40 participants were enrolled, of whom 3 had completed all diary surveys. Participants were women ages 59 to 73, and included 4 non-Hispanic white and 1 Hispanic caregivers. Data included 51 days of surveys (93% adherence). No differences in eating behaviors nor physical activity according to social connectedness were found. Emotional support from any source was positively associated with sleep quality (B= 0.20; SE=0.08; p-value 0.015). On days when caregivers indicated their spouse appreciated them ‘A lot’ versus ‘Not at all,’ sleep quality was marginally better (B=0.73, SE=0.42; p-value-0.08). Finally, days when caregivers felt lonely at least ‘Some of the time’ versus ‘Not at all’ were associated with experiencing more adverse health symptoms (B=1.54; SE=0.58; p-value<0.001). DISCUSSION/SIGNIFICANCE OF FINDINGS: Improved emotional support from any source may support better sleep quality among caregiving spouses, while loneliness appears to contribute to more adverse health symptoms. Findings, if confirmed, can be translated to develop intervention programs that target loneliness and perceived emotional support among caregivers.

Objectives/Goals: Clozapine is the most effective treatment for people with treatment-resistant schizophrenia but is underutilized. Black patients are less likely to receive clozapine than White patients. Given limited data on the efficacy of clozapine in this population, we assessed clinical response in a large clinical trial of clozapine in Black patients. Methods/Study Population: This secondary analysis of a 6-month prospective, open-label clinical trial of clozapine in Black patients with schizophrenia spectrum disorders included 221 participants, 103 from Maryland, and 118 from Nigeria. The primary outcome was reduction in symptom severity as measured by total Brief Psychiatric Rating Scale (BPRS) over time on clozapine and modeled by a linear mixed effects model adjusted for age, sex, location, marital status, diagnosis, smoking status, Duffy null (ACKR-1 CC) genotype, clozapine dose, and clozapine level. We also assessed (i) changes in BPRS subscales over time, (ii) predictors of 20% improvement in BPRS, (iii) time to 20% BPRS improvement, and (v) the burden of clozapine side effects and the association of side effects and clinical improvement. Results/Anticipated Results: The average age was 40.2 years; 63% were male, 78% had schizophrenia, and 20% had schizoaffective disorder. BPRS total scores improved by 10.94 points (p < 0.001), adjusting for age, sex, and clozapine dose. Participants showed significant improvement in positive, resistance, affective, and activation, but not negative subscale scores. Nigerian participants were 21.5 times more likely to demonstrate 20% BPRS improvement compared to Maryland participants (p <0.001) and showed improvement more quickly, with most of the improvement in the first 4 weeks in Nigerian participants and 12 weeks for those in Maryland. 44.1% of participants had weight gain of at least 5% from baseline to endpoint. Improvement in tardive dyskinesia (p = 0.008) and weight gain (p < 0.001) were associated with BPRS improvement. Discussion/Significance of Impact: This study demonstrates clozapine’s efficacy in Black patients with schizophrenia spectrum disorders. Greater improvement in Nigerian participants may reflect differences in treatment resistance, social support, or expectation bias across groups. Further research is needed to improve utilization of clozapine in Black patients.

OBJECTIVES/GOALS: The goal of the study is to provide insights into the use of machine learning methods as a means to predict heterogeneity of treatment effect (HTE) in participants of randomized clinical trials. METHODS/STUDY POPULATION: Using data from 2,441 participants enrolled in the ASPirin in Reducing Events in the Elderly (ASPREE) randomized controlled trial of daily low-dose aspirin vs placebo in the United States, we developed multivariable risk prediction models for the composite outcome of dementia, disability, or death. We used two machine learning techniques, decision trees and random forests, to develop novel non-parametric outcomes classifiers and generate risk-based subgroups. The comparator method was an extant semi-parametric proportional hazards predictive risk model. We then assessed HTE by examining the 5-year absolute risk reduction (ARR) of aspirin vs placebo in each risk subgroup. RESULTS/ANTICIPATED RESULTS: In the random forest classifier, the ARR at 5 years in the highest risk quintile was 13.7% (95% CI 3.1% to 24.4%). For the semi-parametric proportional hazards model, the ARR in the highest risk quintile was 15.1% (95% CI 4.0% to 26.3%). These results were comparable and provide evidence of the viability of internally developed parsimonious non-parametric machine learning models for HTE analysis. The decision tree model results (5-year ARR = 17.0%, 95% CI= -5.4% to 39.4% in the highest risk subgroup) exhibited more uncertainty in the results. DISCUSSION/SIGNIFICANCE: None of the models detected significant HTE on the relative scale; there was substantial HTE on the absolute scale in three of the models. Treatment benefit on the absolute scale may be regarded as bearing greater clinical importance and may be present even in the absence of benefit on the relative scale.

OBJECTIVES/GOALS: Our overall objective is to investigate the relationship between radiologic features of meningioma with recently identified histopathological and molecular biomarkers, and to apply a machine learning (ML) approach to further demonstrate their utility in predicting clinical outcomes. METHODS/STUDY POPULATION: We have enrolled a cohort of 84 patients with meningioma diagnosed on the basis of conventional gadolinium-enhanced MRI imaging features since September 2019. Each patient has demographic and clinical data, Ga-68-DOTATATE MRI/PET SUV and dynamic metrics, DCE-MRI perfusion parameters, and histopathologic data. Various tumor subregions will be segmented semi-automatically and later confirmed by experienced neuroradiologist. Histopathologic data will include histologic grade, mitotic rate, Ki67 proliferative index, and presence of WHO established atypical histologic features, immunohistochemical parameters, and established high-grade molecular features. We will use supervised learning techniques to develop algorithms for predicting molecular features from imaging phenotypes. RESULTS/ANTICIPATED RESULTS: Anticipated results - advancements in understanding the molecular biomarkers of meningiomas has uncovered genetic alterations and epigenetic changes that more accurately determine tumor behavior. Currently, the imaging correlates of these molecular biomarkers are unknown, and utilizing radiographic data to predict prognosis and imaging-based classifications of meningiomas have not yet been investigated. Validated imaging correlates of molecular biomarkers not only provide an in-vivo assessment of tumor biology, but can also be integrated with histopathologic features ( radiopathomics models’) for more accurate disease prognostication. We anticipate that our results will identify surrogate imaging features for some of the recently emerged molecular biomarkers of meningioma. DISCUSSION/SIGNIFICANCE: There is a paucity of data on the importance of imaging phenotypes in determining tumor biology. This work has the potential of significant clinical impact by enabling a priori molecular characterization of meningiomas at the time of new diagnosis or recurrence, thereby allowing a personalized medicine approach to treatment planning.

Objectives/Goals: Knowledge about predictive factors for immune-related endocrinopathies can help identify appropriate populations for specific screening approaches, provide recommendations for ICI therapy selection, guide clinical monitoring strategies to improve patient outcomes, and guide research efforts to provide equitable healthcare for all patients. Methods/Study Population: This is an analysis of the demographic and clinical data available of patients from DiRECT Cohort, a longitudinal study that prospectively follows adult cancer patients who self-identify as Black or White and undergo anti-PD-(L)1 ICI therapy. Endocrinopathies were graded using the CTCAE criteria. Kaplan–Meier method was used to calculate the incidence within the first year of treatment. Bivariate analysis (Chi-square and log-rank test) examined the associations between patient demographics, clinical characteristics, and endocrinopathies. Results/Anticipated Results: Among 955 patients, 13.20% developed endocrinopathies of any grade, most commonly hyper-/hypothyroidism and adrenal insufficiency, and 5.97% were at grade ≥2. Younger age (7.59% in age 30 vs. 4.72% in BMI ≤30, p = 0.022) showed significant associations. No significant difference was found in the incidence of grade ≥2 endocrinopathies by race (13.3 % in White and 10.79% in Black patients, p = 0.732). No association was found with cancer stage or comorbidities. Discussion/Significance of Impact: ICIs can lead to (irAEs). Endocrinopathies are a common type of irAEs, presenting a unique challenge. However, the current literature lacks real-time data and a comprehensive comparative analysis of variables like race. Identifying and understanding these variables ensures equatable access to safe and effective healthcare for all patients.

OBJECTIVES/SPECIFIC AIMS: Opioid use disorder (OUD) is a national epidemic and identified as a top priority by the practices and communities in rural Colorado. Until recently, few resources existed to address OUD in rural communities. In addition to training primary care and behavioral health practice teams in medication assisted treatment (MAT), Implementing Technology and Medication Assisted Treatment and Team Training and in Rural Colorado (IT MATTTRs Colorado) engaged local community members to alter the community conversation around OUD and treatment. For IT MATTTRs, the High Plains Research Network and the Colorado Research Network engaged community members in a 8-10 month process known as Boot Camp Translations (BCT) to translate medical information and jargon around OUD and MAT into concepts, messages, and materials that are meaningful and actionable to community members. The resulting community interventions are reported here. METHODS/STUDY POPULATION: IT MATTTRs conducted separate BCTs in Eastern Colorado and the south central San Luis Valley. Community partners included non-health professionals with diverse backgrounds, public health and primary care professionals, law enforcement, and others. The BCT process includes a comprehensive education on OUD and MAT and facilitated meetings and calls to develop messages and dissemination strategies. Each BCT lasted around 8-10 months. RESULTS/ANTICIPATED RESULTS: The BCT process elicited unique contextual ideas and constructs for messages, materials, and dissemination strategies. Themes common to both BCTs include the prevalence of OUD and that help is available in the local primary care office. Community-tailored messages are distributed through posters and flyer inserts, drink coasters, newspaper articles, letters to local judges, restaurant placemats, and websites. Examples of the materials and messages will be presented. DISCUSSION/SIGNIFICANCE OF IMPACT: Local community members are eager to help address the OUD crisis. Built on community-based participatory research principles, BCT can be used to translate complex information and guidelines around OUD and MAT into messages and materials that reflect local culture and community needs.

The COVID-19 pandemic has led to major disruptions in the clinical research enterprise. Investigators and staff at the University of Washington and Seattle Children’s Research Institute (SCRI) were surveyed to determine the impact of the pandemic restrictions on their non-COVID-19 clinical research studies. Enrollment and study visits were stopped for over half of the interventional trials. There were both positive and negative impacts of the work restrictions on the professional and personal lives of faculty and staff. Academic and research institutions should consider how best to support investigators and their teams during this pandemic.

Despite substantial investment in clinical and translational research, only a small proportion of evidence-based interventions are adopted and sustained in routine practice, contributing to persistent delays between discovery and population benefit. Dissemination and implementation (D&I) science is a critical discipline for addressing this gap, and the NIH Clinical and Translational Science Award (CTSA) program (established 2006) has been strategically positioned as a national infrastructure to advance D&I capacity. We conducted a national environmental scan of publicly available websites and documents from all 66 CTSA hubs (May–July 2025), using a structured extraction tool to capture D&I-specific activities across seven domains: institution and community partnerships, formal D&I organizational structures within the CTSA, consultation services, collaborative programming, training opportunities, educational offerings, and pilot funding mechanisms. Findings reveal substantial heterogeneity in D&I science activities across CTSA hubs; 45% had a formal D&I unit, 54% offered D&I consultation services, and 37% provided collaborative programming. Structured workforce development was limited: 12% offered D&I-focused training grants, 15% offered structured educational programs, and 15% provided D&I-specific pilot funding. Consultation models varied widely in scope, access, and evaluation practices. These findings demonstrate uneven development of D&I science infrastructure across CTSAs and highlight opportunities to strengthen capacity nationally.

The importance of mentoring for professional development in Science, Technology, Engineering, Mathematics and Medicine (STEMM) fields is well established. With the increasing prevalence of team science, mentoring that incorporates team science skills is essential. Here, we describe a novel mentoring program designed to develop technical and relational/interpersonal skills for working in multi-disciplinary team science environments and to develop networks to improve collaboration in multi-disciplinary team science. The Georgia Clinical and Translational Science Alliance Translational Education and Mentoring in Science program is a nine-month program consisting of one-on-one mentoring, peer mentoring groups, mentoring resources, and shared learning experiences. Mentees (fellows) are exposed to a wide range of learning opportunities related to the goals of the program. This multi-institutional effort, in its fifth year, has been well received by participants. To date, 95 faculty, post-doctoral fellows, and research scientists have participated in the program as mentees. Participants indicated that they enjoyed the program, identified new networking opportunities, and would recommend it to others. In addition, fellows reported improved relational, technical, and networking skills over the duration of the program. Mentor ratings were also quite favorable. The multi-institutional nature of the program enriched learning and its unique structure combining traditional one-on-one mentoring with peer learning communities has been beneficial to those participating.

Objectives/Goals: With qualitative interviews we aim to 1-Describe barriers and facilitators for post-transplant lymphoproliferative disease (PTLD) survivors’ access to late effects (LE) care. 2-Investigate clinicians’ perceptions of current and ideal PTLD LE care. Our long-term goal is to develop and pilot implementation strategies to standardize PTLD LE care. Methods/Study Population: Study population: We will recruit 20–25 PTLD survivors or their caregivers and 10–15 health care workers (HCW) from oncology, LE, and solid organ transplant (SOT) teams at St. Louis Children’s Hospital (SLCH). PTLD is a lymphoma-like cancer that occurs in solid organ transplant (SOT) recipients. PTLD survivors experience LE from cancer, yet many do not receive LE care. Research strategy: We will conduct qualitative semi-structured interviews based on the Consolidated Framework for Implementation Research (CFIR). A preliminary codebook will be based on CFIR and refined through transcript review. Team-based coding includes double coding and checking for intercoder reliability. We will generate coding reports to understand themes and identify barriers and facilitators of LE care. Results/Anticipated Results: We hypothesize survivors, caregivers, and HCWs will identify actionable factors to inform future studies to optimize LE care. We will examine the CFIR inner setting (resources, communication, and structural characteristics), outer setting (local attitudes and external pressures), innovation domain (adaptability, evidence base, and relative advantage), individuals domain (need, opportunity, and motivation), and implementation process domain. Our contribution will be novel. 1-This is the first assessment of barriers and facilitators for LE care in pediatric PTLD survivors. 2-We will consider input from HCWs across various disciplines delivering care to PTLD survivors. 3-We anticipate identifying unique contextual factors in PTLD survivors that will influence implementation of evidence-based LE care. Discussion/Significance of Impact: Pediatric cancer survivors experience LE. Coordinated care mitigates LE. PTLD survivors experience a high burden of LE, but less than 10% of PTLD survivors at SLCH follow in LE clinic. No studies have evaluated ideal delivery of LE care for PTLD survivors. Our findings will inform an implementation trial to improve delivery of LE care for PTLD survivors.

ABSTRACT IMPACT: Triple negative breast cancer (TNBC) affects 10-20% of women with breast cancer and is biologically more aggressive than other subtypes. The novel compound we have developed, DL7076, would give clinicians a vital strategy to improve the commonly used cyclophosphamide (CPA) and doxorubicin (DOX) regimen in the treatment of TNBC. OBJECTIVES/GOALS: The objective of this research project is to develop a novel compound which can activate both 1) the constitutive androstane receptor (CAR) and subsequently enhance the CYP2B6-mediated activation of CPA, and 2) the nuclear factor erythroid- related factor-2 (Nrf2) leading to the cardiomyocyte protection from DOX-associated cardiotoxicity. METHODS/STUDY POPULATION: Following the identification of the compound candidate, DL7076 was evaluated for tissue specific induction of CAR and Nrf2 using qPCR, western blot analysis, and luciferase reporter assays.

Further, we have developed a multicellular coculture model incorporating human primary hepatocytes for metabolism, TNBC spheroids as the target, and cardiomyocytes as a side target of DOX. We have investigated the anticancer effects of CPA/DOX on TNBC cells and the toxic effects on cardiomyocytes with/without a CAR-Nrf2 activator, in a multicellular environment where hepatic metabolism is well-retained. RESULTS/ANTICIPATED RESULTS: We found that our dual activator of CAR and Nrf2, DL7076, exhibits tissue specific induction of CAR and Nrf2. Inclusion of DL7076 in combination with the CPA/DOX regimen improves anticancer efficacy, through the subsequent increase in the formation of the active CPA metabolite. With the addition of DL7076, DOX-mediated off-target cardiotoxicity was markedly reduced.

Lastly, utilizing the novel coculture system with human primary hepatocytes, TNBC spheroids, and cardiomyocytes, the inclusion of DL7076 to the CPA/DOX regimen shows decreased spheroid viability and improved cardiomyocyte viability and function. DISCUSSION/SIGNIFICANCE OF FINDINGS: Our findings suggest that DL7076 can facilitate DOX/CPA containing regimens by increasing CAR-mediated metabolism and subsequent CPA bioactivation while selectively protecting cardiomyocytes from DOX-induced toxicity. This research is expected to translate our basic scientific findings into therapeutic interventions for women with TNBC.

OBJECTIVES/GOALS: The objective of this evaluation is to evaluate the long-term impact of the PORT program on the clinical and translational research careers of the participating research staff. The impact of the program is best demonstrated through measures of the scientific contributions of the participants as well as their professional advancement over time. METHODS/STUDY POPULATION: The PORT program participants were tracked through the collection of instructional and public records, including the collection of their subsequent grant and publications. The clinical and translational research careers of the participants was also assessed, using a measure adapted from the operational guidelines for NCATS’ Research Careers Common Metric. A survey was administered to part participants and interviews conducted with participants from the past cohorts. RESULTS/ANTICIPATED RESULTS: The evaluation results demonstrate the PORT program participants made substantial contributions to the advancement of clinical and translational research, particularly through their publication of hundreds of scientific works. In addition, the evaluation results reveal that the program had short-, intermediate- and long-term impact on their research careers, thereby contributing to the advancement of the health research workforce at the University of Michigan for well over a decade. Specific participant cases highlight how individuals utilized their experience and training to advance research agendas and their long-term careers at the institution. These findings can inform the development, implementation and evaluation of similar programs throughout the CTSA consortium and beyond. DISCUSSION/SIGNIFICANCE: Most evaluations of research training and award programs for clinical and translational research staff do not evaluate the long-term impact of CTSA support on the research careers of the participants. The findings of this evaluation can help inform the development of new and more effective workforce development initiatives with long-term impact.

OBJECTIVES/SPECIFIC AIMS: Adults, 60 years of age and older, are in high demand for enrollment in many types of health research. Here we aimed to examine baseline, 60-day and 120-day follow-up trust in research and researchers of Floridians 60 years of age and older engaged in University of Florida’s HealthStreet community engagement initiative. METHODS/STUDY POPULATION: HealthStreet Community Health Workers (CHWs) assess health needs and trust in research of community members and screen for dementia, before providing medical and social services referrals and linkages to opportunities to participate in relevant health research at UF. In addition, participants are followed up at 60 and 120 days. RESULTS/ANTICIPATED RESULTS: Among the 2,193 older adults assessed by CHWs, 62.6% were female, 46.8% were African American, and 6.1% Hispanic/Latino. At baseline, 28.3% reported ever being in a research study; 7.7% reported not being interested in participating in research. Trust in research and researchers was high at baseline [scored from 1 to 10 where 10 was high; mean of 7.4 each for trust in research (SD=2.0) and trust in researchers (SD=2.1)] and high at both follow-ups [60 days 7.8 (SD=2.1) and 7.7 (SD=2) for trust in research and researchers respectively; 120 days 8.0 for both (SD=1.9 and 1.8 respectively)]. DISCUSSION/SIGNIFICANCE OF IMPACT: Individuals who are 60 and older have high trust in research and researchers when approached and high interest in research. Their trust continues through work with HealthStreet CHWs. Community engagement is an important part of the pipeline for recruitment of older adults for research.

OBJECTIVES/GOALS: Rab27B, a small GTPase, functions in exosome formation and secretion. Rab27B is overexpressed in non-small cell lung cancer (NSCLC) and predicts patient survival; however, little is known about its importance in NSCLC cells. Here, we investigated the role of Rab27B in NSCLC tumor initiating cells. METHODS/STUDY POPULATION: Tumor initiating cells (TICs) were enriched in a panel of NSCLC cell lines using low adherence spheroid cultures. QPCR and immunoblot analysis were used to compare Rab27B mRNA and protein expression, respectively, in adherent bulk cancer cells and TIC cultures. Lentiviral-packaged short hairpin RNAs (shRNAs) were used to knockdown Rab27B in PC9 and H1299 NSCLC TICs. The effects of Rab27B knockdown on PC9 and H1299 TIC expansion, transformed growth, and invasion were analyzed by MTT cell proliferation, soft agar colony formation, and Boyden chamber assays respectively. RESULTS/ANTICIPATED RESULTS: Quantitative PCR and immunoblot analysis showed that Rab27B expression is elevated in NSCLC TICs when compared to adherent bulk cancer cells. Efficient knockdown of Rab27B was achieved in PC9 and H1299 NSCLC TICs using two independent shRNA constructs. Rab27B knockdown cells exhibited decreased expansion as spheroid cultures, transformed growth, and invasion when compared to non-target shRNA control cells. Future experiments will focus on determining the importance of Rab27B in TIC exosome production and in vivo tumor growth and metastasis. DISCUSSION/SIGNIFICANCE OF IMPACT: Our results show that Rab27B is important in NSCLC TIC growth and invasion. Further studies are needed to determine the mechanism of Rab27B action. TICs have been linked to enhanced tumorigenic properties, suggesting that Rab27B could be a good candidate for therapeutic targeting of NSCLC TICs.

Objectives/Goals: Present a framework for hosting Community Grand Rounds, where community and academic partners showcase completed community-engaged research (CEnR) projects. This highlights innovative dissemination methods, engages diverse audiences, elicits community responses, and advances the translational science of CEnR. Methods/Study Population: Our approach involves planning and outreach to collaborate with promotion of academic and community engaged grantees to develop community dissemination events that translate the science of CE into accessible, relatable, culturally relevant formats for diverse audiences. These events incorporate interactive presentations that encourage active participation and feedback from attendees. Following each event, an evaluation is completed to assess community impact. Key strategies for hosting, facilitating, and utilizing diverse marketing to ensure that events are tailored to culturally diverse community groups, including regional implementation when practical. This collaborative approach meets a critical need and strengthens the bond between researchers and the communities they aim to serve. Results/Anticipated Results: These events create a feedback loop between the community and academic researchers. It was not just about telling people what was found. We created opportunities for community members and academics to build trust, give us feedback, ask questions, and discuss how findings could be practically applied. By presenting the findings in an accessible way within the community, community members are more informed and empowered to make decisions or advocate for changes in their own lives based on the research. Academics also benefited from community feedback, which provided new insights to help refine future research questions and methods. The goal is for shared conversation and understanding between community members and academics to inspire real-world applications and policy change directly informed by the research. Discussion/Significance of Impact: Community Grand Rounds are one dissemination strategy to leverage community–academic collaboration to present tailored research, fostering engagement, understanding, and action between researchers and community members. This approach effectively enhances the translational science of CEnR by involving and benefiting the community.

OBJECTIVES/GOALS: The correction of spinopelvic parameters is associated with better outcomes in patients with adult spinal deformity (ASD). This study presents a novel artificial intelligence (AI) tool that automatically predicts spinopelvic parameters from spine x-rays with high accuracy and without need for any manual entry. METHODS/STUDY POPULATION: The AI model was trained/validated on 761 sagittal whole-spine x-rays to predict the following parameters: Sagittal Vertical Axis (SVA), Pelvic Tilt (PT), Pelvic Incidence (PI), Sacral Slope (SS), Lumbar Lordosis (LL), T1-Pelvic Angle (T1PA), and L1-Pelvic Angle (L1PA). A separate test set of 40 x-rays was labeled by 4 reviewers including fellowship-trained spine surgeons and a neuroradiologist. Median errors relative to the most senior reviewer were calculated to determine model accuracy on test and cropped-test (i.e. lumbosacral) images. Intraclass correlation coefficients (ICC) were used to assess inter-rater reliability RESULTS/ANTICIPATED RESULTS: The AI model exhibited the following median (IQR) parameter errors: SVA[2.1mm (8.5mm), p=0.97], PT [1.5° (1.4°), p=0.52], PI[2.3° (2.4°), p=0.27], SS[1.7° (2.2°), p=0.64], LL [2.6° (4.0°), p=0.89], T1PA [1.3° (1.1°), p=0.41], and L1PA [1.3° (1.2°), p=0.51]. The parameter errors on cropped lumbosacral images were: LL[2.9° (2.6°), p=0.80] and SS[1.9° (2.2°), p=0.78]. The AI model exhibited excellent reliability at all parameters in both whole-spine (ICC: 0.92-1.0) and lumbosacral x-rays: (ICC: 0.92-0.93). DISCUSSION/SIGNIFICANCE: Our AI model accurately predicts spinopelvic parameters with excellent reliability comparable to fellowship-trained spine surgeons and neuroradiologists. Utilization of predictive AI tools in spine-imaging can substantially aid in patient selection and surgical planning.