Objectives/Goals: To describe one method of strengthening community–academic research partnerships, the Community Scientist Program, and to provide an example of a successful collaboration this program enabled, the Kiosk Project. Methods/Study Population: In collaboration with its community and academic partners, NJ ACTS developed the Community Scientist program, a training and research partnership program that includes human research protections training and team building between community and academic partners for community-engaged research. This program has enabled rapid formation of subsequent research teams – and rapid project implementation. One example is the Kiosk Project. A community–academic team mobilized to take advantage of an internal pilot funding opportunity, designing and executing a project to address disparities in knowledge and participation in clinical trials. Results/Anticipated Results: Five community partners, including four Community Scientists, teamed up with academic researchers to user-test a short video to be placed in local medical settings. This video was designed to educate community members about clinical trials and encourage participation. Together, the team created recruitment and focus group materials. Within 2 months, community partners recruited 40 participants for two rounds for a total of four focus groups. The team reviewed the first focus groups’ comments to determine editing needs. Focus groups then viewed the revised video, concurring that the video successfully incorporated their feedback. Participants provided testimonials about their focus group experience, highlighting the value of their contributions for projects impacting their communities. Discussion/Significance of Impact: Methods for strengthening community–academic research partnerships include programs for developing community research champions and advancing shared research goals. Enriched research partnerships enable rapid recruitment and high levels of community engagement in advancing community health priorities.

OBJECTIVES/GOALS: Tropsensor, a noninvasive portable device using infrared spectroscopy, delivers a troponin res ult within five minutes, significantly quicker than standard of care (SOC) assays. This pilot study assesses the correlation of the Tropsensor and high sensitivity cardiac troponin (hs-cTnI) assay results. METHODS/STUDY POPULATION: Patients undergoing cTnI testing with the Abbott Architect STAT (Abbott Laboratories) hs-cTnI assay were recruited at a quaternary-care emergency department (ED). The Tropsensor was applied to the underside of the patients’ wrist within 5 minutes of the SOC blood draw for 5 minutes. The results of the hs-cTnI assays were compared with the raw output of the Tropsensor device to assess the relationship using both Spearman’s and nonlinear logarithmic measures of correlation. Patient demographic data was extracted from the EHR to supplement the data collected for this study. RESULTS/ANTICIPATED RESULTS: 58 patients were recruited with a mean age of 60 years (60% male, 40% female). Due to connection error, 8 patients’data did not get captured by the device. Additionally, due to noise related to suboptimal device contact with the wrist, 24 patients’data (41%) were rejected. Of the 26 patients with usable data, 9 patients had a troponin above the 99th percentile threshold. A nonlinear correlation of 0.64 and Spearman’s rho of 0.59 were observed between the SOC hs-cTnI assay and Tropsensor optical data. DISCUSSION/SIGNIFICANCE: The Tropsensor exhibits 64.4% correlation to the SOC hs-cTnI assay. While further evaluation is needed, this exploratory study provides insight into the potential of a transdermal optical device to be used as a screening tool for AMI in an ED triage situation.

ABSTRACT IMPACT: Reversing tumor microenvironment (TME) immunosuppression will help to increase the overall efficacy of treatment of chemo-resistant triple negative breast cancer (TNBC) and mitigate racial disparities in treatment response. OBJECTIVES/GOALS: We have developed an ex-vivo whole tissue culture model to test the feasibility of reversing local immunosuppression in TME by chemokine modulatory (CKM) regimen. Our current objective is to analyze the molecular changes in CKM-treated chemoresistant TNBC from White and Black women and identify factors determining response to CKM. METHODS/STUDY POPULATION: Freshly resected residual TNBC from 20 White and 20 Black women ≥18 yrs old treated with neoadjuvant chemotherapy (NAC) will be procured. Tumor explants will be prepared & cultured in the absence and presence of CKM (Interferon-ð 〉1/4, TLR3 agonist rintatolimod and COX-2 inhibitor celecoxib). Chemokines implicated in cytotoxic T-lymphocyte (CTL)- & MDSC/ Treg attraction will be analyzed using Taqman & ELISA. We will have 80% power to detect a 0.7 standard deviation difference in chemokines between untreated & treated samples within and between cohorts using ANCOVA. Bulk RNA sequencing will be performed on both untreated & treated samples from CKM responding (highest aggregate increase in CTL- and highest decrease in Treg/MDSC-favoring chemokines in the top quartile) and non-responding (bottom quartile) tissues. RESULTS/ANTICIPATED RESULTS: Our preliminary data show that Black patients (pts) with breast cancer (BC) have an immunosuppressive TME associated with poor outcomes. This is similar to other existing literature showing that Black pts with BC have less favorable and more unfavorable chemokines in the TME. We anticipate the chemokine changes with CKM treatment will be larger in the Black cohort given their ability to elicit a robust inflammatory response. Therefore, we expect that CKM treatment will result in favorable TME in both groups and improve outcomes in TNBC, which has the worst prognosis of all subtypes, eliminating a key area of disparity in BC. The proposed transcriptome analysis will help identify key gene networks involved in response to CKM treatment and guide modulating the targets for non-responsiveness to improve efficacy of CKM. DISCUSSION/SIGNIFICANCE OF FINDINGS: Pts with residual disease (RD) after NAC have a 3-yr overall survival 68% vs. 94% for pts with complete response. Blacks have a higher incidence of TNBC with more likelihood of RD & mortality. We anticipate that the existing TME differences can be abrogated by our current CKM regimen or via developing an alternative CKM regimen optimized for Black pts.

OBJECTIVES/GOALS: Pediatric heart failure is a complex disease presenting as an end-stage condition due to various etiologies and symptoms, causing 14,000 hospitalizations per year in the United States. Currently, there is a lack of objective metrics that are monitored non-invasively. This study explores tools to adapt remote monitoring technologies for pediatrics. METHODS/STUDY POPULATION: The task was determining commercially available and upcoming technologies for remote heart failure monitoring in the pediatric population. Literature and patent reviews were done in various databases with defined eligibility and key terms. Our inclusion criteria were: English peer-reviewed research or review articles, patents filed by cardiac monitoring companies, and independent groups focusing on non-invasive monitoring solutions. Key terms used for the literature search and patent review included pediatric heart failure’, at-home monitoring’, cardiac monitoring’, and non-invasive’. Based on a strong correlation between increased filling pressures and pediatric heart failure, the term filling pressures’ was also included in the search. RESULTS/ANTICIPATED RESULTS: Preliminary searches demonstrate an abundance of adult-use commercially available devices and patents for monitoring heart failure. Yet, there are no FDA-approved devices for use in the pediatric population. Current devices include monitoring metrics such as lung congestion and multi-parametric monitoring to capture heart rate, thoracic impedance, and oxygen saturation levels. In monitoring filling pressures, Abbott CardioMEMs is a leader in measuring pulmonary arterial pressure invasively in adults. Thus, there is a gap for non-invasive monitoring of filling pressures in both pediatric and adult populations. For further review, a larger focus will be placed on non-invasive methods for direct monitoring or extrapolation of cardiac filling pressures. DISCUSSION/SIGNIFICANCE: Current methods of heart failure monitoring are ineffective in serving the pediatric population. Thus, an identified gap exists in non-invasive filling pressure monitoring for pediatric heart failure. This review informs that innovation within this area would address inefficacies within the current paradigm of heart failure monitoring.

OBJECTIVES/GOALS: Klotho is a protein linked to improved cognition in aging adults. A specific KLOTHO gene variant, KL-VS, increases circulating levels of Klotho. The current study aims to identify if the KL-VS haplotype and Klotho levels are associated with improved neurocognition in pediatric brain tumor survivors. METHODS/STUDY POPULATION: We are actively accruing pediatric brain tumor patients at UCSF alongside an existing multi-institutional cohort study investigating radiation-induced vasculopathies and cognitive outcomes in this population. Normal controls are being enrolled in parallel. Each patient undergoes: 1) single nucleotide polymorphism genotyping to identify KL-VS haplotype status, 2) enzyme-linked immunosorbent assays to measure circulating Klotho, 3) neurocognitive assessments with a computer-based, validated Cogstate battery, and 4) brain volume and white matter lesion segmentation analyses using MRI sequences obtained as part of routine care. RESULTS/ANTICIPATED RESULTS: Genotyping has been performed on 99 enrolled patients. KL-VS heterozygosity was seen in 22.7% of patients. To date, KL-VS status is not associated with neurocognitive outcomes at baseline or Year 1 testing. Association between KL-VS status, circulating Klotho levels, neurocognitive outcomes, brain volume and white matter lesion segmentation analyses is ongoing. We hypothesize that elevated Klotho levels will be associated with improved neurocognition, increased brain volumes in regions of interest and decreased white matter lesion volumes. DISCUSSION/SIGNIFICANCE OF IMPACT: If circulating Klotho leads to improved neurocognition in pediatric brain tumor survivors, Klotho levels might serve as a prognostic biomarker. Furthermore, as Klotho is being investigated for therapeutic indications, it may represent an intervention to prevent cognitive deficits in these patients.

OBJECTIVES/GOALS: A TIA is a transient episode of symptoms attributed to a cerebrovascular cause, and associated with an increased risk of stroke. Care of these patients often requires substantial resources in the Emergency Department (ED). We therefore described neuroimaging and hospitalization use for TIA within a nationally representative sample of US ED visits. METHODS/STUDY POPULATION: Retrospective cross-sectional analysis using TIA encounters in the 2018 National Emergency Department Sample (NEDS), an AHRQ dataset consisting of a weighted sample of 20% of all US ED encounters. Non-contrast Head CT, CTA Head, Carotid Ultrasound, MRI and CT Perfusion imaging utilization was determined based on Common Procedural Terminology (CPT) codes in the non-admitted encounters. The study population includes all adult patients with a discharge diagnosis of TIA as determined by ICD-10 codes (H34.0, G45.0-3, G45.8 G45.9) in any diagnosis position. The percentage of patients receiving each neuroimaging test was reported with the corresponding 95% confidence interval (CI). We utilized survey sample weights to generate reliable national estimates. RESULTS/ANTICIPATED RESULTS: The study population consisted of 80,803 ED encounters with a discharge diagnosis of TIA, representing 326,802 weighted ED visits nationally. Among this group, 46.8% of patients were discharged and 41.8% were admitted to the same hospital, 7% of patients were transferred to another facility, and the remaining 5% left AMA, were dispositioned to home health, died in the ED, or had an unknown disposition. Because discharged encounters retain their more precise CPT coding of procedural information, imaging analysis was conducted in discharged TIA encounters only. Of these encounters, 73% (95% CI, 70.7-76.5) received a noncontrast head CT, 20.9% (95% CI, 19.1-22.7) a CTA Head, 22.5% (95% CI, 20.6-24.4) a carotid ultrasound, and 31.5% (95% CI, 29.3-33.7) an MRI brain without contrast. DISCUSSION/SIGNIFICANCE: The discharge rate of just under 50% of patients is consistent with other published data, and represents a gradual trend over the past decade of decreased admissions for TIA. The fact that for many of these patients, the entire episode of care occurs in the ED setting suggests that the ED may be a rich target for future innovations in care for TIA.

OBJECTIVES/GOALS: Recent scientific discoveries show that human sex determination and differentiation is a spectrum of developmental processes and that sex/gender traits and identities not always fit binarity. This study aims to determine whether the visual arts can effectively transmit these complex scientific ideas on sex and gender variance. METHODS/STUDY POPULATION: A one-hour lecture for undergraduate students enrolled in a behavioral neuroendocrinology course included 17th century Spanish paintings and representative work from contemporary LGBTQIA+ artists in photography. Pre and post self-evaluation was conducted through five multiple choice questions. Chi Square test was employed for statistical analysis, which required elimination of no responses from item analysis. Statistical significance was defined as p value < 0.05. Three artistic images and two scientific images were included in the questions. Acquisition of content-specific knowledge on diverse body configurations, differences of sex development (DSD), transsexuality, histopathology of the gonad and neuroanatomy of the hypothalamus was evaluated. RESULTS/ANTICIPATED RESULTS: Twenty students completed the online pre- and post-test. We found that a 17th century Spanish painting was effective at making the distinction between transsexuality and intersexuality (p < 0.0005). Similarly, an artistic image that reinterprets the Vitruvius Man was effective for presenting the argument that diverse body configurations does not imply clinical pathology (p < 0.0001). Last, a scientific image showing the histopathology of an ovotestis was effective for introducing undergraduate students to diagnostic criteria for DSD (p < 0.02). No significant differences were found in the use of an artistic photograph depicting a young female to male transsexual individual nor in the use of a scientific image showing the neuroanatomical localization of the hypothalamus. DISCUSSION/SIGNIFICANCE: The learning of complex scientific concepts on human sex determination and differentiation can be affected by preconceived ideas, values, and attitudes towards sex and gender variance. The visual arts can provide a familiar ground of understanding between teachers and learners to transform such preconceptions.

OBJECTIVES/SPECIFIC AIMS: Wake Forest Baptist Health (WFBH) is an Academic Learning Healthcare System (aLHS) serving 24 counties in North Carolina and Virginia. Like many aLHSs, WFBH experiences strained community relationships attributable to a history of medical and research abuses against marginalized populations. This legacy accompanies longstanding community mistrust in the healthcare system and research. To overcome these challenges, community-engaged research (CEnR) approaches have potential to repair community-academic relationships, improve public health, and empower groups that traditionally have been neglected by or overlooked in research. To develop and revise our understanding of how CEnR is harnessed at WFBH, semi-structured interviews were conducted with investigators and study staff experienced in CEnR approaches. In-depth interview guides were designed iteratively to capture socio-contextual and detailed descriptions of perceptions, experiences, and strategies specific to the use of CEnR. METHODS/STUDY POPULATION: A keyword search performed within WFBH study records identified 51 investigators whom had submitted research proposals related to CEnR within the past ten years. Sixteen were confirmed eligible based on a review of proposal abstracts, of which 14 responded to email invitations agreeing to participate. Four additional participants were referred by initial participants. Eighteen investigators (16 faculty and 2 research associates) provided consent and completed Interviews. RESULTS/ANTICIPATED RESULTS: The participant sample was 50% female with a mean age of 55 years, 11% Black and 89% White, with representation across various academic backgrounds (e.g., anthropology, medicine, psychology, and public health) A majority of participants (89%) hold doctoral degrees (i.e., PhD, DrPH, EdD, MD, and MD-PhD). On average, participants had been employed at WFBH for 13.9 years, and represented various departments including dermatology, epidemiology and prevention, family medicine, neurology, social sciences and health policy, and psychiatry. Nearly all participants (89%) indicated they had never received formal education or training in CEnR, though 100% reported “on-the-job” training in CEnR. Interviews were audio-recorded, transcribed, coded, and analyzed following an inductive thematic approach, from which twenty-two themes emerged across six domains related to CEnR (Table 2), including: Conceptualization and Purpose, Value and Investment, Community-Academic Partnerships, Sustainability, Facilitators, and Challenges. Results also provided key characteristics that define CEnR (Table 3), and yielded 11 emerging needs necessary to enhance CEnR within aLHSs (Table 4). DISCUSSION/SIGNIFICANCE OF IMPACT: The results of this study provide information critical to understanding how CEnR frameworks and approaches can be harnessed not just in Schools of Public Health, but within aLHSs to build and repair community-academic partnerships, inform research and institutional priorities, and address community health concerns. Despite the small sample size, the number of participant interviews was sufficient to achieve saturation while also providing broad and unique perspectives across various fields and CEnR approaches. Overall, participants conceptualized the purpose and goals of CEnR quite similarly, though there was a great deal of variance in how CEnR was defined and operationalized across interviews, indicating a need to more clearly articulate important features that enhance understanding of what CEnR is and what it is not (Table 3). These discrepancies and inconsistencies indicate a potential need for additional formal training in the understanding and use of CEnR approaches, which is supported by the fact that nearly all participants reported receiving no formal training in CEnR. Across all interviews, participants expressed a need for health care providers and researchers to better understand community contexts, social determinants of health, and historical factors influencing community health and participation in research (Table 4). This work and the data presented here are important for informing CEnR approaches and will be useful for guiding the development of a model incorporating the core tenets of CEnR within the mission, vision, and priorities of aLHSs.

OBJECTIVES/GOALS: The rates of computational phenotyping algorithm reuse across health systems are low, leading to a proliferation of algorithms for the same trait. We propose a framework for reusing computational phenotyping algorithms and describe the real-world deployment of this framework for the development of the Colorado Diabetes EHR Research Repository. METHODS/STUDY POPULATION: The novel phenotype reuse framework consists of 4 steps: select algorithms that are appropriate for reuse by assessing whether they are fit for purpose; extend the algorithm to account for changes in data and care practice standards; localize the algorithm to use local database standards and terminologies; optimize the algorithm by applying a data driven approach to achieve the desired local performance. To identify individuals with type 1 diabetes (T1D) or type 2 diabetes (T2D), we selected and implemented T2D algorithms in a cohort of adults with any diabetes or pre-diabetes related diagnosis code, medication, or abnormal glucose-related laboratory test in the clinical data warehouse for UCHealth and the University of Colorado. RESULTS/ANTICIPATED RESULTS: We included a total of 926,290 patients who were identified by initial filters. Patients were more likely to be female (53%), identify as non-Hispanic white (69%) and had a median age of 58 years (IQR: 41, 70). Implementation, extension, localization, & optimization through iterative chart review prioritized high sensitivity for all-cause diabetes and high specificity for T1D and T2D. Of the original cohort, 252,946 (27%) were identified by the all-cause diabetes algorithm. Of these 11,688 were identified as T1D and 135,588 as T2D. After optimization the all-cause diabetes algorithm had 88% sensitivity, 90% specificity, 74% positive predictive value (PPV), and 96% negative predictive value (NPV). Our algorithms for T1D and T2D had high specificity (100% and 99%, respectively) and PPV (100 and 96% respectively). DISCUSSION/SIGNIFICANCE: Developing computational phenotyping algorithms is expensive and time consuming, yet algorithm reuse is low due to a lack of practical approaches for reusing algorithms. We demonstrate application of a novel framework for algorithm reuse, yielding good alignment of algorithm performance with study goals for identifying individuals with diabetes.

OBJECTIVES/GOALS: The aim of this study was to define the transcription profiles of the molecular markers of mitochondrial biogenesis and fusion/architecture, and the markers of mtDNA copy numbers in the peripheral blood mononuclear cells (PBMCs) from war veterans with/without post-traumatic stress disorder (PTSD). METHODS/STUDY POPULATION: The peripheral blood mononuclear cells (PBMCs) from war veterans with/without post-traumatic stress disorder (PTSD) were used to monitor transcription profile of the molecular markers of mitochondrial biogenesis and fusion/architecture, as well as the markers of mtDNA copy numbers. The human male immortalized monocytes were exposed in vitro to hormonal markers of PTSD in order to monitor the effects of each particular hormonal marker on the molecular markers of mitochondrial biogenesis and fusion/architecture, as well as the markers of mtDNA copy numbers. RQ-PCR analyses were used to define transcriptional profile of above mentioned markers. RESULTS/ANTICIPATED RESULTS: The transcription profiles of above mentioned markers were disturbed, with high individual variability within the groups. A significant increase in the expression of the PPARGC1A transcript was observed in a group of subjects with current PTSD, as well as in the subjects with “life-time” PTSD, compared to healthy controls. PPARGC1B, NRF2 and MFN2 transcripts increased only in PBMCs of “life-time"-PTSD, while the level of transcripts for other investigated genes and the ratio of markers of mtDNA copy numbers showed no significant difference between groups. The in vitro results showed parallelism with the results obtained using the PBMCs from the subjects of the PTSD study. DISCUSSION/SIGNIFICANCE OF IMPACT: Although preliminary (the analysis require a larger number of subjects), the results are first findings and a solid base for further extensive multidisciplinary research in order to clarify the molecular mechanisms for the prevention and treatment of trauma-induced pathological conditions.

Objectives/Goals: Community-engaged research (CER) helps ensure that research findings reach communities. To support it, we administer a pilot program to foster partnerships, build research capacity, and generate data for larger initiatives. We sought to understand the determinants that influence community research pilot project implementation. Methods/Study Population: The community research award provides $30,000 and 24 months of support to a community–academic team. Awardees receive CTSA support through a capacity-building orientation, online written and video materials, and optional office hours. We conducted semi-structured interviews with the community and academic leads using an Integrated-Promoting Action on Research Implementation in Health Services (i-PARIHS)-based guide to examine how the research project, recipients, context, and facilitation shaped implementation. Transcripts were analyzed using rapid qualitative analysis methods. Two coders independently reviewed each transcript and completed a summary template which were then analyzed by partner type and i-PARIHS construct. Results/Anticipated Results: A total of six community leads and seven academic leads who received funds between 2020 and 2024 were interviewed. Three community partners and three academic partners completed projects. Partner commitment and expertise were emphasized as project facilitators, while role ambiguity and turnover were barriers. Innovation was valued for adaptation to community context and increased capacity; however, some leads noted tensions between research and advocacy goals. Context barriers included limited funding, COVID-19, and shifting CBO, local, and national policies. CTSA-provided Facilitation was mentioned positively by nearly all community leads. Academic leads interacted with the CTSA team primarily when conflicts arose. Discussion/Significance of Impact: The i-PARIHS framework highlighted how strong partnerships, expertise, and adaptation to community context enabled projects, while role ambiguity, turnover, and contextual challenges impeded progress. Strengthening facilitation, clarifying roles and responsibilities, and planning for turnover may enhance future projects.

The Translational Science TS22 conference in Chicago in April 2022 was the first time post-pandemic that members of the Association of Clinical and Translational Science were able to meet up in person to share scientific advances. Given the remaining level of risk due to COVID-19, the meeting was designed as hybrid allowing virtual participation to some of the presentations. Prior to the meeting, JCTS Junior Editors were invited to report on the plenary sessions of the meeting. The present perspective constitutes a summary of three plenary sessions.

The COVID-19 pandemic raised the importance of adaptive capacity and preparedness when engaging historically marginalized populations in research and practice. The Rapid Acceleration of Diagnostics in Underserved Populations’ COVID-19 Equity Evidence Academy Series (RADx-UP EA) is a virtual, national, interactive conference model designed to support and engage community-academic partnerships in a collaborative effort to improve practices that overcome disparities in SARS-CoV-2 testing and testing technologies. The RADx-UP EA promotes information sharing, critical reflection and discussion, and creation of translatable strategies for health equity. Staff and faculty from the RADx-UP Coordination and Data Collection Center developed three EA events with diverse geographic, racial, and ethnic representation of attendees from RADx-UP community-academic project teams: February 2021 (n = 319); November 2021 (n = 242); and September 2022 (n = 254). Each EA event included a data profile; 2-day, virtual event; event summary report; community dissemination product; and an evaluation strategy. Operational and translational delivery processes were iteratively adapted for each EA across one or more of five adaptive capacity domains: assets, knowledge and learning, social organization, flexibility, and innovation. The RADx-UP EA model can be generalized beyond RADx-UP and tailored by community and academic input to respond to local or national health emergencies.

Within the Northwestern University Clinical and Translational Sciences Institute, we created a foundational and fluid mentor training curriculum to provide competency-based mentor training for faculty. Via our “Developing and Enhancing Mentoring Relationships” mentor workshop series, launched in 2020, we present eight 90-minute workshops each academic year. This series is designed for both training naive participants and previously trained mentors across ranks and tracks and offers both repeating (“required”) and new (“elective”) workshops annually. We implemented a Mentor Training Certificate Program (MTCP) in 2021 to formally recognize faculty who complete a minimum of nine hours of training, consisting of three required and at least three elective training sessions. Over the first four years of the workshop series, 345 unique faculty attended at least one workshop; 46 completed requirements for the MTCP. MTCP participants complete baseline and annual surveys focused on self-assessment of nine mentoring skills (e.g., providing feedback) and frequency of engaging in five recommended mentoring behaviors (e.g., aligning expectations). Scores increased significantly across all skills; participants reported increased frequency of mentoring behaviors and high satisfaction with the program. Our mentor workshop series, offering both repeating and new workshops annually, provides faculty the opportunity for either initial or advanced training.

Recruitment and retention challenges continue to hinder the success of clinical trials. Artificial intelligence (AI) has emerged as a promising means to optimize various clinical trial processes; however, its impact specifically on recruitment and retention has not been comprehensively evaluated. This scoping review utilized the Joanna Briggs Institute framework and adhered to PRISMA-ScR guidelines, systematically searching literature published between January 2018 and June 2024 across multiple databases. Of the 21,573 records screened, 121 studies were included. A meta-analysis was conducted to quantitatively assess the performance of AI-driven tools. AI applications for patient screening demonstrated strong performance, achieving a pooled sensitivity of 0.91 (95% CI: 0.84–0.95) and an area under the curve (AUC) of 0.79 (95% CI: 0.72–0.85). AI tools employed for eligibility identification and classification also exhibited strong outcomes, with pooled sensitivities of 0.80 (95% CI: 0.76–0.84) and 0.92 (95% CI: 0.84–0.96), respectively, and precisions of 0.84 (95% CI: 0.80–0.88) and 0.91 (95% CI: 0.85–0.95). AI tools aimed at identifying patient cohorts showed moderate effectiveness (pooled sensitivity: 0.70 [95% CI: 0.52–0.84]; AUC: 0.74 [95% CI: 0.61–0.84]). Overall, AI presents significant potential for enhancing clinical trial recruitment and retention, with effectiveness varying across specific applications. These findings underscore AI’s valuable role in improving trial efficiency and data quality.

Housing is an environmental social determinant of health that is linked to mortality and clinical outcomes. We developed a lexicon of housing-related concepts and rule-based natural language processing methods for identifying these housing-related concepts within clinical text. We piloted our methods on several test cohorts: a synthetic cohort generated by ChatGPT for initial infrastructure testing, a cohort with substance use disorders (SUD), and a cohort diagnosed with problems related to housing and economic circumstances (HEC). Our methods successfully identified housing concepts in our ChatGPT notes (recall = 1.0, precision = 1.0), our SUD population (recall = 0.9798, precision = 0.9898), and our HEC population (recall = N/A, precision = 0.9160).

OBJECTIVES/GOALS: With a growing intеrеst in tailoring disеasе diagnosis to еach individual as opposеd to a “onе-sizе-fits-all” approach, our aim is to еnhancе thе robustnеss of thе Itеrativе Clustеring for Subtypе Discovеry (iKCAT) algorithm in charactеrizing lung cancеr subtypеs for individualizеd trеatmеnt. METHODS/STUDY POPULATION: Our mеthod еxplorеs thе robustnеss of thе prеviously dеvеlopеd iKCAT algorithm. This itеrativе clustеring mеthod finds robust—homogеnеous and diffеrеntiablе—subtypеs of lung nodulеs through itеrativе K-mеans clustеring that hеlps classify thеm and lеavеs somе data unclustеrеd. This sеt of unclustеrеd or “hard” data rеprеsеnts imagеs that cannot confidеntly bе assignеd to any subtypеs and may rеquirе morе rеsourcеs (е.g., timе or radiologists) to diagnosе. Wе еxplorе thе robustnеss of iKCAT across multiplе fеaturе spacеs, including dеsignеd imagе fеaturеs (which arе еnginееrеd to capturе somе propеrtiеs such as lеvеl of еlongation, еccеntricity and circularity), rеducеd dеsignеd imagе fеaturеs using Principal Componеnt Analysis (PCA) and Uniform Manifold Approximation and Projеction (UMAP). RESULTS/ANTICIPATED RESULTS: Whеn running our еxpеrimеnt on thе 64 imagе fеaturеs, our rеsults consistеntly carvеd out a singlе purе, homogеnеous clustеr ovеr thе coursе of 30 iKCAT runs. From an initial datasеt of 1490 data points, 1430 points wеrе lеft unclustеrеd in this fеaturе spacе. Whеn conducting thе 30 iKCAT runs on thе PCA fеaturе spacе with 10 componеnts, wе found it did not producе any distinct clustеr abovе thе dеfinеd homogеnеity thrеshold. Thе 2D UMAP fеaturе spacе consistеntly gеnеratеd 8 clustеrs with an avеragе homogеnеity of 87. 22% ovеr 30 runs, and only lеft 9 points unclustеrеd. Ovеr 30 iKCAT runs, wе idеntifiеd 8 pеrsistеnt clustеrs or subtypеs, 3 mostly malignant and 5 mostly bеnign clustеrs. DISCUSSION/SIGNIFICANCE: Through our еxpеrimеnt using thе iKCAT algorithm, wе found that iKCAT’s clustеring functionality producеd thе most pеrsistеnt rеsults on thе 2D UMAP fеaturе spacе duе to its high avеragе homogеnеity scorеs and consistеncy in idеntifying clustеrs/subtypеs, hеlping improvе tailorеd disеasе diagnosis.

Objectives/Goals: The purpose of this study is to explore and understand the experience of loneliness in adults over 65 years of age with chronic illnesses residing in public and private community dwellings in Puerto Rico. Methods/Study Population: The Phenomenological qualitative approach aims to deepen participants’ understanding of how they define loneliness, the associated risk factors, the strategies they use to cope with it, and its perceived effectiveness. The project has three phases: the first phase involves obtaining informed consent, the second phase consists of the interview, and the third phase concludes the interview with a reminder that a follow-up meeting will be held to validate the information collected. This study will use a convenience sampling method to recruit 20 participants aged 65 years or older with chronic illnesses residing in public (10 participants) and private (10 participants) community dwellings in Puerto Rico. Results/Anticipated Results: This study is needed to better understand how older adults with chronic illnesses experience loneliness, what factors influence their perception, and what strategies they use to cope with it. Discussion/Significance of Impact: The findings may inform community interventions and public policies aimed at improving the quality of life for this population.

Objectives/Goals: People experiencing homelessness (PEH) face disproportionate cervical cancer burden and screening barriers. Our goal was to design a tailored intervention involving community health worker (CHW)-led education and delivery of context-appropriate screening options in two homeless shelters in Indiana. Methods/Study Population: Guided by a community advisory board and following a human-centered design (HCD) framework, interviews with 30 PEH were conducted in the inspiration phase to explore experiences, knowledge, and attitudes toward cervical cancer screening, including human papillomavirus (HPV) self-sampling, a novel approach where patients collect their own vaginal swab. Rapid qualitative analysis informed an HCD session with 12 PEH in the ideation phase to further explore screening motivators and key messages to encourage uptake of HPV self-sampling. Data were synthesized into an educational flipbook and iteratively refined with participant feedback. Results/Anticipated Results: Findings from interviews and the HCD session highlighted a strong desire to be screened and the need for clear information, access to a trusted CHW, and choice in screening options. The final intervention consisted of an individual cervical cancer education session with a CHW utilizing the educational flipbook, followed by optional screening through HPV self-sampling at the shelter and/or navigation to a clinic. To date, a total of 200 participants have enrolled in the education session. Preliminary results show significant knowledge gains and retention and positive shifts in attitudes toward screening. After an education flipbook redesign, HPV self-sampling uptake significantly increased. Discussion/Significance of Impact: Applying a HCD approach enabled meaningful engagement to iteratively develop and refine an intervention that addressed community needs, increased HPV self-sampling uptake, and expanded cervical cancer screening access for people experiencing homelessness in Indiana.