OBJECTIVES/SPECIFIC AIMS: In this study, we propose to investigate effectiveness of 2 core services provided by the Center for Clinical and Translational Science (CCTS), home for CTSA program in the School of Medicine at the University of Utah. METHODS/STUDY POPULATION: We will apply a longitudinal database of research and tenure track faculty (n>600) in the School of Medicine at the University of Utah from 2006 to 2016 to estimate the effect of initial usage of the biostatistics and clinical services cores of the University of Utah CCTS on the probability of (a) ≥1 peer reviewed publication, (b) external grant funding, and (c) academic promotion within 1, 2, and 3 years after the initial contact. We will apply a “new users” design (Hernan et al., Epidemiology, 2008; 19: 766–779) to compare the outcomes of faculty initiating use of the 2 CCTS cores Versus faculty without prior use of these cores in a series of cohorts defined by the calendar year of initial contract with the 2 cores, with covariate adjustment performed within each cohort to account for measured confounders. Separate outcome models will be specified for each cohort, but the statistical models will be fit to stacked augmented data sets which include the data from each cohort. Using the stacked data set, results will be pooled across each of the cohorts to increase statistical power. Robust sandwich estimates of standard errors will be used to account for the inclusion of multiple assessments for each faculty member. RESULTS/ANTICIPATED RESULTS: Estimates of the effect of initiation of new CTSA usage on academic productivity outcomes will be obtained, and provided in conjunction with sensitivity analyses to address the potential impact of uncontrolled confounding. DISCUSSION/SIGNIFICANCE OF IMPACT: The proposed evaluation strategy should overcome some of the biases inherent in typical metrics for effectiveness of CTSA programs, and will be applied to evaluate success of future initiatives.

OBJECTIVES/GOALS: - Illuminate processes and findings of a translational science case study of impactful research with incarcerated pregnant women and mothers; - Improve our understanding of the translational mechanisms by sharing translational challenges, facilitators, an METHODS/STUDY POPULATION: Utilized the following evaluation methods and tools: - The Retrospective Translational Science Case Study protocol to examine translational path from innovation to policy and practice, barriers and facilitators for that translational movement. - Translational Science Benefits Model (TSBM) Checklist for translational/research impact analysis Triangulated diverse data sources: - Primary data: semi-structured interviews with research partners - Secondary data: researchers’ grant applications, reports, and publications; public stories/news related to their research; scientific publications; organizational/policy documents; and over 50 interviews with 30 stakeholders featured in published sources. RESULTS/ANTICIPATED RESULTS: The research contributed to community and public health, policy/legislative, clinical/medical, and economic benefits, social/institutional change, health equity advocacy, catalyzing research (consequent research studies) and public awareness. Translational research challenges: cultural differences between research and prison system; politics of translating research to policy change; issues of capacity, power, privilege, and opportunity when doing community-engaged research; and science vs. social justice criticism. Facilitators of translation: CTSA support; stakeholder engagement; authentic collaboration; researchers as translation catalysts; and engagement in legislative activities. DISCUSSION/SIGNIFICANCE: The evaluation case study provides useful knowledge about translational impact, challenges, and facilitators of community-based research that moved along the translational continuum and contributed to transformational, systemic changes on the legal, clinical, organizational, and interpersonal levels.

OBJECTIVES/GOALS:

1. 1. Examine the associations among BMI and markers of cardiometabolic risk, including blood pressure, lipids and blood glucose.

2. 2. Assess prevalence of kidney function deterioration, identified as hyperfiltration and moderately increased albuminuria (MIA), in obese compared to normal weight adolescents.

METHODS/STUDY POPULATION: De-identified electronic health records (EHR) data were extracted for female adolescents, aged 12-21 years, and their offspring through 24 months, who received health care services (Jan 2012 to Dec 2016) in NYC from 12 academic health centers and community health centers that are part of PCORnet NYC Clinical Data Research Network (NYC-CDRN). Data were analyzed using SAS (version 3.2.5). Patient characteristics overall and for study subgroups were examined using standard summary statistics. Trends in cardio-renal variables were examined by BMI groups coded according to NHANES as underweight, normal weight, overweight or obese. Multiple linear regression analyses will control for covariates. RESULTS/ANTICIPATED RESULTS: Data from 651,066 adolescent females ages 12-21 were retrieved. Analysis was performed on a subset of 202,214 unique patients (26% white, 15% black, 12.9% Latina) for whom there was complete data for BMI and blood pressure. Distribution of BMI was 6% underweight, 59% normal weight, 19% overweight, and 17% obese. There were significant differences in mean systolic (SBP, mean±SD mmHg: 102±12, 108±11, 112±12, 116±12) and diastolic blood pressure (DBP, mean±SD mmHg: 62±10, 66±8, 68±8.9, 70±9) across the four BMI groups with an increasing trend (p-values<0.0001). We will examine renal function trends, and whether these cardio-renal differences persist when controlling for age, race and ethnicity. DISCUSSION/SIGNIFICANCE OF IMPACT: Although SBP/DBP means were within normal limits across BMI groups, significant increasing trends suggest that women in higher BMI groups may be at increased risk for hypertension and potentially for renal dysfunction. We will examine contributions of race/ ethnicity and age to these associations.

OBJECTIVES/GOALS: To describe the creation, use and outcome of a successful multi-session case study for team science education and training. Creating a case study that spans multiple sessions can aid in emphasizing many team science concepts using one ongoing scenario. METHODS/STUDY POPULATION: We will describe the creation and use of a multi-session case study used in a team science graduate course. This case study incorporates the interpretation and use of assessments that coincide with concepts presented in each session. Participants engage with the case study as a team. The use of this case study allows participants to draw conclusions and make decisions about team interventions using concepts they’ve just learned. The multi-session case study also allows participants to see the outcome of their decisions in the next session. Further, the continuous nature of this case study allows participants to build on their knowledge from session to session and make connections between concepts. RESULTS/ANTICIPATED RESULTS: Incorporating a multi-session case study should help participants better understand team science concepts and practice incorporating the use of those concepts into teams in a more realistic way over time. The case study framework has been used in a team science graduate course for the last two years. The teaching team has incorporated continuous improvement into optimizing the case study over time. We’ll share preliminary results collected over the use of the case study so far along with the improvements made over time. DISCUSSION/SIGNIFICANCE: This education framework is very versatile and can be incorporated into a team science course or series of workshops and provides a real-world situation that allows participants to practice incorporating team science concepts and interventions in a team.

OBJECTIVES/SPECIFIC AIMS: To describe the epidemiology of patients with carbapenem-resistant Enterobacteriaceae (CRE) bacteriuria in metropolitan Atlanta, GA and to identify risk factors associated with progression to an invasive CRE infection. We hypothesize that having an indwelling urinary catheter increases the risk of progression. METHODS/STUDY POPULATION: The Georgia Emerging Infections Program (EIP) performs active population- and laboratory-based surveillance to identify CRE isolated from a sterile site (e.g. blood) or urine among patients who reside in the 8-county metropolitan Atlanta area (population ~4 million). The Georgia EIP performs a chart review of each case to extract data on demographics, culture location, resistance patterns, healthcare exposures, and other underlying risk factors. We used a retrospective cohort study design to include all Georgia EIP cases with Escherichia coli, Klebsiella pneumoniae, Klebsiella oxytoca, Enterobacter cloacae, or Klebsiella (formerly Enterobacter) aerogenes, adapting the current EIP definition of resistance to only include isolates resistant to meropenem, imipenem or doripenem (minimum inhibitory concentration ≥ 4) first identified in a urine culture from 8/1/2011 to 7/31/2017. Patients with CRE identified in a sterile site culture prior to a urine culture will be excluded. Within this cohort, we will identify which patients had a subsequent similar CRE isolate identified from a sterile site between one day and one year after the original urine culture was identified (termed “progression”). CRE isolates will be defined as similar if they are the same species and have the same carbapenem susceptibility pattern. Univariable analyses using T-tests or other nonparametric tests for continuous variables, and Chi-square tests (or Fisher’s exact tests as appropriate) for categorical variables will compare patient demographics, comorbidities and presence of invasive devices including urinary catheters between patients who had progression to an invasive infection and those who did not have progression. Covariates with a p-value of < 0.2 will be eligible for inclusion in the multivariable logistic regression model with progression to invasive infection as the primary outcome. All statistical analyses will be done in SAS 9.4. RESULTS/ANTICIPATED RESULTS: From 8/1/2011 to 7/31/2017 we have preliminarily identified 546 patients with CRE first identified in urine, representing an annual incidence rate of 1.1 cases per 100,000 population. Most cases were K. pneumoniae (352, 64%), followed by E. coli (117, 21%), E. cloacae (48, 9%), K. aerogenes (18, 3%), and K. oxytoca (11, 2%). The mean patient age was 64 +/− 18 years and the majority (308, 56%) were female. Clinical characterization through chart review was available for 507 patients. The majority of the patients were black (301, 59%), followed by white (166, 33%), Asian (12, 2%), and other or unknown race (28, 6%). 466 (92%) patients had at least one underlying comorbid condition with a median Charlson Comorbidity Index of 3 (IQR 1-5). 460 (91%) infections were considered healthcare-associated (366 community-onset and 94 hospital-onset), while 44 (9%) were community-associated. 279 (55%) patients had a urinary catheter within the two days prior to the CRE culture. The analysis of patients who progress to an invasive CRE infection, including the results of the univariable and multivariable analyses assessing risk factors for progression is in progress and will be reported in the future. DISCUSSION/SIGNIFICANCE OF IMPACT: In metropolitan Atlanta, the annual incidence of CRE first isolated in urine was estimated to be 1.1 cases per 100,000 population between 2011 and 2017, with the majority of the cases being K. pneumoniae. Most patients had prior healthcare exposure and more than 50% of the patients had a urinary catheter. Our anticipated results will identify risk factors associated with progression from CRE bacteriuria to an invasive infection with a specific focus on having a urinary catheter, as this is a potentially modifiable characteristic that could be a target of future interventions.

OBJECTIVES/GOALS: Empowering the Participant Voice (EPV) is a Rockefeller-led 6-CTSA consortium that aims to collect research participant feedback through new Research Participant Perception Survey (RPPS)/REDCap infrastructure and data aggregation to a national database. Here we describe diverse Use Cases and launch dissemination to other hubs. METHODS/STUDY POPULATION: The EPV team refined the RPPS-S and developed fielding and data standards, a multi-lingual RPPS/REDCap project XML, At-a-Glance Dashboard, EPV Consortium Database, and Use Cases to align with local initiatives and stakeholder input. Sites ran full thread tests of the infrastructure before launch. To demonstrate RPPS/REDCap, 5 sites implemented Use Cases, surveyed diverse populations via email, patient portal or SMS, and analyzed results using the At-a-Glance Dashboard External module (which provides visual analytics and enables filtering by participant/study characteristics). Sites continue to collect, synthesize and respond to actionable data. To disseminate infrastructure, we will invite early adopters to implement the RPPS/REDCap infrastructure locally, joining the EPV learning collective. RESULTS/ANTICIPATED RESULTS: To date, 5 sites surveyed 10,199 research participants, at post-consent or end of study. 2833 (26%) research participants responded, from diverse demographic groups. More than 90% gave the Top Box score response regarding courtesy, respect for cultural background, privacy, and lack of pressure to join a study. Disparities were apparent in the informed consent experience, with a Top Box score range of 38-78% in different demographics. Dissatisfaction with out-of-pocket research costs was a recurring theme. Top Box scores varied for feeling like a valued partner in research (69-93%), would recommend research participation to friends or family (56%-81%), and Overall Experience (64%-90%) questions. Sites identified actionable findings in areas of consent, communication, partnership, and study conduct. DISCUSSION/SIGNIFICANCE: The EPV RPPS/REDCap infrastructure enabled sites to broadly collect participant feedback, identify actionable findings and make inter-institutional comparisons. Collaborators are designing local initiatives to increase response rate and diversity, address disparities in research participation experiences, and discover better practices.

Objectives/Goals: This qualitative study evaluated facilitators and barriers to clinical research participation among lower-income, predominately racial/ethnic minority communities to inform a Co-Learning series. The Co-Learning series of community members, stakeholders, and researchers developed strategies to improve diversity in research. Methods/Study Population: Community focus group (FG) participants were recruited from urban communities experiencing poverty, whereas stakeholder FGs included diverse community leaders and researchers. The Social Ecological Model was used as the guiding theoretical framework throughout the qualitative design. Directed content analysis using three independent coders reaching 100% consensus identified prominent factors for increasing diversity in research. The co-learning series was comprised of community members, stakeholders, and researchers who discussed the prominent FG factors over seven in-person meetings to develop a toolkit to increase diversity in research. Results/Anticipated Results: Community (n = 51) and stakeholder (n = 50) FG participants were 54.0±16.0 years of age, 81.2% female, 39.6% Black/African American, 51.5% Hispanic, and 60% had Discussion/Significance of Impact: Due to the lack of inclusivity in clinical research, findings are typically not applicable to health disparity populations limiting the benefit of research to all. This study provides practical community-driven strategies to increase diversity in clinical research, highlighting the role of trust, relationships, and cultural relevancy.

OBJECTIVES/SPECIFIC AIMS: Clinical research in the 21st century will require a well-trained workforce to insure that research protocols yield valid and reliable results. Several organizations have developed lists of core competencies for clinical trial coordinators, administrators, monitors, data management/informaticians, regulatory affairs personnel, and others. While the Clinical Research Appraisal Inventory assesses the self-confidence of physician scientists to be clinical investigators, no such index exists to assess the competence of clinical research professionals who coordinate, monitor, and administer clinical trials. We developed the Competency Index for Clinical Research Professionals (CICRP) as a general index of competency (ie, GCPs) as well as sub-scales to assess competency in the specific domains of Medicines Development; Ethics and Participant Safety; Data Management; and Research Methods. METHODS/STUDY POPULATION: We analyzed data collected by the Joint Task Force on the Harmonization of Core Competencies from a survey of research professionals working in the United States and Canada. Respondents reported how competent they believed themselves to be on 51 clinical research core competencies. Factor analyzes identified 20 core competencies that defined a Competency Index for Clinical Research Professionals—General (CICRP-General, ie, GCPs) and 4 subindices that define specialized research functions: Medicines Development; Ethics and Participant Safety; Data Management; and Research Concepts. RESULTS/ANTICIPATED RESULTS: Factor analysis identified 20 core competencies that defined a Competency Index for Clinical Research Professionals—General (CICRP-General, ie, GCPs) and 4 subindices that define specialized research functions: Medicines Development; Ethics and Participant Safety; Data Management; and Research Concepts. DISCUSSION/SIGNIFICANCE OF IMPACT: These indices can be used to gage an individual’s readiness to perform general as well as more advanced research functions; to assess the education and training needs of research workers; and to evaluate the impact of education and training programs on the competency of research coordinators, monitors, and other clinical research team members.

OBJECTIVES/SPECIFIC AIMS: Morphea (localized scleroderma) is an autoimmune disease characterized that is widely thought to have a monophasic course, in which an initial period of inflammation (activity) ultimately results in scarring, atrophy, and functional impairment (damage). Understanding the long-term clinical course of morphea is important for the planning of future interventional studies, and as a tool for clinicians in determining risk for poor disease outcomes. METHODS/STUDY POPULATION: We conducted a prospective cohort study of 130 participants enrolled in the Morphea in Children and Adults Cohort over a median follow-up time of 4.3 years, to determine the rates of response to treatment and disease recurrence as measured by the Localized Scleroderma Cutaneous Assessment Tool (LoSCAT). To determine risk factors for recurrence of disease activity, survival analysis using the log-rank test was used to compare subgroups by morphea type, therapy, and age at disease onset. RESULTS/ANTICIPATED RESULTS: Within a 1-year follow-up period, 66% of patients treated with methotrexate and 46% of patients with UVA1 phototherapy had achieved complete response to treatment. In patients who had achieved response to treatment, 29% experienced disease recurrence at an average of 1.7 years after documented disease inactivity. Patients with generalized morphea experienced higher recurrence rates than those with linear morphea (HR: 3.03, 95% CI: 1.48–6.22), and those treated with UVA1 phototherapy had higher recurrence over those treated with methotrexate (HR: 2.33, 95% CI: 1.03–5.31). In patients with follow-up periods longer than 5 years (n=50), disease recurrence was observed in 44% of patients and the majority of recurrence represented new activity in an area of pre-existing morphea (82%). DISCUSSION/SIGNIFICANCE OF IMPACT: This study highlights the previously under-studied dynamic long-term course of morphea, and identifies the clinical characteristics that predispose patients to having a relapsing-remitting course. We conclude that patients with morphea should be followed closely over time even in the absence of disease activity due to the potential for disease recurrence.

Within the Biostatistics, Epidemiology, and Research Design (BERD) component of the Northwestern University Clinical and Translational Sciences Institute, we created a mentoring program to complement training provided by the associated Multidisciplinary Career Development Program (KL2). Called Research design Analysis Methods Program (RAMP) Mentors, the program provides each KL2 scholar with individualized, hands-on mentoring in biostatistics, epidemiology, informatics, and related fields, with the goal of building multidisciplinary research teams. From 2015 to 2019, RAMP Mentors paired 8 KL2 scholars with 16 individually selected mentors. Mentors had funded/protected time to meet at least monthly with their scholar to provide advice and instruction on methods for ongoing research, including incorporating novel techniques. RAMP Mentors has been evaluated through focus groups and surveys. KL2 scholars reported high satisfaction with RAMP Mentors and confidence in their ability to establish and maintain methodologic collaborations. Compared with other Northwestern University K awardees, KL2 scholars reported higher confidence in obtaining research funding, including subsequent K or R awards, and selecting appropriate, up-to-date research methods. RAMP Mentors is a promising partnership between a BERD group and KL2 program, promoting methodologic education and building multidisciplinary research teams for junior investigators pursuing clinical and translational research.

OBJECTIVES/SPECIFIC AIMS: There has been substantial research showing that there are race and sex differences on alcohol use. Similarly, race and sex disparities are also seen in a variety of different factors that impact drinking behaviors and other health outcomes. One of these factors of interest is Adverse Childhood Experiences (ACEs) which is associated with an increased risk for excessive alcohol use and the harmful effects of drinking. Several studies have shown that racial minorities and females have a greater risk of ACEs, which may be partly related to various structural factors (i.e. poverty) and social norms. Although there has been a substantial amount of research done on ACEs, very few studies have looked at how their interaction with race and sex can influence alcohol-related behaviors. METHODS/STUDY POPULATION: 1,509 participants who self-identified as either Black or White were recruited through a screening protocol at the NIAAA where they completed a series of questionnaires. We categorized the participants into two groups based on the Structured Clinical Interview for DSM-IV disorders: Alcohol Dependent individuals (N=921) with either a past and/or current diagnosis and Non-dependent individuals (N=588). ACEs exposure was assessed using the Childhood Trauma Questionnaire (CTQ). We looked at both total score and the 5 subscales: emotional abuse, physical abuse, sexual abuse, physical neglect, and emotional neglect. Drinking behaviors were assessed using a 90-day Timeline Followback interview and the Alcohol Use Disorder Identification Test (AUDIT). The non-dependent sample was 63% White and 55% male while the alcohol dependent sample was 47% White and 70% male. We tested the interaction effects using ANOVA. RESULTS/ANTICIPATED RESULTS: In the ND sample, there were significant race*sex*ACEs effects for average drinks per day with CTQ total score (P = 0.007), physical abuse (P = 0.005), and physical neglect (P = 0.003). There was also a 3-way interaction with physical neglect on heavy drinking days (P = 0.039) and a 2-way race*ACEs interaction on AUDIT total with physical abuse (P = 0.048). In the AD sample, there were significant 2-way race*ACEs interactions for three drinking outcomes: heavy drinking days with physical neglect (P = 0.009), AUDIT-Harmful Use subscore with CTQ total score (P = 0.028) and physical neglect (P = 0.001), AUDIT-Total score with CTQ total score (P = 0.007), physical abuse (P = 0.042), sexual abuse (P = 0.024), and physical neglect (P = 0.003). There were also 3-way interactions for AUDIT-Harmful use (P = 0.013) and AUDIT-Total scores (P = 0.011) with emotional abuse. DISCUSSION/SIGNIFICANCE OF IMPACT: Our results indicate that there are both 2-way (race*ACEs) and 3-way (race*sex*ACEs) interaction effects on alcohol consumption and the related negative effects for both non-dependent and dependent samples. There were no sex*ACEs interaction effects in either sample implying that race may play a bigger role in differentiating drinking outcomes by ACEs across males and females. However, contrary to our expectations, race seemed to be protective factor for Black participants against both alcohol consumption and the negative effects despite having higher rates of ACEs exposure. Future analyses will explore personality measures as potential mediators of the relationship between ACEs and alcohol use. Also, analyses will look to see if there are any behavioral factors that may contribute to resiliency among minority populations.

OBJECTIVES/SPECIFIC AIMS: The ACT Network was developed by 46 members of the CTSA Program hubs in collaboration with NCATS to help investigators explore and validate feasibility of clinical studies in real-time using linked electronic health record data for cohort discovery. ACT is being disseminated nationally across the CTSA consortium. METHODS/STUDY POPULATION: Diffusion of Innovation Theory and Lean Start-Up principles inform dissemination strategies. Core materials were developed nationally and are being tailored to meet local CTSA dissemination norms. An advisory board, with expertise in communications, journalism, customer channel management, pharmaceutical commercialization and health IT entrepreneurship, is providing strategic advice to develop and refine dissemination strategies. Evaluation of dissemination methods will include network usage and web analytics for the ACT Network’s interactive digital content and log-in portal, and surveys-interviews of ACT users using the RE-AIM implementation framework. RESULTS/ANTICIPATED RESULTS: Formative research identified ACT’s primary value proposition for clinical researchers: “Explore patient populations in depth, in real time, from your desktop;” “Confirm study feasibility by iteratively testing and refining inclusion and exclusion criteria;” “Demonstrate feasibility in funding proposals and IRB submissions;” and “Identify collaborating sites for multi-site studies by searching for patients across the CTSA network.” Early dissemination metrics, including number-type of registered users, queries performed, and web analytics, will be presented. DISCUSSION/SIGNIFICANCE OF IMPACT: Researchers nationwide face common barriers in accruing enough participants for clinical trials. The inability to identify the right number and type of people to participate often makes clinical trials slow and costly. Better cohort discovery at the protocol development phase is a necessary requirement. By end of 2018, the ACT Network will reach 60% of the CTSA consortium providing a new tool for investigators to improve the design and execution of clinical trials.

OBJECTIVES/SPECIFIC AIMS: Biostatistics and Epidemiology courses within clinical research or public health training programs are typically developed and taught separately. As a result, students may have trouble in their research outside the classroom, where biostatistical and epidemiological concepts must be well integrated. Case method teaching is a participant- and discussion-centered pedagogical approach that has been used in business and law schools for more than 50 years to improve student learning, yet has taken longer to be adopted in health professional schools. The case method is distinguished by presenting learners with a real-world problem without a single unique solution. Designed to mimic the constraints and incomplete information found in real life, it is an ideal approach for integrating multiple related disciplines. A team of Clinical and Translational Science (CTS) faculty from the Tufts CTSI collaborated to develop a new course that integrates epidemiology and biostatistics disciplines using the case method. METHODS/STUDY POPULATION: We developed an intermediate-level, case-based course integrating epidemiology and biostatistics topics using modern, real-world clinical examples. Recognizing the importance of technical skill building, this intermediate-level Tufts CTS course adopted a hybrid approach, incorporating lecture and in-class laboratory exercises, alongside cases. We surveyed CTS faculty to identify a set of core methodological competencies. These included randomized trials, case-control and cohort studies, confounding, effect modification, propensity scores, linear and logistic regression, and survival analysis. Faculty provided us with clinical questions and deidentified data sets corresponding to these competencies; we also reviewed publicly available data sets. RESULTS/ANTICIPATED RESULTS: CTS faculty collaborated to develop 10 cases (with accompanying data sets) from modern clinical research examples that illustrate the connections between epidemiology and biostatistical concepts. Each case contains a background section, a statement of the core problem, a data set with data dictionary, articles from the primary literature (often the publication of the data set) with discussion questions and in-class lab exercises (R programming). One case presents students with the challenge of whether acupuncture may be an effective therapy for pain associated with chronic headache. Through case activities, students gain experience weighing observational Versus experimental evidence, apply directed acyclic graph theory, and analyze clinical trial data. Qualitative evaluations in 2015 (pilot year) and 2016 indicate students preferred the integrated approach to separate courses, and found the integration facilitated application of methods to their independent research projects. Significant rewards for faculty include cross-disciplinary collaboration, sharpened teaching skills, and engaging with learners in a dynamic classroom environment. DISCUSSION/SIGNIFICANCE OF IMPACT: Despite administrative and pedagogical challenges, a case-based, integrated curriculum offers rewards for faculty and students. The case method may be a useful pedagogical strategy to integrate other closely related topics or courses in translational science to better prepare scholars for the challenges of independent research.

OBJECTIVES/GOALS: The goals of this study are to 1) adapt a mindfulness-based intervention that supports the development of trust-promoting behaviors of OBGYN providers with patients who identify as Black women based on the input of providers and patients, and 2) assess the feasibility of implementation for OBGYN healthcare providers. METHODS/STUDY POPULATION: Goal 1: Focus groups will be conducted with members of the populations of providers and Black women patients in Alachua County, Florida to identify essential intervention content to complement the central component of mindfulness and spiritually based practices. This complementary content will serve to address the institutional and cultural context of the intervention setting. Goal 2: Providers will be recruited to participate in interviews about their perceptions of intervention feasibility. These aspects include recruitment potential, acceptability of the intervention content and delivery, implementation practicality, identification of appropriate outcomes, and identifying strategies to recruit Black women patients to participate in program evaluation. RESULTS/ANTICIPATED RESULTS: Goal 1: We will elicit the perspectives of providers and Black women patients regarding the respective roles and relationship of mindfulness and spirituality to increase trust-promoting behaviors with patients who are Black women. We also anticipate identifying additional content to complement the core intervention components that participants perceive as necessary to develop the knowledge, skills, and behaviors which convey the trustworthiness of providers to patients. Goal 2: We expect to gain key insights into intervention design, implementation, and evaluation feasibility from the perspective of providers. Interview data will be aggregated and qualitatively analyzed for themes pertaining to feasibility. DISCUSSION/SIGNIFICANCE: An intervention that builds on mindfulness and spiritual practice is an innovative approach to improving interpersonal outcomes in provider-patient relationships. By investigating the feasibility of such an intervention, we will gain insight into how to design and deliver a program to increase the trust-promoting behaviors of OBGYN providers.

OBJECTIVES/GOALS: Composition of demographics or image types in publicly available datasets may detract from deep learning (DL) diagnosis performance of underrepresented melanoma subtypes. We evaluate a DL model’s performance on melanoma subtypes (acral; head and neck) that have known association with poor prognosis. METHODS/STUDY POPULATION: We trained a CNN using a single InceptionV3 model for 30 epochs on dermoscopic images of pigmented lesions from the International Skin Imaging Collaboration (ISIC). The ISIC 2018 challenge training set had 10008 total images, with 1113 total nevi, 6705 total melanomas, 97 acral nevi, 10 acral melanomas, 256 head and neck (H&N) nevi, and 164 H&N melanomas. The non-acral test set had 117 melanomas and 200 nevi. The acral test set had 201 melanomas and 161 nevi. The H&N test set had 199 melanomas and 128 nevi. Area under the receiver operating curve (AUC) was calculated. The model was retrained with acral lesion oversampling (10x) and performance on the acral test set was re-evaluated. RESULTS/ANTICIPATED RESULTS: The model performed on the non-acral test with an AUC of 80.5%, on the acral test with an AUC of 76.3%, and on the head and neck test with an AUC of 83.8% After oversampling acral lesions within the training set, the model showed nearly the same performance as without oversampling on acral lesions: AUC of 75.6%. DISCUSSION/SIGNIFICANCE OF IMPACT: Diagnosis of high-risk melanoma subsets (acral; H&N) remains reliable despite underrepresentation during training, increasing validity for broad implementation of DL technology. Datasets for individual subtypes may not be warranted as findings suggest features may be learned from other skin lesions.