Objectives/Goals: We advance multimodal modeling, including digital twins (DTs), within an AI-enabled Learning Health System (LHS) to turn healthcare data into insights for precision care and translational science. DTs are dynamic patient models integrating EHRs, neuroimaging, biomarkers, wearables, and other real-world data (RWD) tools. Methods/Study Population: Multiple sclerosis (MS) provides a compelling use case of heterogeneous manifestations including fatigue, mobility deficits, cognitive deficits, and sleep disturbance, requiring multimodal integration to capture complexity. DTs integrate EHR, neuroimaging, biomarkers, wearable, and other RWD via ETL pipelines using standards like FHIR, OMOP, and DICOM. Modeling uses ensemble learning, LSTM/DBNs, dimensionality reduction, and bias auditing. Explainable AI (XAI) provides transparency through counterfactual “what if” analyses, such as testing whether risk changes if a patient improves gait speed, adjusts therapy, increases sleep duration, or lowers biomarker levels. Continuous monitoring detects model drift, ensuring reliability per FDA V3: verification, validation, vigilance. Results/Anticipated Results: A robust extract–transform–load (ETL) pipeline maps these inputs into standards such as Fast Healthcare Interoperability Resources (FHIR), the Observational Medical Outcomes Partnership (OMOP) common data model, and the Digital Imaging and Communications in Medicine (DICOM) format, ensuring interoperability and reuse across sites. Development emphasizes robustness through parameter optimization, ensemble learning, prevention of data leakage, preprocessing, dimensionality reduction, and regularization. Key AI applications include MRI lesion and atrophy segmentation with nnU-Net, temporal deep learning for longitudinal forecasting with deep belief networks (DBNs) and long short-term memory (LSTM) models, ensemble modeling to improve generalizability, and bias auditing to promote fairness. Discussion/Significance of Impact: This initiative advances digital health, neuroinformatics, and precision medicine for MS and other complex diseases. Aligned with NIH ODSS Data COUNTS and FDA V3, the framework supports discovery, regulatory science, and generalization to other variable conditions.

Objectives/Goals: Broad and shallow data from large national cohorts provide generalizable real-world insights, while deep and narrow data from smaller cohorts capture detailed multimodal measures. This project integrates both approaches to study cognitive decline in Parkinson’s disease, which affects up to 50% of patients. Methods/Study Population: This longitudinal study includes validated digital biomarkers of motor, non-motor, sleep, and driving activity in 150 participants, plus novel social connectedness measures in 150 PD – partner dyads. PD and cognitive status are assessed annually; 4 weeks of continuous real-world behavior via actigraphy, social connectedness, and driving sensors are collected biannually. Anchor variables from pilot PD, PPMI, and LongROAD enable harmonization and cross-cohort modeling. Model development focuses on generative time series models that can capture the joint distribution of multimodal time series data for predicting values for future time steps. Together combined with genetics, plasma, and neuroimaging, they enable digital twins to predict decline and identify modifiable risks. Results/Anticipated Results: This project is designed to make impactful contributions to scientific knowledge, technical capability, clinical practice, and healthcare equity. Addressing key gaps in understanding PD cognitive decline, developing clinically validated digital biomarkers, and advancing data modeling for public health and precision medicine, including the creation of Digital Twin models. By integrating real-world data and social context into PD research, we will enhance clinical trials, improve patient outcomes, and provide clinicians with valuable tools, leading to a deeper understanding of PD and ADRDs. The data generated will be mined and shared with colleagues for years, driving new research and insights. Discussion/Significance of Impact: This project enhances monitoring and prediction of cognitive decline in PD, developing clinically valid, interpretable tools for real-world health. This generalizable platform unifies digital, imaging, and biomarker data as a model for translational research, advancing trial readiness across neurological and chronic diseases.

Objectives/Goals: The NIH Office of Data Science and Strategy created Data COUNTS (Collect Once, Use Numerous TimeS) to transform real-world data into actionable insights for translational research. The NEurOinformatics Network (NEON) applies this principle with neurology and national cohort use cases. Methods/Study Population: UNMC and Nebraska Medicine are deploying Data COUNTS to standardize data capture, ensure interoperability, and maximize reuse across research, clinical care, and operations. Teams integrate electronic health records, neuroimaging, biomarkers, wearable sensors, and social drivers of health into federated pipelines. HL7 FHIR and the OMOP Common Data Model maintain interoperability and reproducibility. Use cases include neurological disorders (multiple sclerosis, Alzheimer’s disease, and Parkinson’s disease), cancer outcomes through SEER, diabetes, and rural health disparities. Integration with the National Clinical Cohort Collaborative (N3C) leverages anchor variables and harmonized pipelines to connect local and national datasets for generalizable analytics and collaborative science. Results/Anticipated Results: By linking with CTSA, IDeA-CTR, SEER, N3C, and other national health data, this initiative strengthens Learning Health System infrastructure, accelerates precision medicine, and advances population health. Beginning at NM and UNMC, the model will extend to regional systems, especially in rural and underserved areas. Use cases in neurology, cancer, diabetes, and rural health demonstrate local impact, while SEER and N3C provide scalable pathways for harmonization and national integration. Discussion/Significance of Impact: Nebraska’s leading health system generates multimodal datasets that, connected with SEER and N3C through Data COUNTS principles, enable predictive modeling, explainable AI, and digital twins. These use cases operationalize a scalable framework for translational science.

Institutional Development Awards for Clinical and Translational Research (IDeA-CTR) networks, funded by NIH/NIGMS, aim to advance CTR infrastructure to address historically unmet state and regional health needs. Success depends on the response to actionable feedback to IDeA-CTR leadership from network partners and governance groups through annual surveys, interviews, and governance body recommendations. The Great Plains IDeA-CTR applied internal formative meta-evaluation to evaluate dispositions of 172 governance recommendations from 2017 to 2021. Results provided insights to improve the classification and quality of recommendations, credibility of evaluation processes, responsiveness to recommendations, and communications and governance in a complex CTR network comprising multiple coalitions.

Background: In their interim infection prevention and control recommendations for the coronavirus disease 2019 (COVID-19) pandemic, the Centers for Disease Control and Prevention (CDC) recommend that healthcare facilities have a plan to identify, investigate, and trace potential COVID-19 exposures. In an academic hospital, the scale of such tracing is substantial, given that medically complex patients can have dozens of staff contacts across multiple locations during an encounter. Furthermore, the family-centered care model employed by pediatric institutions precludes visitor exclusion, further complicating tracing efforts. Despite this complexity, tracing accuracy and timeliness is of paramount importance for exposure management. To address these challenges, our institution developed a contact-tracing system that balanced expert participation with automated tracing tools. Methods: Our institution’s contact-tracing initiative includes positive patients, parents and/or visitors, and staff for the enterprise’s inpatient, procedural, and ambulatory locations at the main campus and 4 satellites. The team consists of 11 staff and is overseen by an infection preventionist. For positive patients and parents and/or visitors, potentially exposed staff are automatically identified via a report that extracts staff details for all encounters occurring during the patient’s infectious period. For positive staff, trained contact tracers call the staff member to determine whether mask and distancing practices could result in others meeting CDC exposure criteria. Any potentially exposed healthcare workers (HCWs) receive an e-mail that details exposure criteria and provides follow-up instructions. These HCWs are also entered into a secure, centralized tracking database that (1) allows infection prevention and occupational health staff to query and identify all epidemiologic links between traced patients, parents and/or visitors, and staff, and (2) initiates staff enrollment in a twice-daily symptom tracking system administered via REDCap. Potentially exposed patients and parents and/or visitors are contacted directly by a hospital representative. The contact tracing team, infection prevention staff, and occupational health staff meet daily to review positive staff cases in the last 24 hours. Results: To date, the team has traced ~1,300 patients, 15 parents and/or visitors, and 700 staff. Since the start of the pandemic, tracing and contact notification for all positive cases has been conducted within 24 hours. Through these proactive tracing efforts and other institutional infection prevention initiatives, the institution only experienced 1 staff cluster (N < 15) and <5 hospital-onset patient cases. Conclusions: Equipping a trained group of contact tracers with automated tracking tools can afford infection prevention and occupational health departments the ability to achieve and sustain timely and accurate contact tracing initiatives throughout a large-scale pandemic response.

Funding: No

Disclosures: None

The goal of this study was to assess the utility of participatory needs assessment processes for continuous improvement of developing clinical and translational research (CTR) networks. Our approach expanded on evaluation strategies for CTR networks, centers, and institutes, which often survey stakeholders to identify infrastructure or resource needs, using the case example of the Great Plains IDeA-CTR Network. Our 4-stage approach (i.e., pre-assessment, data collection, implementation of needs assessment derived actions, monitoring of action plan) included a member survey (n = 357) and five subsequent small group sessions (n = 75 participants) to better characterize needs identified in the survey and to provide actionable recommendations. This participatory, mixed-methods needs assessment and strategic action planning process yielded 11 inter-related recommendations. These recommendations were presented to the CTR steering committee as inputs to develop detailed, prioritized action plans. Preliminary evaluation shows progress towards improved program capacity and effectiveness of the network to respond to member needs. The participatory, mixed-methods needs assessment and strategic planning process allowed a wide range of stakeholders to contribute to the development of actionable recommendations for network improvement, in line with the principles of team science.

OBJECTIVES/SPECIFIC AIMS: To complete a needs assessment and action planning process that engaged clinical and translational research network members in identifying needs through survey feedback, characterizing the needs in small group sessions, and developing recommendations for action at the network’s annual scientific meeting. METHODS/STUDY POPULATION: The project included (1) a survey of 357 members across partner institutions from the Great Plains IDeA CTR Network, (2) 6 - 90 minute brainstorming sessions to characterize needs identified through survey assessment, and (3) 6 - 60 minute sessions to develop recommendations for network improvement based on the characterization activity. Approximately 75 members participated in the characterization and recommendation sessions. RESULTS/ANTICIPATED RESULTS: Seven areas of need from the survey were identified based upon the frequency of identification by network members (support to move research across the translational spectrum, database design and management, data access and sharing, data analysis, recruitment and retention of subjects, support for members who have submitted grants but were repeatedly unsuccessful, mentoring). Members indicated which characterization sessions they were interested in attending and based on the enrollment numbers needs related to unsuccessful grant submitters and mentoring were combined as were needs related to database design and data access-sharing. Sessions resulted in 8 inter-related recommendations for network action that included to (1) develop GP-CTR directory/registry of clinicians, researchers, system partners, that can be used to identify people that want to be involved in research partnerships or mentoring, (2) create a GP CTR Navigators Program to will provide support to network members throughout the collaborative research and grant preparation process, (3) identify and disseminate information about assets (funding, databases/registries) that exist amongst network partners that can be leveraged by member, (4) develop a searchable repository of evidence-based interventions for T3/T4 efforts, (5) review GP CTR supported professional development, and technological resource offerings and identify potential gaps, (6) facilitate opportunities for peer support/networking, (7) provide guidance to GP CTR network institutions looking to adopt policies that will support translational research collaboration, and (8) identify potential barriers to GP CTR network engagement (i.e., infrastructure, communication, marketing). DISCUSSION/SIGNIFICANCE OF IMPACT: This process allowed for a wide range of network members to contribute to actionable recommendations for CTR leadership to move into action and improve the scientific network’s ability to conduct clinical and translational research.

Demographically adjusted norms generally enhance accuracy of inferences based on neuropsychological assessment. However, we hypothesized that demographic corrections diminish predictive accuracy for real-world activities with absolute cognitive demands. Driving ability was assessed with a 45-minute drive along a standardized on-road route in participants aged 65+ (24 healthy elderly, 26 probable Alzheimer’s disease, 33 Parkinson’s disease). Neuropsychological measures included: Trail-Making A and B, Complex Figure, Benton Visual Retention, and Block Design tests. A multiple regression model with raw neuropsychological scores was significantly predictive of driving errors (R2 = .199, p = .005); a model with demographically adjusted scores was not (R2 = .113, p = .107). Raw scores were more highly correlated with driving errors than were adjusted scores for each neuropsychological measure, and among healthy elderly and Parkinson’s patients. When predicting real-world activities that depend on absolute levels of cognitive abilities regardless of demographic considerations, predictive accuracy is diminished by demographic corrections. (JINS, 2010, 16, 679–686.)