Hostname: page-component-586b7cd67f-2plfb Total loading time: 0 Render date: 2024-11-28T13:06:09.518Z Has data issue: false hasContentIssue false

311 Democratizing access to clinical data for research: Implementation and evaluation strategies in an academic medical center and lessons learned

Published online by Cambridge University Press:  03 April 2024

Riddhiman Adib
Affiliation:
Oregon Health & Science University
Susan Myers
Affiliation:
Oregon Health & Science University
Erik Benton
Affiliation:
Oregon Health & Science University
Aaron Cohen
Affiliation:
Oregon Health & Science University
Mohammad Adibuzzaman
Affiliation:
Oregon Health & Science University
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

OBJECTIVES/GOALS: To facilitate data exploration at an academic medical center, we piloted self-service data science tools to provide easy access to research data and provide analytical workspace. The objectives are: i) data delivery with data governance and cohort discovery under a managed self-service model and ii) data science and analytics tool for advanced users. METHODS/STUDY POPULATION: Using existing commercial frameworks, we implemented a few pilot self-service tools. The key characteristics of the tools were i) high degrees of functionality and flexibility for data access and data governance, ii) lower cost to build and maintain, and iii) long-term organizational strategic alignment with the academic medical center. We conducted a two-phase evaluation with the pilot self-service tool: functionality-based assessment, prioritizing tools for data science users, and usability-based assessment, evaluating selected tools through customized maturity models and surveys. The evaluation study targeted a focus group study with five diverse faculties and researchers in an academic medical center seeking improved access to research resources. RESULTS/ANTICIPATED RESULTS: In evaluation phase 1, we explored seven self-service tool frameworks suitable for our research data warehouse (RDW). In phase 2, we implemented the top two tools selected from phase 1, QlikView and Palantir Foundry. Although the tool built on Palantir has higher mean and individual scores for user feedback than Qlik's, there is no statistically significant difference. Both tools had steep initial learning curve. Palantir has better feedback from qualitative responses. Our study findings highlight prioritized functionalities (efficiency, flexibility, sustainability, security, and cost reduction) for data science tool users; however features and the tool itself requires long term organizational planning and investment. DISCUSSION/SIGNIFICANCE: Academic and research medical centers strongly focus on efficient pilot data access for researchers to aid hypothesis generation. Establishing a clinical research-focused self-service data tool addresses the well-established demand for research resources and offers a model for similar organizations.

Type
Informatics and Data Science
Creative Commons
Creative Common License - CCCreative Common License - BYCreative Common License - NCCreative Common License - ND
This is an Open Access article, distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives licence (https://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is unaltered and is properly cited. The written permission of Cambridge University Press must be obtained for commercial re-use or in order to create a derivative work.
Copyright
© The Author(s), 2024. The Association for Clinical and Translational Science