No CrossRef data available.
Article contents
426 Datathon Revisited: Implementation of Lesson Learned
Published online by Cambridge University Press: 24 April 2023
Abstract
OBJECTIVES/GOALS: In 2020, Baylor College of Medicine held a datathon to introduce a data warehouse, identify its capabilities/limitations, foster collaborations, and engage trainees. The event was held again in 2022, and lessons learned (e.g., tools for data self-service or team communication) were applied. METHODS/STUDY POPULATION: Senior faculty reviewed proposals with an emphasis on feasibility, impact, and relevance to quality improvement or population health. Selected teams worked with Information Technology (IT) for 2 months and presented findings at a 1-day event. Surveys were administered to participants before and after the event to evaluate their background, team characteristics, collaborations, knowledge before and after the datathon, perceived value of the datathon, and plans for future work. Descriptive statistics of respondents’ self-reports were tabulated. RESULTS/ANTICIPATED RESULTS: In 2022, 19 of 36 projects were accepted (13/33 in 2020). At both events, most projects studied quality improvement or clinical outcomes. Of 82 participants in 2022, 54 completed surveys. In 2022, 72% had no datathon experience (48% in 2020). Median effort was 10 person-hours; median IT time was 20% (20 and 10%, in 2020). Seven respondents finished and 21 partially finished their projects (1 and 11, in 2020); 92% made new collaborations (91% in 2020). Respondents strongly agreed that: the experience was valuable (n=28), they would participate in future datathons (n=30), and they would use the warehouse for future work (n=25). Twenty-seven have planned abstracts; 25 have planned manuscripts. DISCUSSION/SIGNIFICANCE: The 2022 datathon had more participants with less experience, potentially due to improved promotion and training opportunities. Fewer person-hours and a higher percentage of IT time were required as compared to 2020, and more projects were completed, possibly due to increased IT efficiency.
- Type
- Team Science
- Information
- Creative Commons
- 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), 2023. The Association for Clinical and Translational Science