0
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      562 AI Translation Advisory Board: Mastering team science to facilitate implementation of AI into clinical practice

      abstract
      , , , , , ,
      Journal of Clinical and Translational Science
      Cambridge University Press

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          OBJECTIVES/GOALS: Healthcare sectors are rushing to develop AI models. Yet, a dearth of coordinated practices leaves many teams struggling to implement models into practice. The Enterprise AI Translation Advisory Board uses across-disciplinary team to facilitate AI translation. METHODS/STUDY POPULATION: The Mayo Clinic Enterprise AI Translation Advisory Board was established to assess AI solutions lever aging cross-disciplinary team science to accelerate AI innovation and translation. The 23-member board reflects expertise in data science, qualitative research, user experience, IT, human factors, informatics, regulatory compliance,ethics, and clinical care, with members spanning thought leadership, decision-making, and clinical practice. Taking an approach of respectful communication, transparency, scientific debate, and open discussion, the Board has consulted onover two dozen projects at various stages of the AI life cycle. RESULTS/ANTICIPATED RESULTS: Common issues identified for projects earlier in the AI life cycle, sometimes fatal but often address able once identified, include a lack of buy-in from potential product users, a lack of planningabout integration into clinical workflow, inadequately labeled data, and attempting to use machine learning when what is desired is really a causal model for intervening. Recommendations for projects later in the AI life cycle include details of a testing plan (silent evaluation, pragmatic clinical trials), advice about clinical integration, both post-hoc and on going auditing for performance disparities, and planning for regulatory clearance. DISCUSSION/SIGNIFICANCE: Advising is more valuable for projects at the ideation phase, when multi disciplinary interrogation can identify weaknesses. But at all phases, projects have gaps related to a lack of specific disciplinary expertise. A multi disciplinary cluster like the AI Translation Advisory Board seeks to address these gaps.

          Related collections

          Author and article information

          Journal
          J Clin Transl Sci
          J Clin Transl Sci
          CTS
          Journal of Clinical and Translational Science
          Cambridge University Press (Cambridge, UK )
          2059-8661
          April 2024
          03 April 2024
          : 8
          : Suppl 1
          : 167-168
          Affiliations
          Mayo Clinic
          Article
          S2059866124004783
          10.1017/cts.2024.478
          11035300
          727e66a8-1b23-4c83-be91-8e6bd3bd782a
          © The Association for Clinical and Translational Science 2024

          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.

          History
          Page count
          Pages: 2
          Categories
          Team Science

          Comments

          Comment on this article