Description
Machine Learning and data science-anchored diagnostic and prognostic tools are advancing clinical decision-making at a rapid pace, requiring the need to train clinicians on their range of applicability and limitations. We propose DSL-TEACH (Data Science Literacy Training to Enhance Approaches for Clinical decision-making in Healthcare), a prototypical framework addressing this need by promoting literacy in data science and predictive analytics applied to clinical decision making.
Learning Objective: After participating in this session, the learner will be able to:
- Understand the need for greater awareness of new data science tools in medicine (i.e., case-based reasoning, machine learning-anchored practice-based evidence) given their impact and utility in advancing the field of clinical decision-making
- Review the key components of data science promoted in the proposed framework, DSL-TEACH, and understand its utility in clinical care and clinical decision-making via exemplar learning modules
- Recognize the need for more data science literacy training programs targeted towards applications in clinical decision-making and clinical care
Authors:
Samir Rachid Zaim (Presenter)
University of Arizona
Ahyoung Amy Kim, University of Arizona
Colleen Kenost, University of Arizona
Helen Zhang, University of Arizona
Yves Lussier, University of Arizona
Vignesh Subbian, University of Arizona
Presentation Materials: