1. Bridging expertise with machine learning and automated machine learning in clinical medicine.
- Author
-
Chien-Chang Lee, Yeongjun Park, James, and Wan-Ting Hsu
- Subjects
- *
MACHINE learning , *CLINICAL medicine , *CLINICAL decision support systems , *LANGUAGE models , *MEDICAL care - Abstract
The article discusses the use of machine learning (ML) and automated machine learning (AutoML) in clinical medicine. It highlights the challenges faced by healthcare professionals in adopting ML due to technical complexities and the potential solution of partnering with vendors. AutoML is presented as a solution that streamlines the ML analysis process, making it accessible to users with limited programming skills. The article emphasizes the potential of AutoML to accelerate innovation and improve patient outcomes in various medical domains. It also acknowledges the limitations and challenges associated with integrating AutoML into healthcare, including performance variability and ethical concerns. The need for ongoing dialogue, increased investment in education, and a principled approach to deployment is advocated to fully leverage AutoML's transformative potential in patient care. [Extracted from the article]
- Published
- 2024
- Full Text
- View/download PDF