Data-Centric Foundation Models in Computational Healthcare: A Survey
Yunkun Zhang, Jin Gao, Zheling Tan, Lingfeng Zhou, Kexin Ding, Mu Zhou, Shaoting Zhang, Dequan Wang
Why It Matters
What makes this one worth your time
Understanding data-centric approaches in foundation models can improve healthcare AI systems by addressing data quality and ethical challenges.
A survey of data-centric foundation models in healthcare, highlighting data challenges and opportunities.
Summary
The paper surveys data-centric approaches in the context of foundation models for computational healthcare, discussing challenges and opportunities in data quality, security, and alignment with human values, and provides a list of relevant models and datasets.
Key contributions
- Survey of data-centric approaches in foundation models for healthcare.
- Discussion on AI security and alignment with human values.
- Compilation of healthcare-related foundation models and datasets.
Notable insights
- The interactive nature of foundation models emphasizes the importance of data quality and characterization.
- Foundation models can potentially enhance patient outcomes and clinical workflows.
Possible limitations
- Not stated in the abstract
Abstract
arXiv:2401.02458v3 Announce Type: replace-cross Abstract: The advent of foundation models (FMs) as an emerging suite of AI techniques has struck a wave of opportunities in computational healthcare. The interactive nature of these models, guided by pre-training data and human instructions, has ignited a data-centric AI paradigm that emphasizes better data characterization, quality, and scale. In healthcare AI, obtaining and processing high-quality clinical data records has been a longstanding challenge, encompassing data quantity, annotation, patient privacy, and ethics. In this survey, we investigate a wide range of data-centric approaches in the FM era (from model pre-training to inference) towards improving the healthcare workflow. We discuss key perspectives in AI security, assessment, and alignment with human values. Finally, we offer a promising outlook on FM-based analytics to enhance patient outcomes and clinical workflows in the evolving landscape of healthcare and medicine. We provide an up-to-date list of healthcare-related foundation models and datasets at https://github.com/Yunkun-Zhang/Data-Centric-FM-Healthcare.