Data-Centric Foundation Models in Computational Healthcare: A Survey
arXiv:2401.02458 · doi:10.1145/3800677
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.
Published in ACM Computing Surveys
References in corpus (13)
- BioBERT: a pre-trained biomedical language representation model for biomedical text mining
- Segment Anything in Medical Images
- Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Segment Anything Model for Medical Image Analysis: an Experimental Study
- Translating Radiology Reports into Plain Language using ChatGPT and GPT-4 with Prompt Learning: Promising Results, Limitations, and Potential
- CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection
- 3DSAM-adapter: Holistic adaptation of SAM from 2D to 3D for promptable tumor segmentation
- VisionFM: a Multi-Modal Multi-Task Vision Foundation Model for Generalist Ophthalmic Artificial Intelligence
- Embedded Visual Prompt Tuning
- ExBEHRT: Extended Transformer for Electronic Health Records to Predict Disease Subtypes & Progressions
- From Pretraining to Privacy: Federated Ultrasound Foundation Model with Self-Supervised Learning
- A-Eval: A Benchmark for Cross-Dataset Evaluation of Abdominal Multi-Organ Segmentation