AutoAdapt: Reliable Few-Shot Adaptation under Clinical Distribution Shifts
Large pretrained clinical models provide a practical way to reuse learned prior knowledge across hospitals by adapting models to them.
Key points
- In practice, a target hospital may only have a small labeled patient cohort, a setting commonly referred to as few-shot adaptation.
- In this work, we introduce AutoAdapt with two core designs to deal with these challenges.
- These selected strategies then form a combination for effective few-shot adaptation.
- We conduct extensive experiments across critical care, emergency care, and diagnostic datasets, and the results show that AutoAdapt consistently achieves state-of-the-art performance using only a few patients for adaptation.
Sources (1)
- [1]AutoAdapt: Reliable Few-Shot Adaptation under Clinical Distribution ShiftsarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 03:22 AM
Large pretrained clinical models provide a practical way to reuse learned prior knowledge across hospitals by adapting models to them.
In practice, a target hospital may only have a small labeled patient cohort, a setting commonly referred to as few-shot adaptation.
Extractive summary: sentences quoted from the sources.