Back

A Framework for Evaluating the Efficacy of Foundation Embedding Models in Healthcare

Xu, S.; Gui, H.; Rotemberg, V.; Wang, T.; Chen, Y.; Daneshjou, R.

2024-04-19 health informatics
10.1101/2024.04.17.24305983 medRxiv
Show abstract

Recent interest has surged in building large-scale foundation models for medical applications. In this paper, we propose a general framework for evaluating the efficacy of these foundation models in medicine, suggesting that they should be assessed across three dimensions: general performance, bias/fairness, and the influence of confounders. Utilizing Googles recently released dermatology embedding model and lesion diagnostics as examples, we demonstrate that: 1) dermatology foundation models surpass state-of-the-art classification accuracy; 2) general-purpose CLIP models encode features informative for medical applications and should be more broadly considered as a baseline; 3) skin tone is a key differentiator for performance, and the potential bias associated with it needs to be quantified, monitored, and communicated; and 4) image quality significantly impacts model performance, necessitating that evaluation results across different datasets control for this variable. Our findings provide a nuanced view of the utility and limitations of large-scale foundation models for medical AI.

Matching journals

The top 9 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.