Sung‐Min Park

Sung Min Park, Kristian Georgiev, Andrew Ilyas et al. · mit

The goal of data attribution is to trace model predictions back to training data. Despite a long line of work towards this goal, existing approaches to data attribution tend to force users to choose between computational tractability and efficacy. That is, computationally tractable methods can struggle with accurately attributing model predictions in non-convex settings (e.g., in the context of deep neural networks), while methods that are effective in such regimes require training thousands of models, which makes them impractical for large models or datasets. In this work, we introduce TRAK (Tracing with the Randomly-projected After Kernel), a data attribution method that is both effective and computationally tractable for large-scale, differentiable models. In particular, by leveraging only a handful of trained models, TRAK can match the performance of attribution methods that require training thousands of models. We demonstrate the utility of TRAK across various modalities and scales: image classifiers trained on ImageNet, vision-language models (CLIP), and language models (BERT and mT5). We provide code for using TRAK (and reproducing our work) at https://github.com/MadryLab/trak .

Seunghyun Lee, Da Young Lee, Sujeong Im et al.

With recent achievements in tasks requiring context awareness, foundation models have been adopted to treat large-scale data from electronic health record (EHR) systems. However, previous clinical recommender systems based on foundation models have a limited purpose of imitating clinicians' behavior and do not directly consider a problem of missing values. In this paper, we propose Clinical Decision Transformer (CDT), a recommender system that generates a sequence of medications to reach a desired range of clinical states given as goal prompts. For this, we conducted goal-conditioned sequencing, which generated a subsequence of treatment history with prepended future goal state, and trained the CDT to model sequential medications required to reach that goal state. For contextual embedding over intra-admission and inter-admissions, we adopted a GPT-based architecture with an admission-wise attention mask and column embedding. In an experiment, we extracted a diabetes dataset from an EHR system, which contained treatment histories of 4788 patients. We observed that the CDT achieved the intended treatment effect according to goal prompt ranges (e.g., NormalA1c, LowerA1c, and HigherA1c), contrary to the case with behavior cloning. To the best of our knowledge, this is the first study to explore clinical recommendations from the perspective of goal prompting. See https://clinical-decision-transformer.github.io for code and additional information.

Miyeon Jung, You-Bin Lee, Sang-Man Jin et al.

Daytime hypoglycemia should be accurately predicted to achieve normoglycemia and to avoid disastrous situations. Hypoglycemia, an abnormally low blood glucose level, is divided into daytime hypoglycemia and nocturnal hypoglycemia. Many studies of hypoglycemia prevention deal with nocturnal hypoglycemia. In this paper, we propose new predictor variables to predict daytime hypoglycemia using continuous glucose monitoring (CGM) data. We apply classification and regression tree (CART) as a prediction method. The independent variables of our prediction model are the rate of decrease from a peak and absolute level of the BG at the decision point. The evaluation results showed that our model was able to detect almost 80% of hypoglycemic events 15 min in advance, which was higher than the existing methods with similar conditions. The proposed method might achieve a real-time prediction as well as can be embedded into BG monitoring device.