Deep Normed Embeddings for Patient Representation
This work addresses the need for interpretable patient representations in critical care medicine, offering a systematic approach to define intermediate rewards for reinforcement learning, though it is incremental in applying geometric priors to clinical data.
The authors tackled the problem of representing clinical time series data by introducing a contrastive learning objective that projects EHR data into a normed embedding space, where the Euclidean norm correlates with mortality risk and angles indicate organ failures, achieving a compact representation for patient monitoring and downstream tasks.
We introduce a novel contrastive representation learning objective and a training scheme for clinical time series. Specifically, we project high dimensional EHR. data to a closed unit ball of low dimension, encoding geometric priors so that the origin represents an idealized perfect health state and the Euclidean norm is associated with the patient's mortality risk. Moreover, using septic patients as an example, we show how we could learn to associate the angle between two vectors with the different organ system failures, thereby, learning a compact representation which is indicative of both mortality risk and specific organ failure. We show how the learned embedding can be used for online patient monitoring, can supplement clinicians and improve performance of downstream machine learning tasks. This work was partially motivated from the desire and the need to introduce a systematic way of defining intermediate rewards for Reinforcement Learning in critical care medicine. Hence, we also show how such a design in terms of the learned embedding can result in qualitatively different policies and value distributions, as compared with using only terminal rewards.