Unveiling Discrete Clues: Superior Healthcare Predictions for Rare Diseases

TL;DR

This paper introduces UDC, a novel method that enhances rare disease prediction by aligning textual knowledge with collaborative signals in a shared discrete space, overcoming data scarcity issues.

Contribution

The paper proposes a unified framework that combines discrete encoding, contrastive learning, and co-teacher distillation to improve rare disease prediction accuracy.

Findings

UDC outperforms existing methods on three datasets.

Enhanced disease representation through discrete encoding.

Improved semantic alignment between textual and collaborative signals.

Abstract

Accurate healthcare prediction is essential for improving patient outcomes. Existing work primarily leverages advanced frameworks like attention or graph networks to capture the intricate collaborative (CO) signals in electronic health records. However, prediction for rare diseases remains challenging due to limited co-occurrence and inadequately tailored approaches. To address this issue, this paper proposes UDC, a novel method that unveils discrete clues to bridge consistent textual knowledge and CO signals within a unified semantic space, thereby enriching the representation semantics of rare diseases. Specifically, we focus on addressing two key sub-problems: (1) acquiring distinguishable discrete encodings for precise disease representation and (2) achieving semantic alignment between textual knowledge and the CO signals at the code level. For the first sub-problem, we refine the standard vector quantized process to include condition awareness. Additionally, we develop an advanced contrastive approach in the decoding stage, leveraging synthetic and mixed-domain targets as hard negatives to enrich the perceptibility of the reconstructed representation for downstream tasks. For the second sub-problem, we introduce a novel codebook update strategy using co-teacher distillation. This approach facilitates bidirectional supervision between textual knowledge and CO signals, thereby aligning semantically equivalent information in a shared discrete latent space. Extensive experiments on three datasets demonstrate our superiority.