Overcoming Uncertain Incompleteness for Robust Multimodal Sequential Diagnosis Prediction via Curriculum Data Erasing Guided Knowledge Distillation

TL;DR

NECHO v2 introduces a robust multimodal sequential diagnosis framework that employs curriculum data erasing and advanced knowledge distillation to improve prediction accuracy amid uncertain missing data in clinical sequences.

Contribution

It develops a novel curriculum data erasing guided knowledge distillation method to enhance robustness in multimodal diagnosis prediction with incomplete data.

Findings

Outperforms existing methods in incomplete data scenarios

Demonstrates robustness on healthcare multimodal datasets

Effective in both balanced and imbalanced missing data settings

Abstract

In this paper, we present NECHO v2, a novel framework designed to enhance the predictive accuracy of multimodal sequential patient diagnoses under uncertain missing visit sequences, a common challenge in real clinical settings. Firstly, we modify NECHO, designed in a diagnosis code-centric fashion, to handle uncertain modality representation dominance under the imperfect data. Secondly, we develop a systematic knowledge distillation by employing the modified NECHO as both teacher and student. It encompasses a modality-wise contrastive and hierarchical distillation, transformer representation random distillation, along with other distillations to align representations between teacher and student tightly and effectively. We also propose curriculum learning guided random data erasing within sequences during both training and distillation of the teacher to lightly simulate scenario with missing visit information, thereby fostering effective knowledge transfer. As a result, NECHO v2 verifies itself by showing robust superiority in multimodal sequential diagnosis prediction under both balanced and imbalanced incomplete settings on multimodal healthcare data.