Diffmv: A Unified Diffusion Framework for Healthcare Predictions with Random Missing Views and View Laziness

TL;DR

Diffmv is a diffusion-based framework that improves healthcare predictions by effectively handling missing views and view laziness in multi-view EHR data, leading to better utilization and performance.

Contribution

The paper introduces Diffmv, a novel diffusion framework that addresses missing views and view laziness, enhancing multi-view EHR data exploitation for healthcare predictions.

Findings

Achieves superior performance on multiple health prediction tasks.

Effectively handles random missing views in EHR data.

Balances view utilization through a novel reweighting strategy.

Abstract

Advanced healthcare predictions offer significant improvements in patient outcomes by leveraging predictive analytics. Existing works primarily utilize various views of Electronic Health Record (EHR) data, such as diagnoses, lab tests, or clinical notes, for model training. These methods typically assume the availability of complete EHR views and that the designed model could fully leverage the potential of each view. However, in practice, random missing views and view laziness present two significant challenges that hinder further improvements in multi-view utilization. To address these challenges, we introduce Diffmv, an innovative diffusion-based generative framework designed to advance the exploitation of multiple views of EHR data. Specifically, to address random missing views, we integrate various views of EHR data into a unified diffusion-denoising framework, enriched with diverse contextual conditions to facilitate progressive alignment and view transformation. To mitigate view laziness, we propose a novel reweighting strategy that assesses the relative advantages of each view, promoting a balanced utilization of various data views within the model. Our proposed strategy achieves superior performance across multiple health prediction tasks derived from three popular datasets, including multi-view and multi-modality scenarios.