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

2025-05-17

AI Summary

Addressing two prevalent challenges in multi-view electronic health record (EHR) prediction—*stochastic view missing* and *view inertia* (i.e., redundancy or inefficiency in certain views)—this paper proposes the first unified generative framework based on a *multi-view conditional guided diffusion model*. The method enables controllable reconstruction of missing views via *cross-view progressive alignment* and *context-aware denoising*, while introducing a *relative-advantage-driven view adaptive reweighting mechanism* to dynamically calibrate view-specific contributions—thereby relaxing conventional assumptions of data completeness and uniform view utilization. Extensive experiments across three benchmark EHR datasets demonstrate that our approach significantly outperforms state-of-the-art methods on multiple downstream tasks, including disease prediction and hospitalization risk stratification. Notably, it exhibits superior robustness under sparse-view and cross-modal settings.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

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.

Problem

• Addresses random missing views in EHR data
• Mitigates view laziness in multi-view utilization
• Enhances healthcare predictions with diffusion framework

Innovation

• Unified diffusion-denoising framework for EHR views
• Contextual conditions for progressive view alignment
• Reweighting strategy to balance view utilization