Addressing Asynchronicity in Clinical Multimodal Fusion via Individualized Chest X-ray Generation

TL;DR

This paper introduces DDL-CXR, a novel method that dynamically generates up-to-date chest X-ray representations from asynchronous multimodal clinical data, significantly improving prediction accuracy in medical applications.

Contribution

The paper presents a new latent diffusion model-based approach for patient-specific CXR generation conditioned on EHR and previous CXR, addressing asynchronicity in multimodal clinical data fusion.

Findings

Outperforms existing methods on MIMIC datasets.

Effectively captures disease progression and anatomical changes.

Addresses asynchronicity in multimodal clinical data fusion.

Abstract

Integrating multi-modal clinical data, such as electronic health records (EHR) and chest X-ray images (CXR), is particularly beneficial for clinical prediction tasks. However, in a temporal setting, multi-modal data are often inherently asynchronous. EHR can be continuously collected but CXR is generally taken with a much longer interval due to its high cost and radiation dose. When clinical prediction is needed, the last available CXR image might have been outdated, leading to suboptimal predictions. To address this challenge, we propose DDL-CXR, a method that dynamically generates an up-to-date latent representation of the individualized CXR images. Our approach leverages latent diffusion models for patient-specific generation strategically conditioned on a previous CXR image and EHR time series, providing information regarding anatomical structures and disease progressions, respectively. In this way, the interaction across modalities could be better captured by the latent CXR generation process, ultimately improving the prediction performance. Experiments using MIMIC datasets show that the proposed model could effectively address asynchronicity in multimodal fusion and consistently outperform existing methods.