Prospective evaluation of multimodal respiratory failure prediction: Do chest X-rays improve performance beyond EHR signals?

2026-05-25

AI Summary

This study addresses the challenge of prospectively predicting the need for invasive mechanical ventilation within 24 hours in critically ill patients by proposing a gated multimodal framework that dynamically integrates time-series structured electronic health record (EHR) data with representations from chest X-ray (CXR) foundation models (REMEDIS and MedInsight). A key innovation lies in an adaptive gating mechanism that selectively activates CXR-derived features only when they are discriminative, thereby minimizing redundant or misleading contributions. In prospective clinical validation, the proposed model achieved an AUROC of 0.860, significantly outperforming an EHR-only baseline (AUROC: 0.752) and surpassing clinicians’ assessments across sensitivity, specificity, and positive predictive value.

Abstract

Early prediction of respiratory failure is critical for timely clinical intervention in intensive care units. Existing electronic health record (EHR)-based models can continuously monitor physiologic deterioration, but they may not fully capture pulmonary pathophysiology reflected in chest radiographs (CXRs). In this study, we ask whether CXR information improves prospective prediction of invasive mechanical ventilation beyond EHR signals alone. We develop a gated multimodal framework that integrates structured EHR time-series data with CXR foundation-model representations. The gating module adaptively controls the contribution of imaging features based on patient-specific clinical context, allowing the model to selectively rely on imaging information when it is informative. We prospectively evaluate the framework for predicting invasive mechanical ventilation within 24 hours in ICU patients and compare it with an established EHR-only model (Vent.io), physician predictions obtained at matched clinical time points, and alternative multimodal variants. The gated multimodal models achieved higher discrimination than the EHR-only baseline, with AUROC values of 0.860 and 0.858 using REMEDIS and MedInsight CXR representations, respectively, compared with 0.752 for Vent.io. Relative to physician predictions, the multimodal framework substantially improved sensitivity while maintaining favorable specificity. Compared with the EHR-only model, multimodal integration increased specificity and positive predictive value, suggesting that CXR information can refine risk estimation in selected patients. These findings support adaptive multimodal fusion as a practical strategy for incorporating imaging into prospective respiratory failure prediction.

Problem

• respiratory failure prediction
• chest X-ray
• electronic health record
• mechanical ventilation
• multimodal fusion

Innovation

• gated multimodal fusion
• chest X-ray foundation models
• respiratory failure prediction
• adaptive feature integration
• prospective clinical evaluation