Purpose <p>Early mortality risk stratification in Acute Respiratory Distress Syndrome (ARDS) remains challenging because conventional approaches often fail to capture the complex interplay between temporal physiological dynamics and the progression of pulmonary structural injury. This study proposed a multimodal adaptive-gating framework to improve mortality prediction in this population.</p> Methods <p>This retrospective study included 102 patients with ARDS, integrating clinical time-series data and dual-time-point dynamic radiomic features. We proposed the Adaptive Gating Multimodal Fusion Network (AdaG-Net), a dual-branch architecture comprising: (1) a clinical branch utilizing Bidirectional Long Short-Term Memory (Bi-LSTM) with channel-wise and additive attention mechanisms; and (2) an imaging branch based on dynamic radiomics. Principal Component Analysis (PCA) was used for dimensionality reduction, while Euclidean distance and difference vectors quantified temporal radiomic evolution. An adaptive gating module dynamically fused multimodal representations. Performance was rigorously assessed using a time-ordered expanding window cross-validation strategy.</p> Results <p>AdaG-Net achieved a mean AUROC of 0.910 ± 0.018, significantly outperforming radiomics-only, clinical-only, and non-gated multimodal baselines. Incorporating dynamic radiomic evolution features improved imaging branch performance by 8.5% compared to static radiomics. Key clinical predictors identified included potassium, pH, anion gap, lactate, and oxygen saturation. The learned gating weights confirmed patient-specific adaptive modality reweighting.</p> Conclusion <p>Integrating clinical time-series data with dynamic CT radiomics via adaptive gating significantly enhances mortality prediction in ARDS. However, the model’s real-world clinical impact, including its influence on treatment decisions and patient outcomes, requires prospective validation.</p>