Stroke diagnosis in emergency rooms (ERs) is challenging due to limited access to MRI scans and a shortage of neurologists. Although AI-assisted triage has shown promise, existing methods typically use MRI-derived training labels, which may not align with stroke patterns in patient multimedia data. To address this mismatch, we propose an Adaptive Uncertainty-aware Stroke TrIage Network (AUSTIN) (Source code for the framework is at https://github.com/shuashua0608/AUSTIN ), that leverages inconsistencies between clinician triage decisions and MRI-derived labels to enhance AI-driven stroke triage. This approach mitigates overfitting to clinician-MRI disagreement cases during training, significantly improving test accuracy. Additionally, it identifies high-uncertainty samples during inference, prompting further imaging or expert review. Evaluated on a clinical stroke patient dataset collected in an ER setting, AUSTIN achieves over 20% performance gain over human triage and a 13% improvement over a prior state-of-the-art method. The learned uncertainty scores also show strong alignment with discrepancies in clinical assessments, highlighting the framework’s potential to enhance the reliability of AI-assisted stroke triage.