Developing a Predictive Model for Ischemic Stroke Onset Time Using Transfer Learning

Introduction Identification of acute ischemic stroke (AIS) patients within the 4.5-hour therapeutic window is critical for therapy. Diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) sequences are an approach to determine whether the time since stroke (TSS) is within 4.5 hours. However, inter-observer variability and limited accuracy are observed in visual assessments. We aim to develop a transfer-learning model for predicting AIS onset within 4.5 hours. Materials and Methods 266 AIS patients with known TSS who underwent imaging scans before treatment were retrospectively analysed, divided into a training set (n = 211) and a validation set (n = 55). The model was built using DWI and FLAIR sequences. After image preprocessing and data augmentation, a 3D ResNet-18 pretrained on the Kinetics dataset was selected and adapted via transfer-learning with DWI–FLAIR input. The model performance was compared with human visual assessment, which was based on the DWI–FLAIR mismatch principle. Partial mismatch was defined as hyperintense infarct on DWI with a smaller corresponding hyperintense area on FLAIR. Results Baseline characteristics did not differ between the training and validation sets. On the validation set, the model achieved sensitivity of 0.833 (0.703–0.941), specificity of 0.880 (0.737–1.000), and AUC of 0.929 (0.758–0.935), outperforming human visual assessment (sensitivity 0.767(0.613–0.903); specificity 0.360(0.185–0.560); AUC 0.563(0.451–0.693)). For partial DWI–FLAIR mismatch cases, the model correctly classified all 15 cases, whereas humans classified 4. Conclusion The 3D ResNet-18 model shows promise in identifying AIS within 4.5 hours, including partial DWI–FLAIR mismatch, but requires multi-center validation before use.