Machine Learning Predicts Hemorrhagic Transformation after Stroke Using Diffusion and Perfusion Weighted MR Imaging

Motivation: Hemorrhagic transformation (HT) following acute ischemic stroke (AIS) critically affects patient prognosis. Goal(s): To develop reliable machine learning (ML) models for predicting HT in AIS patients using MRI. Approach: 379 AIS patients were randomly split into training and testing set. All underwent MRI including DWI and PWI within 24-hour of symptom onset, and had follow-up CT/MRI within 14-days. Clinical features and MRI parameters were collected. Six ML-algorithms were trained and optimized. Various fusion models were created. The best-performing model was selected based on testing set performance. Results: A Logistic Regression-based practical model and a refined fusion model were generated, freely accessible at https://yike-wood.github.io/HT-Predict/. Impact: Practical model effectively predicts HT outcome using only three key features with high efficiency. Refined model, enhanced with domain knowledge, achieves higher accuracy and more reliable predictions, which makes it a valuable approach in decision making especially under complicated situations.