Meeting Banner
Abstract #0233

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

Jing Wang1, Yike Guo2, Shixin Xu2, and Yu Luo3
1Department of Radiology, Shanghai Fourth People's Hospital, Shanghai, China, 2Duke Kunshan University, Kunshan, China, 3Shanghai Fourth People's Hospital, Shanghai, China

Synopsis

Keywords: Diagnosis/Prediction, Machine Learning/Artificial Intelligence, stroke;hemorrhagic transformation

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.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords