Deep learning on pre-procedural computed tomography and clinical data predicts outcome following stroke thrombectomy.
James P DiproseWilliam K DiproseTuan-Yow ChienMichael T M WangAndrew McFetridgeGregory P TarrKaustubha GhateJames BeharryJaeBeom HongTeddy WuDoug CampbellP Alan BarberPublished in: Journal of neurointerventional surgery (2024)
The discriminative performance of deep learning for predicting functional independence was comparable to logistic regression. Future studies should focus on whether incorporating procedural and post-procedural data significantly improves model performance.
Keyphrases
- deep learning
- computed tomography
- electronic health record
- artificial intelligence
- big data
- convolutional neural network
- atrial fibrillation
- magnetic resonance imaging
- positron emission tomography
- current status
- acute ischemic stroke
- data analysis
- magnetic resonance
- contrast enhanced
- brain injury
- blood brain barrier
- dual energy
- image quality