Acute Stroke Prediction with Facial Images
The Deep Learning Model used in this dataset utilizes data augmentation techniques on images to improve the overall accuracy of the model. The model has a learning rate of 0.1 and is trained for 10 epochs. The model also uses k-fold cross-validation with a k-value of 3 to improve the robustness of the model and prevent overfitting. After training, the model achieved an accuracy of 94%. This high accuracy indicates that the model is able to accurately detect and diagnose acute stroke in patients using facial images. The model is a valuable tool for healthcare professionals and researchers working in the field of stroke medicine.
Distributed under the MIT License. See LICENSE for more information.