Abstract:
Without a cure, stroke is the leading cause of death and disability worldwide. Deep learning-based stroke risk prediction models can outperform existing models with large, well-labeled data. Stroke data is usually split among hospitals due to health-care systems’ strict privacy policies. Additionally, positive and negative data are extremely imbalanced. Transfer learning can solve small data problems by using correlated domain knowledge, especially when multiple data sources are available. We propose a novel Hybrid Deep Transfer Learning-based Stroke Risk Prediction (HDTL-SRP) scheme to exploit the knowledge structure from multiple correlated sources (i.e., external stroke data, chronic diseases data like hypertension and diabetes). It outperforms current stroke risk prediction models in synthetic and real-world scenarios. It also shows the possibility of real-world deployment in multiple hospitals with 5 G/B5G infrastructures.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
