Prediction of Acute Ischemic Stroke Using diverse Machine Learning Models with an accuracy of 97.5%
Using a machine learning based approach to predict hemorrhagic stroke severity in susceptible patients.
Doctors could make the best use of this approach to decide and act upon accordingly for patients with high risk would require different treatment and medication since the time of admission. This could save lives since a time of action plays a crucial role in determining the lifespan of a patient stuck in coma. In return, such an approach where a model is trained over time with more such datapoints (new patients) could save more lives thereby increasing the medical standards.
The primary assumption made was that all medical factors could be contributing factors to predict the severity of strokes in patients.
This repo has all the project files for building an ML model to predict the severity of acute ischemic strokes (brain strokes) observed in patients. For quick navigation, use the following links:
© 2021 Dr. Harshika Chebolu
All copyrights of the dataset belong to Dr. Harshika Chebolu, Post Graduate in General Medicine at Gandhi Medical Hospital, Hyderabad, India.
Having trouble understanding or implementing this project? Check out the documentation or create a pull request and I could help you sort it out.