we developed classifiers to predict the presence and severity of Parkinson’s Disease from gait recordings. We created a gait segmentation algorithm to extract features indicative of gait abnormalities, and then tested supervised learning models with forward feature selection.We diagnosed the presence of Parkinson’s with 85% accuracy, and severity with 75% accuracy.
-
Notifications
You must be signed in to change notification settings - Fork 1
marcoal/ParkinsonsGait
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Machine learning project to predict severity of Parkinson's using only sensors on patients feet
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published