Inspiration
According to 2017 data by Jama Neurol(2017), 3 top Neurological Disorders are stroke, Alzheimer's disease and other dementias, and migraine. According to Gooch et al.,1, in 2011, nearly 100 million Americans were affected by at least 1 of the more than 1000 neurological disorders.
What it does
Our model determines the chances of having a neurological condition from EEG data.
How we built it
We followed the following steps to build the solution.
- We analyzed the data
- Did some feature engineering to remove Null values and replace 0s with mean
- Tranied several models on the data to determine the best models that can predict the neurological condition
- Tested the models with test data
What we learned
We learned LSTM for multiclass classification today.
What's next for Neurological Disorder Analysis using NeuroTech@Rice Data
We'll try to refine the model and launch an application if possible.
References
GBD 2017 US Neurological Disorders Collaborators. Burden of Neurological Disorders Across the US From 1990-2017: A Global Burden of Disease Study. JAMA Neurol. 2021;78(2):165–176. doi:10.1001/jamaneurol.2020.4152
Thumbnail Image by Milad Fakurian on Unsplash
Built With
- colab
- data-analysis
- lstm
- machine-learning
- python
- randomforestclassifier
- scikit-learn
Log in or sign up for Devpost to join the conversation.