|
--- |
|
title: Stroke Prediction App Streamlit |
|
emoji: 💻 |
|
colorFrom: green |
|
colorTo: gray |
|
sdk: streamlit |
|
sdk_version: 1.36.0 |
|
app_file: app.py |
|
pinned: false |
|
license: apache-2.0 |
|
--- |
|
|
|
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference |
|
|
|
# Early Detection of Stroke Risk with Machine Learning |
|
This project tackles the crucial task of predicting stroke risk using machine learning. It leverages a powerful model called Light Gradient Boosting (LightGBM) to analyze data and identify individuals who might be at higher risk of stroke. |
|
|
|
## Prioritizing Safety with Recall |
|
Unlike some models, this project prioritizes "recall," meaning it would rather recommend a checkup for a healthy person than miss someone with potential stroke risk. This approach ensures people get the necessary medical attention, even if they ultimately turn out to be healthy. |
|
|
|
## User-Friendly Experience with Streamlit |
|
The project is built with Streamlit, a framework designed for creating user-friendly web applications. This means the application is accessible and easy to navigate, allowing anyone to assess their potential stroke risk without needing technical expertise. |
|
|
|
## Overall Benefits |
|
Early Detection: The project empowers proactive healthcare by identifying potential stroke risks early. |
|
Prioritized Safety: The focus on recall ensures individuals with potential risk receive necessary checkups. |
|
User-Friendly Access: The Streamlit interface makes the tool accessible to a broad audience. |
|
|
|
### This project demonstrates the potential of machine learning to improve healthcare outcomes by providing a user-friendly tool for early stroke risk detection. |
|
|
