💡[Feature]: in the existing repo of Fetal Health Classification,I want to add XGBoost and LightGBM models which helps in increases the accuracy of the prediction #1233
Description
Is there an existing issue for this?
- I have searched the existing issues
Feature Description
XGBoost Strengths:
Optimized for speed and performance.
Works great with structured/tabular data.
Handles missing data efficiently.
Good for dealing with imbalanced datasets.
Best for:
Complex datasets where features interact in non-obvious ways.
Cases where accuracy is more important than making the model easy to explain.
LightGBM Strengths:
Very fast training, even on large datasets.
Works well with many features and can handle missing or sparse data.
Best for:
Large datasets with many rows and columns.
Often faster than XGBoost while still giving good accuracy.
Accuracy potential:
Similar or slightly better than XGBoost, especially for large or high-dimensional data.
Best use-case:
If you need faster training while maintaining accuracy similar to XGBoost.
As of now in the project these have used with 96% highest accuracy
Logistic Regression
Decision Tree Classifier
Random Forest Classifier
Gradient Boosting Classifier
Use Case
Use Case:
Scenario: Expecting mothers go for regular check-ups during pregnancy, where doctors monitor the health of the fetus using tests like Cardiotocogram (CTG).
Problem: Sometimes, it’s hard to tell if a fetus is healthy or if there might be problems. Mistakes can happen, leading to undetected issues that could harm the baby or mother.
Solution: Use machine learning models to analyze the CTG data and classify the fetal health into three categories: normal, suspect, and pathological.
Benefits
Early Detection of Risks: Better accuracy helps find problems early, allowing timely medical help for mothers and babies.
Reducing Infant Mortality: Accurate predictions lower the chances of stillbirths and deaths by identifying high-risk pregnancies needing extra care.
Better Resource Allocation: Hospitals can use resources wisely, focusing on high-risk cases for timely support.
Improved Maternal Health: Accurate predictions lower the risk of undiagnosed issues, helping to keep mothers healthy during childbirth.
Increased Trust in Technology: Higher accuracy builds trust in AI tools, helping doctors and families rely on technology for better care.
Reducing Healthcare Costs: Finding problems early cuts down on expensive emergencies and long-term care needs.
Add ScreenShots
its not there
Priority
High
Record
- I have read the Contributing Guidelines
- I'm a GSSOC'24 contributor
- I want to work on this issue