Fetal Health Prediction

This project aims to predict fetal health using machine learning models, including Multinomial Logistic Regression, Random Forest Classifier, and Decision Tree Classifier, implemented in Jupyter Notebook. The dataset contains three target values [1, 2, 3], representing different fetal health states.

Features

• Multinomial Logistic Regression: Applied for multiclass classification.
• Random Forest Classifier: Utilized for robust predictions with ensemble learning.
• Decision Tree Classifier: Implemented for interpretable model outcomes.
• Data preprocessing and feature engineering for improved model accuracy.
• Evaluation metrics for comparing model performance.

Dataset

The dataset contains features related to fetal health, such as:

• Baseline FHR (fetal heart rate)
• Accelerations
• Decelerations
• Other relevant medical parameters

Target values represent:

1. Normal Fetal Health
2. Suspect Fetal Health
3. Pathological Fetal Health

Usage

1. Clone the repository:

   git clone https://github.com/MUNEEB502/fetal-health-prediction.git

2. Open the Jupyter Notebook:

   jupyter notebook Fetal_Health_Prediction.ipynb

3. Run all cells in the notebook to:
   • Load and preprocess the data.
   • Train and evaluate the models.
   • Visualize the results.

Results

• Multinomial Logistic Regression: Accuracy: 0.8753% .
• Random Forest: Accuracy: 0.9148% .
• Decision Tree: Accuracy: 0.8927% .

Visualization of results is embedded within the notebook for better insights.

---

CONTRIBUTING

Contributions are welcome! If you'd like to contribute to this project, please fork the repository and submit a pull request.

---

MUNEEB UR REHMAN (MUNEEB502)

🔗 Links