Fetal Health Classification using Hyperparameter Tuning
:max_bytes(150000):strip_icc()/GettyImages-1288913695-230c3b035bce4442b29e1598a492022d.jpg)
Fetal health monitoring is crucial for ensuring the well-being of both the mother and the baby during pregnancy. It helps in the early detection of potential complications, such as fetal distress or growth abnormalities, allowing for timely medical intervention. Effective monitoring can significantly reduce the risk of adverse outcomes and contribute to a healthy pregnancy and safe delivery.
A Cardiotocography (CTG) test is a prenatal monitoring technique used to assess fetal well-being by measuring the fetal heart rate (FHR) and uterine contractions. This model classifies the outcome of Cardiotocogram test to ensure the well being of the fetus.
The dataset used in this project is available in the data directory. It is in CSV (Comma-Separated Values) format.
This dataset contains 2126 records of features extracted from Cardiotocogram exams, which were then classified by three expert obstetritians into 3 classes:
- Normal
- Suspect
- Pathological
Dataset Source Link: kaggle dataset
EDA Notebook
Model-training Notebook
Note: Switch to T4 GPU for faster execution
Currently working on creating frontend interface for this model and hosting it.
The Fetal Health Classification project is intended solely for educational and demonstration purposes. The predictions generated by this project should not be used as a basis for medical treatments. Always seek the advice of a qualified healthcare professional before making any medical decisions or starting any treatment.
If you like this project, do give it a ⭐and share it with your friends