Polycystic ovary syndrome (PCOS) is a common endocrine disorder in women of reproductive age that affects the menstrual cycle, fertility, and metabolic health. A comparative analysis of machine learning models for PCOS detection aims to evaluate and compare the performance of different machine learning algorithms for detecting PCOS based on various clinical, hormonal, and ultrasonographic parameters. The goal of such an analysis is to identify the best performing machine learning model for PCOS detection, which could be useful for improving the diagnostic accuracy and facilitating early intervention.

The notebook has been run locally using Python 3.7

To merge the data files using left join, put the datasets in same folder and run the follwing command:

python data_merge.py

Once done, the rest of analysis is in Jupyter Notebook, to run Jupyter Notebook issue this command:

pip install notebook
cd /your/directory/
jupyter notebook

Open Healthcare PCOS.ipynb