Inspiration
This web application focuses on women's health and environment's protection. Women health and environmental protection are linked together. Because of women’s relationship with the environment, they can be critical agents of environmental conservation, sustainable development and adaptation to climate change. So, both women and environment are inter-dependent on one another. I have developed a web application which will help women analyze their lifestyle and menstrual health in an eco-friendly manner keeping the environment clean and green.
What it does
In this web application, I have provided two types of assessment which women can take. First is a Lifestyle Assessment and second one is an ML-based PCOS Risk Prediction Test.
A healthy lifestyle is one which helps to keep and improve our health and well-being. But in the chaos of a woman's daily life, healthy living may take back seat to chores. To tackle such situations, I have developed a lifestyle assessment based on the multiple online resources. This assessment will help women analyze their lifestyle choices in depth and will help them highlight some of the flaws in their current lifestyle.
PCOS is a common health problem caused by an imbalance of reproductive hormones. Women of all races and ethnicities are at risk of PCOS. Your risk of PCOS may be higher if you have some specific symptoms. So, based on some common symptoms and related datasets, I have developed this ML-based PCOS Risk Prediction Test which will inform women whether they are at risk of suffering from PCOS or not so that women at risk can get their clinical checkup done at the earliest and can start their treatment in case the results are positive.
Apart from these assessments, I have discussed ways of environmental protection through women. I have discussed about the importance of menstrual cups in protecting the environment and tried t encourage women to start using menstrual cups. I have also provided links from where women can purchase these cups.
Checkout the application live at http://sakkhi.pythonanywhere.com
Technologies Used includes:
- Python : Python is the programming language in which the ML model for PCOS detection is has been built.
- Flask : Flask is used to build the backend of the web application.
- Sklearn : This is the python library which is used to set up the ML random forest model.
- Javascript, HTML and CSS : These are the technologies which have been used to create the frontend of the web application.
- PythonAnywhere : This is the service which has been used to host the web application.
How I built it
I have used Python and Flask API to build the web application. I have used women health information from various online resources in order to spread awareness amongst women.
For the PCOS Risk Detection Test, I have used a dataset available on Kaggle which contains data from 10 different hospitals across Kerala, India. The dataset contains all physical and clinical parameters to determine PCOS. However, I have used only those parameters which can be easily recognized by an individual without much clinical help. The dataset size is however small, only 542 rows. In order to train this model, I first performed some data processing in order to remove the extra parameters and manage missing values. I have used Random Forest classification algorithm to generate a model.
Random forest is a supervised learning algorithm which is used for classification problems. This algorithm creates decision trees on data samples and then gets the prediction from each of them and finally selects the best solution by means of voting. It is an ensemble method which is better than a single decision tree because it reduces the over-fitting by averaging the result.
Challenges I ran into
Firstly, thinking about such an idea was a challenge in itself. Further, deciding about which machine learning technique to use for training the PCOS detection model was some work too.
What I learned
This was my first time building a complete Flask Application on my own, so this was a good learning experience.
What's next for Sakkhi
I want to eventually add many more features to the application like daily health insights and blogs on environmental protection, online fitness tools and tracker, menstrual cycle tracker and ovulation calendar and many more.
Log in or sign up for Devpost to join the conversation.