Description :
Medassis is a groundbreaking healthcare website designed to empower users by predicting diabetes risk through advanced machine learning algorithms. This Python-based platform allows users to input crucial health data such as height, weight, gender, HbA1c level, blood glucose level, hypertension status, smoking history, and previous heart disease records. The sophisticated ML model then analyzes this data to determine if a user has diabetes and assesses the probability of developing the condition.
The backend of Medassis is built using Flask, ensuring robust performance and scalability, while the frontend is crafted with HTML, CSS, JavaScript, Bootstrap, and Tailwind, offering a sleek and responsive user interface. Users can easily create accounts, log in, and save their health history, facilitating personalized and continuous health monitoring.
One of the standout features of Medassis is its ability to generate immediate, detailed health reports as soon as users input their data. These reports provide final prediction details and are accessible within the app and sent directly to the user's email, ensuring a seamless and convenient experience. Moreover, Medassis offers the ability to plot 3D graphs, allowing users to visualize health trends of past users, distinguishing between those who are suffering from diabetes and those who are not.
Designed to be exceptionally user-friendly, Medassis provides actionable health insights, helping users proactively manage and monitor their health. By integrating cutting-edge technology with intuitive features, Medassis stands as a beacon of innovation in the healthcare industry, delivering a seamless and insightful experience for all its users.
Backend
Flask: A lightweight WSGI web application framework in Python that powers the backend of Medassis, ensuring robust performance and scalability.
Frontend
HTML: The standard markup language used to create the structure of the web pages.
CSS: Used for styling the web pages to make them visually appealing and responsive.
JavaScript: Adds interactivity and dynamic elements to the web pages.
Bootstrap: A powerful front-end framework that helps in designing responsive and mobile-first web pages.
Tailwind: A utility-first CSS framework for creating custom designs without writing custom CSS.
Machine Learning
Python: The primary programming language used for developing the ML model and the overall project.
ML Libraries: Utilizes popular libraries such as scikit-learn, TensorFlow, or PyTorch for building and training the machine learning model.
Data Visualization
Matplotlib/Plotly: Libraries used for plotting 3D graphs and visualizing health trends of past users, differentiating between those with and without diabetes.
User Authentication and Data Management
SQLAlchemy: An SQL toolkit and Object-Relational Mapping (ORM) library for managing user data and ensuring efficient database operations.
SQLite: A lightweight, disk-based database used for storing user data securely and efficiently.
Flask-Login: Manages user sessions and authentication, allowing users to create accounts and log in securely.
Email Integration
Flask-Mail: A Flask extension used to send health reports directly to users' email addresses, ensuring they have easy access to their health insights.
Additional Tools
Jinja2: A templating engine for Python used to create HTML templates dynamically.
WTForms: A form handling library for creating and validating forms easily within Flask.
This comprehensive tech stack ensures Medassis delivers a robust, efficient, and user-friendly experience, providing valuable health insights and seamless interaction for all users.
