Student Wellness – Early Wellness Pattern Detection System

Create Account
Login
Check-in
Analysis
Dashboard

Inspiration

As students, we know how easy it is to get caught up in assignments, exams, deadlines, and everyday responsibilities. Sometimes we don't notice that we're sleeping less, feeling more stressed, getting mentally tired, or losing concentration until it starts affecting our daily life.

This inspired us to build Student Wellness. We wanted to create something simple that would encourage students to pause, check in with themselves, and understand whether their daily habits were forming unhealthy patterns.

What it does

Student Wellness allows students to complete a quick daily wellness check-in based on factors such as:

Sleep duration and quality
Energy levels
Academic workload
Stress
Mental fatigue
Concentration
Study breaks
Overall well-being

The system uses this information to generate a Wellness Score, identify a risk level, highlight contributing factors, and provide personalized recommendations.

The dashboard also allows students to view their previous check-ins and understand how their wellness changes over time through trends and visualizations.

How we built it

We built Student Wellness using Python and Streamlit for the application, SQLite for storing user and wellness data, and Pandas and Plotly for data processing and visualizations.

We created separate modules for authentication, wellness scoring, recommendations, and dashboard analysis. The application follows a simple flow: a student signs up, completes a daily check-in, receives wellness insights, and can return to the dashboard to track their progress.

Challenges we ran into

One of our biggest challenges was deciding how different factors should contribute to the overall Wellness Score. Sleep, stress, workload, energy, and mental fatigue all affect wellness differently, so we had to design a scoring approach that was simple enough to understand while still being meaningful.

We also faced challenges while implementing user authentication, storing user-specific records, connecting multiple Streamlit pages, and making sure the dashboard displayed useful information from previous check-ins.

Accomplishments that we're proud of

We are proud that we turned a simple idea into a working application that students can actually interact with.

We are especially proud of features like the Wellness Score and risk-level calculation, contributing-factor detection, personalized recommendations, trend visualization through the dashboard, and user-specific wellness history.

Most importantly, we are proud that the project focuses on early awareness rather than waiting until a student is already overwhelmed.

What we learned

This project taught us that building a useful application is about more than just writing code. We learned how to break a real-world problem into smaller technical components and connect them into one complete system.

We also gained practical experience with Streamlit, SQLite, data visualization, user authentication, Python modules.

Most importantly, we learned to think from the user's perspective and keep the application simple enough that someone would actually want to use it every day.

What's next for Student Wellness – Early Wellness Pattern Detection System

We want to make Student Wellness more intelligent and useful over time.

Some of our future plans include:

AI-based wellness trend prediction
More advanced early-warning pattern detection
Personalized recommendations based on long-term patterns
Wellness reminders and notifications
Improved data visualization
Anonymous, privacy-conscious wellness insights for institutions
Cloud deployment so students can access their wellness data from anywhere

Our long-term vision is to help students recognize changes in their wellness before they turn into bigger problems, while keeping the system focused on awareness, privacy, and prevention.