Al-Driven Public Health Chatbot for Disease Awareness

Image of HTML BOT code
Image of HTML BOT code
profile of GITHUB
CODE of HTML in GITHUB
Image of HTML BOT code
Image of HTML BOT code
Image of HTML BOT code
Image of HTML BOT code
Image of HTML BOT code
Image of HTML BOT code
Image of HTML BOT code
Image of HTML BOT code
Image of HTML BOT code
Image of HTML BOT code
HTML CODE RUN
HTML CODE RUN
HTML CODE RUN

Inspiration

During the pandemic, misinformation spread almost as quickly as the virus. Many people struggled to find trustworthy health information. We wanted to build a simple, AI-driven chatbot that makes disease awareness more accessible to everyone

What it does

The chatbot answers basic health questions about common conditions like COVID-19, flu, and diabetes. Users can interact with it through a web interface and get instant responses with relevant health information.

How we built it

we can build it by many sources like js,python,html. but i like so it by fronted develment bt html,css and js

Challenges we ran into

Natural Language Understanding: Users don’t always type the exact disease name (e.g., “Tell me about corona” vs “What is COVID-19?”). Making the chatbot flexible enough to recognize variations was tricky.

Accuracy of Health Information: Since health is a sensitive domain, we had to make sure that the information provided was correct, up-to-date, and written in a simple way that anyone could understand.

Frontend–Backend Integration: Connecting the HTML/JS frontend with the Flask backend required handling CORS issues and ensuring smooth API calls.

User Experience: Designing a clean, friendly chat interface that feels natural but also remains simple to build was challenging with only HTML/CSS/JS.

Scalability: The initial version supports only COVID-19, flu, and diabetes. Expanding to more conditions while keeping the chatbot fast and lightweight required careful planning.

Error Handling: We had to make sure that if the server was down or a user asked something unrelated, the chatbot would still respond gracefully.

Accomplishments that we're proud of

Built a working chatbot in a short time.

Designed a clean, user-friendly interface.

Successfully connected the Flask backend with the web frontend.

What we learned

How to integrate Flask APIs with a web frontend.

Importance of CORS handling in full-stack applications.

How small, AI-like features (pattern recognition, keyword matching) can already provide real value

What's next for Al-Driven Public Health Chatbot for Disease Awareness

What’s Next

Expand Disease Coverage: Add more diseases and health conditions (e.g., hypertension, asthma, mental health topics) to make the chatbot more useful for a wider audience.

Smarter AI/NLP Integration: Move beyond simple keyword detection by integrating NLP models (like spaCy, GPT, or BERT) so the chatbot can understand natural language questions more flexibly.

Multilingual Support: Enable responses in multiple languages to reach non-English speakers and improve accessibility worldwide.

Voice Interaction: Add speech-to-text and text-to-speech features so users can interact with the chatbot by talking instead of typing.

Real-Time Data Integration: Connect with APIs from trusted health organizations (WHO, CDC, government portals) to provide up-to-date information and alerts.

Personalized Recommendations: Allow users to input basic health information and get tailored advice or educational resources (while keeping privacy in mind).

Mobile-Friendly & Deployable: Deploy the chatbot on cloud platforms, integrate with WhatsApp, Telegram, or a mobile app for broader reach.

Gamification for Awareness: Add quizzes or tips of the day to encourage people to learn about diseases in an engaging way.