Inspiration
- Doctor Shortages & Overburdened Healthcare Systems - Many regions lack enough doctors to provide timely healthcare. Healthcare assistants can help reduce the workload by handling basic medical queries, triaging symptoms, and providing preliminary guidance.
- Limited Accessibility to Healthcare - In rural or underserved areas, people may not have access to doctors. A chatbot can bridge this gap by providing basic medical advice, especially for preventive care and common illnesses.
- Long Wait Times for Consultations - Patients often have to wait weeks or months for a doctor’s appointment. A chatbot can provide instant responses, helping users determine whether they need to see a doctor urgently.
- Lack of Personalized Medical Advice - Generic healthcare websites provide one-size-fits-all answers. Your AI chatbot can provide personalized responses based on patient history, symptoms, and medical conditions.
- Mental Health Crisis & Stigma Around Seeking Help - Many people hesitate to seek mental health support due to stigma. A chatbot can provide anonymous mental health screening, coping strategies, and support.
- Medication & Treatment Adherence Issues - Many patients forget to take medications or misuse prescriptions.
AI assistant can provide therapeutic dietary recommendations, check for drug interactions and
What it does
MedNova - Your Smart Companion for better Health!:
- Personalized Nutrition & Meal Planning – Tailors meal recommendations based on medical conditions.
- Drug Interaction Detection – Identifies potential adverse drug interactions.
- Disease Information – Offers insights into various diseases, including causes and risk factors.
- Symptom Analysis – Helps users understand potential conditions based on reported symptoms.
- Treatment & Cure Suggestions – Provides guidance on medical treatments and home remedies.
- Medical Q&A – Answers general health-related queries using AI-driven responses.
- Patient-Doctor Dialogues – Simulates doctor-patient conversations to improve medical communication.
How we built it
- Model Integration – We incorporated Falcon-7B-Instruct-Sharded (6.2 billion parameters) for accurate medical Q&A responses. Then we fine tuned the model on medical data.
- User Interface – We utilized Streamlit to create a seamless and interactive user experience.
Challenges we ran into
- Compute limitations slowed down our model training, causing delays in integrating additional features into the app.
Accomplishments that we're proud of
- We are proud to announce that our model is now available on Hugging Face, providing seamless integration for developers and researchers to easily incorporate it into their projects.
What we learned
- Developing MedNova required strong time management and strategic task distribution, ensuring smooth collaboration among our four team members.
- Through this project, we gained deeper insights into AI’s vast potential in revolutionizing the medical industry, from assisting healthcare professionals to improving patient outcomes.
What's next for MedNova
We are expanding MedNova’s capabilities by incorporating 3D and 2D image analysis to enhance diagnostic insights, object detection, and segmentation analysis. This will support:
- Organ segmentation – Assisting radiologists with AI-driven liver and lung segmentation for faster cancer diagnosis and treatment planning.
- Volume measurements – Helping detect diseases like chronic kidney disease and heart failure through precise organ volume assessments.
Built With
- css
- html
- huggingface
- javascript
- python
- transformers
Log in or sign up for Devpost to join the conversation.