This repository houses machine learning models and pipelines for predicting various diseases, coupled with an integration with a Large Language Model for Diet and Food Recommendation. Each disease prediction task has its dedicated directory structure to maintain organization and modularity.

The project uses natural language processing and information retrieval to create an interactive system for user queries on a collection of PDFs. It involves loading, segmenting, and embedding PDFs with a Hugging Face model, utilizing Pinecone for efficient similarity searches

video capsule endoscopy abnormality classification for capsule vision 2024 challenge

Official PyTorch Implementation of paper 'Edge-Based Graph Neural Networks for Cell-Graph Modeling and Prediction'

💻🔒 A local-first full-stack app to analyze medical PDFs with an AI model (Apollo2-2B), ensuring privacy & patient-friendly insights — no external APIs or cloud involved.

Smart solution addressing PTSD, security, and post-service instability for military personnel

A TSX-based wellness and cycle care tracking app with mood journal, symptom tracker, and AI assistant.

🌐 A full-stack telehealth platform enabling virtual consultations, real-time symptom prediction via AI, and chatbot-assisted triage — built with React, Node.js, and Python.

A curated list of tools, frameworks, applications, datasets, and resources for AI in Healthcare.

AI Toolkit for Healthcare Imaging in Keras 3

A full-stack medical helpline website with Live predictions usings fitbit or health band

ML-based system for disease prediction from symptoms and prescription recommendation

ChannelMAE is a combination of MAE and ChannelViT

Binary classification of breast cancer using PyTorch. Used StandardScaler, LabelEncoder, Dataset, DataLoader, custom nn.Module model, BCELoss, and SGD. Focused on implementing a complete training pipeline, not optimizing accuracy.

Detection of presence or absence of pneumonia in chest x-ray images using a CNN deep learning architecture

Health Information Website with Chatbot Source Code

AI-powered medical assistant chatbot for symptom checking, disease prediction, severity analysis, and self-care guidance

Hero-V1 is an Android app and website featuring an AI-powered chatbot that identifies illness categories based on symptoms, like cancer. Built with Jupyter Notebook, TensorFlow, Flask, and Android Studio, it streamlines healthcare by providing symptom-based insights.

🏥 DICOM Flask App – AI-Powered Lesion Detection A Flask-based web app for uploading, processing, and analyzing DICOM medical images. Uses DeepLesion (Faster R-CNN) for lesion detection and ResNet50 for classification. Features a multi-tab UI with sidebar navigation. A sample DICOM file is included for testing!

AI-powered healthcare assistant that helps users identify symptoms, check medicines, and find specialized doctors — accessible anytime, anywhere.