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.

[NeurIPS 2025] MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks

HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research

[WWW-2025] ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration

Built a regression model that predicts the expected days of hospitalization time and an uncertainty range estimation.

Computer Vision

扩散模型相关综述论文与学习资料的系统整理，涵盖基础理论、算法演化与最新研究方向。#扩散模型 #稳定扩散 #潜在扩散模型 #去噪扩散模型 #生成模型 #深度学习 #机器学习 #计算机视觉 #神经网络 #科研 #综述 #入门教程 #医学人工智能 #医疗AI #医学影像 #视网膜影像 #糖尿病视网膜病变 #图像生成 #PyTorch项目 #开源项目 #GitHub项目 #人工智能学习 #AI算法 #研究论文 #深度生成模型 #AI教育 #医疗研究 #机器学习综述

Built an activity-aware pulse rate estimation using PPG and Accelerometer sensors.

The project focuses on building machine learning models for dental image classification and detection. Using CNN for image classification and YOLOv5 for object detection, the models aim to identify various dental conditions from medical images. The repository contains the data preprocessing pipeline, model training, and evaluation methods.

Assisting a radiologist in classifying a given chest x-ray for the presence or absence of pneumonia using Deep Learning.

Gene Regulatory Network Inference

Reinforcement Learning for policy-making for epidemics (EpiPolicy https://youtu.be/JDYb4_coAf4)

Approximated missing values in noisy, heterogeneous electronic health records by low rank modeling.

A maternal health platform empowering ASHA workers with smart data tools to detect high-risk pregnancies, deliver personalized dietary advice, and ensure safer outcomes in rural India.

[ACIIDS 2024] DiabetesNet: A Deep Learning Approach to Diabetes Diagnosis

End-to-end explainable AI pipeline for medical classification using Random Forest and XGBoost with SHAP and LIME for global and local interpretability. Designed for transparent, trustworthy machine learning in healthcare and research applications.

AI Skills for Dentists - Research critique, clinical evidence review, and content creation tools for Claude Desktop and Codex

Project SWASTHYA is an AI-driven healthcare platform for early cancer detection using machine learning and deep learning. It analyzes medical images and clinical data with CNNs and ML models, offering modular pipelines and Streamlit-based prediction apps for research and education.

Full-stack codebase (backend, frontend, AI modules) for the official https://mosaico.iss.it/ web platform, hosted by the Istituto Superiore di Sanità.

Ontology-based smart recipe recommender system using OWL 2.0 and DL queries