🚀 Predicting diabetes risk in females with AdaBoost Classifier! 💻✨

🩻 Detect lung nodules in CT scans using YOLOv8 and AWS SageMaker for early lung cancer diagnosis and efficient model deployment.

CIRC: A protocol layer for coordinating clinical agents across systems, specialties, and institutions. A protocol layer for deploying, coordinating, and governing autonomous AI agents in healthcare. CIRC enables clinical agents to route tasks, interoperate across systems (EHRs, claims, labs), and coordinate across specialties.

This project predicts lung cancer risks using machine learning models like Random Forest, Logistic Regression, and SVM. It analyzes patient data with features such as age, smoking habits, and symptoms. Data preprocessing, visualization, and performance evaluation ensure accurate predictions for early diagnosis.

AI/ML developer working on YOLOv8-based counterfeit capsule detection system for healthcare safety and deep learning research applications.

Parkinson's Disease detection using SVM with Linear Kernel on biomedical voice measurements — achieving 87.17% accuracy with real-time custom input prediction.

AI-powered heart disease risk assessment system with explainable predictions, lifestyle recommendations, and interactive what-if analysis.

Production-ready Multi-Disease Prediction Platform (Diabetes, Heart, Parkinson's). Features SVM/Logistic Regression models, batch processing, and automated clinical PDF reporting. Built with Streamlit & Scikit-Learn.

This project leverages YOLOv8 and AWS SageMaker to detect lung nodules in CT scan images — an essential step toward early lung cancer diagnosis. The system automates CT image preprocessing, model training, and deployment on SageMaker endpoints using scalable cloud infrastructure.

An AI-powered clinical assistant using Retrieval-Augmented Generation (RAG) on the MIMIC-IV DiReCT dataset. It retrieves relevant patient cases and generates diagnostic reasoning using LLMs. Built with Streamlit, Transformers, FAISS, and SentenceTransformers.

This study audits and mitigates fairness issues in cardiac MRI segmentation across SIEMENS, Philips, and GE scanners. A baseline 2D U-Net showed spurious vendor bias, particularly for the minority GE domain. Implementing a Domain Adversarial Neural Network reduced F1-Score disparity, stabilizing recall and improving clinical safety.

🩺 Complete Health Diagnostic Hub – A 🌐 web-based platform using 🤖 machine learning to predict potential health risks for ❤️ heart, 🩸 kidney, 🏥 liver, and 🩹 diabetes conditions.

A Python-based system to predict diabetes using Machine Learning with Support Vector Machine (SVM). Includes data preprocessing, model training, and evaluation to achieve high prediction accuracy.

This project focuses on applying a Variational Quantum Circuit (VQC) for diabetes prediction using real-world medical data.

NeuroDetect AI is a deep-learning based system that detects brain tumors and Alzheimer’s disease from MRI scans using optimized CNN and transfer-learning models. It provides fast and reliable predictions through a simple web interface with a Flask backend, offering an effective AI solution for early neurological diagnosis.

Contains the codes for the AcouSem-AFNet; Non-Invasive TB Detection using Acoustic and Semantic Features from Cough Sounds, MICCAI 2025

Automated Healthcare Compliance Tracker — Agentic Google Apps Script system using a multi-agent architecture to auto-manage student clinical placement compliance across multiple cohorts. Autonomous agents handle Drive scaffolding, real-time KPI dashboards, and 30-day expiry alert emails.

This project is a healthcare AI model built using Python and scikit-learn to predict patient health risk levels (Low, Moderate, High) based on demographic, socioeconomic, and medical history data.

🩺 Complete Health Diagnostic Hub – A 🌐 web-based platform using 🤖 machine learning to predict potential health risks for ❤️ heart, 🩸 kidney, 🏥 liver, and 🩹 diabetes conditions.