Similarity-first interpretability studio for breast tumor samples: pick a case, find its closest “twins” (benign/malignant look-alikes), visualize neighborhood structure, compare feature fingerprints, and run minimal-change counterfactual edits toward a target class. Educational demo only, not for diagnosis.

A MATLAB-based GUI tool that predicts diabetes risk using machine learning (Random Forest) on the Pima Indian dataset.

This project studies the use of machine learning techniques to predict the long-term outcomes of stroke victims.

🩺 AstraMed: A Clinical Risk Intelligence Platform. Powered by SOTA Ensemble ML & BioMistral-7B for predictive medical analytics and explainable risk scoring.

The aim of this project is to predicts the likelihood of patients getting heart disease. Therefore, allowing researchers to develop better ways to prevent this from happening and establish better patterns.

🎗️ Breast Cancer Detection using PyCaret - a low-code machine learning pipeline. This project leverages automation and explainability to classify malignant and benign tumors from the Breast Cancer Wisconsin dataset. Built for simplicity, transparency, and clinical insight.

NSGA-II multi-objective feature selection on medical tabular data. 9 of 30 features at 94.74% accuracy - matching full-feature baselines with 70% feature reduction.

7 ML classifiers (XGBoost, RF, SVM, LR, KNN, NB, LDA) predicting COVID-19 from blood/hematological parameters across 7 datasets; basis of a PLOS ONE paper

A Streamlit-based health risk analysis app that uses machine learning to estimate cardiovascular risk and track user responses over time.

Breast tumour classifier (Malignant vs Benign) — ML on 569 patients × 30 cell-scan measurements achieving 97.5% accuracy

Diabetes risk prediction — 6 ML models compared with feature scaling and GridSearchCV tuning (Random Forest ⭐ ~79% accuracy, ~85% ROC-AUC) on Flask

ML ensemble (RF + GB + XGBoost) for varicose vein recovery risk prediction with SHAP explainability, scenario comparison, FastAPI backend, and React dashboard.

Forecasting blood glucose 5–60 minutes ahead from continuous glucose monitor data — a convolutional-recurrent net with per-patient transfer learning (PyTorch).

Heart disease prediction web app — Random Forest classifier on 13 patient health inputs (~84% accuracy) with Flask UI and confidence scoring

This project predicts brain stroke risk using machine learning by analyzing medical and lifestyle factors. It includes data preprocessing, model training, and a simple web interface for real-time predictions. Designed for learning, research, and healthcare analytics, it demonstrates practical ML applications in disease-risk assessment.

🩺 AI-powered multi-disease prediction system using ML. Predicts Anemia, Thalassemia, Diabetes, Heart Disease & Thrombocytopenia from blood biomarkers. Built with Python, Streamlit & scikit-learn. Features admin panel, PDF reports & role-based access control.

This project is an interactive web application built using Streamlit that predicts whether a breast tumor is Benign or Malignant based on clinical cell nuclei measurements. The application uses a pre-trained Logistic Regression model trained on the Wisconsin Breast Cancer dataset.

PCOS Prediction using Classification Algorithms - Logistic Regression, Support Vector Machine, Naive Bayes and Random Forest.

An intelligent deep learning application for automatic teeth segmentation in panoramic dental X-rays. Uses UNet++ with ResNet50 encoder for high-accuracy detection. Built with Streamlit for easy clinical use, providing real-time visual feedback and overlay analysis.

Heart attack risk prediction — 5 ML models compared (XGBoost ⭐ ~88% accuracy, ~95% ROC-AUC) with Flask web app and 13 clinical inputs