Industrial Thesis in Machine Learning for the achievement of Master of Science in Computer Science.

A command-line based intelligent patient monitoring system that analyzes health data using machine learning and rule-based logic to predict risk levels, detect condition escalation, and provide timely healthcare recommendations.

Explainable machine learning models for Type-2 diabetes risk prediction with focus on interpretability and clinical decision support.

Predicting traffic accident risk using Physics-Informed Feature Engineering and Advanced Stacking Ensemble (XGBoost, LightGBM, CatBoost).

This study aims to explore the impact of incorporating multiple predictors on diabetes risk prediction by comparing the performance of a multiple linear regression model with age, BMI, and family history against a simpler model using only blood pressure as a predictor.

It is a Capstone project. A model has been created to predict for the heart diseases. It can be very useful for the health sector as cardiovascular diseases are rapidly increasing. The record contains patients' information. It includes over 4,000 records and 15 attributes.

End-to-end EHR risk prediction pipeline using MLOps stack — MLflow, FastAPI, Docker, and config-driven training.

Interactive dashboard for predicting prediabetes risk using machine learning and SHAP interpretability. Built for clarity, modular benchmarking, and clinical transparency. Includes manual input prediction, threshold-based classification, SHAP visualizations, and model comparison across classifiers.

A machine learning-based solution designed to predict metabolic syndrome risk using clinical, demographic, and lifestyle data.

Graph based AI for early detection of underperformance in educational and organizational contexts implemented with Jac

Predicts second heart-attack risk with logistic regression; reproducible EDA, metrics, visuals, and PDF write-up.

The aim of this project is to predict the risk of osteoporosis in patients using a dataset of patients' medical records. Osteoporosis is a condition that weakens bones, making them fragile and more likely to break. It develops slowly over several years and is often only diagnosed when a minor fall or sudden impact causes a bone fracture.

SyntheticHealthSimulator generates realistic synthetic medical data for machine learning research. It models 20-year health trajectories based on lifestyle factors, biomarkers, and genetic risks. NOT FOR CLINICAL USE.

ML pipeline Portfolio project to predict cardiovascular risk using NHANES health survey data (2017-2018). XGBoost classifier with threshold tuning, ROC/PR evaluation, and automated reporting.

Production-ready ML pipeline for retail banking default prediction with feature engineering, CatBoost models, and Dockerized FastAPI deployment on Google Cloud.

An AI-driven mobile app platform that predicts burnout in homemakers using daily routine and mental health indicators, and provides personalized, real-time interventions to prevent physical and emotional exhaustion.

Machine learning system that predicts heart disease risk using patient health data and visual insights

End-to-end cardiovascular risk assessment system using statistical analysis and machine learning. Includes EDA, hypothesis testing, feature engineering, recall-focused modeling, interpretable results, and a Streamlit web app for probability-based risk stratification and decision support.

ML-based heart disease risk prediction with explainability (SHAP) and Streamlit demo

A tool for predicting the chance of breast cancer based on data.