Projects

DeepONet Cardiovascular Modeling

Deep Operator Network for cardiovascular hemodynamics modeling with physics-informed constraints for patient-specific predictions.

PINO Coronary Flow Prediction

Physics-Informed Neural Operator (PINO) for efficient coronary artery blood flow simulation replacing traditional CFD methods.

EASYCHECK Dehydration & Viscosity System

Wearable PPG-based system for real-time dehydration assessment and blood viscosity monitoring in clinical settings.

PPG-based Fluid Loading Prediction

AI system for predicting fluid responsiveness using PPG spectrograms with ensemble deep learning models achieving AUC 0.85+

FFR Prediction & Coronary Artery Diagnosis

Optimized FFR prediction algorithm for diagnostic gray zone using hemodynamic features, synthetic models, and biometric data beyond conventional vessel imaging approaches.