A physics-integrated deep learning approach using a hybrid 1D CNN-LSTM neural network to estimate patient-specific non-Newtonian blood viscosity from photoplethysmography (PPG) …
AI system for predicting fluid responsiveness using PPG spectrograms with ensemble deep learning models achieving AUC 0.85+
Addressed limitations in AI-based coronary diagnosis by incorporating hemodynamic flow features and biometric data beyond vessel imaging alone, improving FFR prediction accuracy in …
Optimized FFR prediction algorithm for diagnostic gray zone using hemodynamic features, synthetic models, and biometric data beyond conventional vessel imaging approaches.