Post-PCI Cardiac Death Prediction via Synthetic Minority Augmentation and Stress-Tested Probability Quality

Mikhail Lazarev

Submission Type: I want my submission to be considered for poster only

Keywords: AI, machine learning, cardiology, PCI, bifurcation lesions, mortality prediction, class imbalance, synthetic data

TL;DR: We improve post-PCI cardiac mortality prediction by using synthetic minority augmentation and edge-case stress tests to boost rare-event detection and produce more clinically reliable risk probabilities.

Confirmation Of Submission Requirements: I submit an abstract. It uses the template provided on the submission page and is no longer than 2 pages.

Submission Number: 126