Rapid Thrombogenesis:

As a primary author of the study titled "Deep Learning Model Development for Thrombogenesis Prediction Using Hyperparameter Tuning" while working as a research apprentice at UNCP. In this project, we developed a predictive deep learning model to identify thrombogenesis in COVID-19 patients, achieving an R² of up to 94.8% on Computational Fluid Dynamics datasets.

PUBLISHED PAPER

My contributions included implementing hyperparameter optimization using Ray Tune and transitioning to Recurrent Neural Networks to enhance model performance. This work underscores my expertise in Python, PyTorch, deep learning, and algorithm design, and demonstrates my commitment to advancing patient care through innovative AI solutions. Paper

Rapid Thrombogenesis Prediction — Institute of Digital Engineering - USAThe long-term goal of this project was to produce software capable of reading magnetic resonance image (MRI) data from any patient and reporting thrombogenesis-related fluid dynamic metrics.

Page updated

Google Sites

Report abuse