I am currently pursuing a Ph.D. in Biomedical Engineering at New York University Abu Dhabi and Tandon School of Engineering at NYU, as a Global Ph.D. Fellow with the Clinical AI Lab. In 2022, I earned my Master of Science in Data Science and Artificial Intelligence, with distinction, from Jordan University of Science and Technology. My master's studies were fully funded through the prestigious German Academic Exchange Service (DAAD) award. Prior to that, in 2014, I completed my Bachelor of Science in Industrial and Systems Engineering at the Islamic University of Gaza. My passion for data analytics, coupled with a strong belief in the transformative power of data to drive robust decision-making and innovative solutions, has led me to pursue a career in data science focused on machine learning applications for healthcare data.
My current research focuses on developing foundation models for structured electronic health record (EHR) data, with a particular emphasis on advancing the retrieval of patients historical events for clinical prediction tasks via retrieval-augmented techniques. I am interested in creating value-aware and context-sensitive encodings that better capture the complexity of patient trajectories, enabling more accurate prediction, retrieval, and decision-support systems. Ultimately, my goal is to design machine learning methods that are both clinically meaningful and computationally robust, advancing safer, more reliable, and patient-centered applications of artificial intelligence in healthcare.
https://saeedshurrab.github.io/
- EHR-RAGp: Retrieval-Augmented Prototype-Guided Foundation Model for Electronic Health Records
- Multimodal Deep Learning for Stroke Prediction and Detection using Retinal Imaging and Clinical Data
- Multimodal Machine Learning for Stroke Prognosis and Diagnosis: A Systematic Review
- Self-supervised learning methods and applications in medical imaging analysis: a survey
- Multimodal masked siamese network improves chest X-ray representation learning
