Tzuf Lahan

Research oriented MSc student in Information Systems Engineering with strong background in data science and machine learning. Experienced in applied research, model development, and hands-on experimentation with advanced ML and deep learning methods. Currently conducting thesis research on medical imaging using CT scans and deep learning, with a strong interest in language models, training strategies, and fine-tuning methodologies for real-world applications. Highly motivated to work at the intersection of cutting-edge research.

MSc Thesis: Detection of Abdominal Aortic Aneurysm (AAA) from CT Scans
Research project focused on detecting Abdominal Aortic Aneurysm using opportunistic CT scans of the lower spine.
The work applies deep learning–based medical image analysis techniques to identify vascular abnormalities in non-targeted clinical imaging data, aiming to support early detection and real-world clinical decision making.

Published Research – AI-Based Empathy Detection in Nursing Simulations
Peer-reviewed research article published in Clinical Simulation in Nursing (Elsevier, 2026) and available on ScienceDirect, investigating the feasibility of using computer vision and deep learning to detect empathic behavior in video-recorded nursing simulations.
The study developed and evaluated AI models for analyzing non-verbal cues such as eye contact, facial expressions, physical proximity, and touch, and compared algorithmic outputs with traditional observer-based empathy assessments.