Lilyana Khatib is a passionate and skilled Machine Learning (ML) Algorithm Engineer with a focus on machine and deep learning algorithms. Holding a Master’s degree in Computer Science, she specializes in applying advanced machine learning techniques to real-world challenges, particularly in the healthcare and medical fields. She is known for her quick learning ability and disciplined approach to problem-solving. In her current role at Biosense Webster, Lilyana is involved in developing algorithms for electrophysiology and cardiac rhythm, contributing to the advancement of medical technology. Beyond her professional work, she is actively engaged in volunteering efforts, including mentoring and empowering Arab women in STEM and exposing high-school students to the world of technology. Her research interests also extend to adaptive testing systems and computer vision applications.
Profile
Scopus
Education
Lilyana Khatib completed her M.Sc. in Computer Science at the University of Haifa, graduating with a GPA of 95, cum laude. During her studies, she focused on machine learning and its applications in various domains, including healthcare. She pursued a Deep Learning course at the Technion, where she achieved an impressive grade of 97, demonstrating her mastery in the field. Her academic career was marked by a commitment to excellence, combining theoretical knowledge with practical research. Her B.Sc. in Computer Science from the University of Haifa, with a GPA of 83, laid the foundation for her deep interest in artificial intelligence and machine learning. Lilyana’s academic training enabled her to conduct high-impact research, such as her thesis on adaptive testing for fall risk assessments. She continues to build on this foundation through her professional work and volunteer initiatives.
Experience
Lilyana Khatib’s professional experience spans across various aspects of machine learning and algorithm development. Currently working as a Machine Learning Algorithm Engineer at Biosense Webster since 2022, Lilyana designs and implements ML algorithms, addressing challenges in electrophysiology and cardiac rhythm. She manages end-to-end ML pipelines, including data collection, feature engineering, model development, and evaluation. In this role, she collaborates with multidisciplinary teams, including hardware, software, and clinical experts, to integrate algorithms seamlessly. Prior to this, she worked as a Research Assistant at Bar Ilan University, contributing to ML research on sign language recognition and motion capture analysis. Additionally, she served as a Teaching Assistant at the University of Haifa, tutoring computer science students and creating AI lab exercises. Lilyana’s diverse experiences allow her to approach problems with both academic rigor and practical insight, making her a versatile contributor to machine learning projects.
Awards and Honors
Lilyana Khatib has received several academic and professional accolades throughout her career. She graduated with distinction (cum laude) from the University of Haifa with a Master’s degree in Computer Science, reflecting her strong academic performance and dedication to excellence. Her research contributions have also earned recognition in the field of machine learning, with her work on adaptive testing algorithms for older adults being published in Applied Sciences. In addition, her participation in international conferences such as the Language Resources and Evaluation Conference (LREC) in Marseilles, France, where she co-authored a paper on sentiment analysis, further highlights her standing in the research community. Beyond academic awards, Lilyana is also celebrated for her leadership roles, especially in mentoring and empowering underrepresented groups in STEM, such as her involvement as a team lead at AWSc and a mentor at Tsofen, showcasing her commitment to fostering diversity and inclusion in technology.
Research Focus
Lilyana Khatib’s research focuses on the intersection of machine learning, healthcare, and computer vision. Her primary area of interest lies in developing advanced algorithms for healthcare applications, specifically in cardiac rhythm analysis, electrophysiology, and fall risk assessments. Through her work at Biosense Webster, she applies both classic machine learning and deep learning techniques to real-world challenges in the medical field, improving patient outcomes through more accurate diagnostics and assessments. Lilyana’s M.Sc. thesis, which explored a machine learning-based computerized adaptive testing algorithm for fall risk, demonstrates her dedication to healthcare technology. Additionally, she has worked on projects such as the Crying Detection Application, which uses computer vision to detect emotional states without relying on audio. Her research is highly interdisciplinary, integrating computer science, healthcare, and AI, and aims to make a meaningful impact on medical practices and patient care, particularly for vulnerable populations such as older adults.
Publications
- Using Machine Learning to Shorten and Adapt Fall Risk Assessments for Older Adults 🧠📊 (Applied Sciences, 2025)
- Capturing Distalization 📖 (Workshop on Sentiment Analysis and Linguistic, LREC, Marseilles, France, 2022)