Exploring clinical decision making
About Us
DataMED Lab at Tel Aviv University explores clinical decision-making through the lens of artificial intelligence and data science to bridge the gap between computational methods and the intuitive needs of healthcare professionals.
We analyze large-scale clinical datasets and integrate advanced computational methods:
including machine learning, deep learning, and natural language processing with both real-world medical records and simulated clinical environments.
This hybrid approach enables us to study clinical decision-making, optimize care workflows, and design AI-powered tools that directly support healthcare professionals and improve system efficiency.
Among our projects: Developing a dynamic risk-stratification algorithm using Hebrew NLP and ML for emergency and community settings, Modeling clinical reasoning patterns through a conceptual framework inspired by behavioral analysis, Evaluating how large language models (LLMs) and generative AI can augment clinical decision support, Piloting INTEGRA: an interactive triage system based on generative reasoning analytics.
Our international collaborations include: The EU JUST CT initiative (ESR iGuide) on imaging equity and safety, Remote stroke diagnosis through AI-driven platforms, Identifying women at high risk of breast cancer using NLP-based approaches, And building dynamic algorithms for patient prioritization in resource-constrained environments.
Through these diverse projects, we aim to bridge clinical insight with data-driven innovation; translating ideas into impactful tools that improve healthcare delivery.
_edited.jpg)
_edited.jpg)
Our PhD Students
PhD student
Etti Naimi
Decision-making models and their applications in nursing clinical practice: A Conceptual Framework derived from behavior analysis
PhD student
Roman Filshtniski
AI in the nursing field
In collaboration with Prof. Sivia Bar-Noy
PhD student
Sara Kivity
The "career" of chronic illness
In collaboration with Pro. Michael Barilan
and Dr. Reut Noham
PhD student
Neta Shanwetter Levit
Modeling the Health-Seeking Behavior and Decision-Making in Cancer Patients: The Role of Pivotal Decision Agents and Emerging AI Technologies
PhD student
Aya Sarsour
Professional Identity, Responsibility, and the Use of Smart Search Technologies Among Nurses: A Comparative Study
PhD student
Hadas Shachaf
Leveraging Generative AI to Improve Medication Safety: A Decision Support Approach to Minimizing Prescribing Errors
PhD student
Nuha Abo Yunis
How does AI-based clinical instruction, compared to human-led instruction, influence nursing student׳s epistemic trust, ethical attitudes, decision-making processes, learning outcomes, and the nature of instructor–learner interaction.
PhD student
Katia Shleonsky
Examining the contribution of generative artificial intelligence to individual and collective mindfulness in team decision- making processes of nurses in a simulated field
PhD
Moriya Suliman
An examination of the factors associated with the accuracy of clinical decision-making among nurses, through the analysis of cognitive processes and multidimensional monitoring
PhD candidate
Michal Davidson Katzir
Compassion fatigue, resilience levels, and mindfulness among medical staff, exposed to treating injured patients from the Iron Sword war, compared to staff not exposed to treating war-injured patients
PhD candidate
Liron Zohar
Regulatory Sandboxes in Healthcare: Comparative Analysis and Recommendations for the Israeli Model
Our MSc Students
MSc student
Shaked Mondani Dollev
AI in the ED: Effects on Patient Safety and Quality of Care.
MSc student
Mahmoud Hamdan
GenAI to Transform Inpatient Discharge Summaries to Patient-Friendly Language and Format
MSc student
Natalia Weiner
Integrating overseas nursing program graduates into Israeli healthcare institutions: Challenges, barriers and opportunities
MSc student
Dana Balog
The Mediating Role of Initial Nursing Anamnesis in Triage in the Gap Between Reported Pain at Admission and Discharge from the ED
MSc student
Dani Greenberg
Understanding Reasons for Returning to the ED After Urgent Care Clinic Discharge Without Referral
MSc student
Sharinne Herzig
The association between training based on personalized videos and self-efficiency and hospital revisits among patients who underwent stoma surgery
MSc student
Michal Berkovich
Interaction between human and machine: Examining the degree of compatibility between the recommendations of an AI system with a medium level of autonomy and the medical team’s decisions in the decision-making process in the ED.
MSc student
Dr. Lior Moskovich
Utilizing AI in Medical Imaging Tests: Mapping Current Applications, Team Attitudes, and Predicting its Impact on Radiological Workforce
MSc student
Reshef Peled
Integrating overseas nursing program graduates into Israeli healthcare institutions: Challenges, barriers and opportunities
Publications
Recent publications (selected)
Levin, C., Orkaby, B., Suliman, M., & Saban, M. (2026). From metrics to morals: Evaluating ethical and clinical dimensions of AI in ICU decision-making. Ethics and Information Technology.
Khermesh, K., Alon, Y., Gatt, R., Deutsch, V., Shalev, I., Badelbayev, T., Elkalay, Y., Kirgner, I., Saban, M., & Katz, B.-Z. (2026). Digital decision support using a phospholipid-dependent biomarker for early exclusion of negative cases in lupus anticoagulant diagnostics. npj Digital Medicine.
Kivity, S., Barilan, Y. M., Noham, R., & Saban, M. (2026). Using a large language model to support thematic analysis of patient experiences in chronic illness management: Comparative qualitative study. Journal of Medical Internet Research.
Gargi, Y., Levran, N., Vine, J., Cohen, A., Weiner, D., Stein, D., Levi, O., Cohen, D., Klein, J., Taube, H. S., Glebov, M., Lazebnik, T., Saban, M., Efrat, S., Drori, E., Haviv, Y., & Segal, E. (2026). Detecting the metabolic transition to personalize nutritional timing: Model development and preliminary validation in a large ICU cohort. Critical Care.
Orkaby, B., Segev, R., & Saban, M. (2026). How do dialysis nurses and AI reason clinically? A scenario-based comparative study. BMC Nursing.
Yonatan, G., Cohen A, Stein, D., Levi, O., Cohen, D., Klein, J., Taube, HS., Vine, J., Glebov, M., Lazebnik, T., Saban, M., Haviv, Y., & Segal, E. (2026). Noradrenaline-trajectory phenotypes in septic shock: derivation and external validation in two independent cohorts. Intensive Care Medicine Experimental.
Saban, M., Haim, G. B., Livne, A., Eden, H., Kreiss, Y., & Dankner, R. (2026). ChatGPT-4 versus emergency physicians for walk-in ED patients: history, differential diagnosis, testing, and disposition—a prospective feasibility study. Discover Artificial Intelligence.
Hack, S., Attal, R., Elazar, D., Alon, Y., Meyuchas, R., Livne, L., Madgar, O., & Saban, M. Cautionary Lessons from Real-World Testing of GPT-4.1 AI for Pediatric Foreign Body Aspiration. (2025). European Archives of Oto-Rhino-Laryngology
Singer, C., Saban, M., Luxenburg, O., Yellin, L. B., Hierath, M., Sosna, J., ... & Brkljačić, B. (2025). Computed tomography referral guidelines adherence in Europe: insights from a seven-country audit. European Radiology, 35(3), 1166-1177.
Sosna, J., Joskowicz, L., & Saban, M. (2025). Navigating the AI Landscape in Medical Imaging: A Critical Analysis of Technologies, Implementation, and Implications. Radiology, 315(3), e240982.
Shanwetter Levit, N., & Saban, M. (2025). When investigator meets LLM: A qualitative analysis of cancer patient decision-making journeys. NPJ Digital Medicine.
Levin, C., Zaboli, A., Turcato, G., & Saban, M. (2025). Nursing judgment in the age of generative artificial intelligence: A cross-national study on clinical decision-making performance among emergency nurses. International Journal of Nursing Studies, 105216.
Saban, M., Alon, Y., Luxenburg, O., Singer, C., Hierath, M., Karoussou Schreiner, A., & Sosna, J. (2025). Comparison of CT referral justification using clinical decision support and large language models in a large European cohort. European Radiology, 1-10.
Alon, Y., Naimi, E., Levin, C., Videl, H., & Saban, M. (2025). Leveraging natural language processing to elucidate real-world clinical decision-making paradigms: A proof of concept study. Journal of Biomedical Informatics
Levin, C., Orkaby, B., Kerner, E., & Saban, M. (2025). Can large language models assist with pediatric dosing accuracy?. Pediatric Research
Saban, M., Lutski, M., Zucker, I., Uziel, M., Ben-Moshe, D., Israel, A., ... & Merzon, E. (2025). Identifying diabetes related-complications in a real-world free-text electronic medical records in Hebrew using natural language processing techniques. Journal of diabetes science and technology, 19(4), 999-1007.
Events
Quarterly PhD Research Meeting, June 2026
As part of our quarterly PhD research meetings, the doctoral students of the DataMED Lab gathered to share research progress, conduct peer review of ongoing manuscripts, and discuss methodological and clinical challenges. Bringing together researchers from diverse disciplines—including nursing, health sciences, pharmacy, and data science—the meeting highlighted the value of interdisciplinary collaboration, constructive feedback, and a shared research community.
Lecture at the MIE 2026, Genova Italy
At the conference, our PhD student Roman presented a pilot study exploring how nurses respond to clinical support generated by AI compared to support provided by expert nurses.
The study examined how nurses used recommendations without knowing whether the guidance was written by ChatGPT or by an expert nurse. The findings highlighted differences in how clinicians adopt external recommendations, showing that clinical experience plays a central role in trust, reliance, and decision-making when interacting with AI systems.
Lecture at the Ministry of Health’s Forum for AI Implementers in Digital Health.
The discussion focused on one of the key questions in modern healthcare:
How can artificial intelligence be integrated into clinical decision-making while remaining aligned with real-world clinical practice?
The forum explored clinician involvement, trust, regulation, and the gap between promising AI pilots and actual implementation in routine care. Ultimately, the discussion emphasized that meaningful healthcare AI must support clinicians and adapt to the realities of patient care.
Lecture at the Engineering-Academic Knowledge Fund Seminar
The talk focused on one of the most urgent questions in modern healthcare:
How can we integrate artificial intelligence into clinical decision-making without losing the human element - the patient, the caregiver, and the connection between them?
It explored the opportunities presented by generative AI, the ethical dilemmas it raises, and the critical decision points where intuition, empathy, and clinical experience remain irreplaceable.
Presentation at ESICM 2024, Barcelona
As part of the ESICM 2024 conference in Barcelona, the Head of our Lab presented a talk titled:
"Human–GenAI Partnerships: Comparing ICU Nurse Triage and AI in Critical Care."
The lecture offered new insights into how generative AI can enhance the clinical expertise of ICU nurses. It explored the evolving relationship between human judgment and AI capabilities, highlighting the potential for collaboration -
not replacement - in the future of critical care.
Synergy Conference on BioImaging & AI
This groundbreaking event brought together leading experts in bioimaging and artificial intelligence for a day of interdisciplinary dialogue and innovation.
Organized by the Head of DataMED Lab at Tel Aviv University, the conference hosted over 100 participants — including radiologists, radiographers, health policymakers, and academic researchers — to explore new frontiers at the intersection of technology and clinical imaging.
Highlights from the Synergy Conference
The conference featured keynote talks by leading experts, including Prof. Rachel Miron on national wait-time measurement, Dr. Gad Levi on the future of radiology, and Prof. Jacob Sosna on implementing comprehensive AI solutions in healthcare.
Participants praised the event for fostering meaningful knowledge exchange in medical imaging and artificial intelligence. The discussions emphasized the importance of interdisciplinary collaboration and advanced technologies in improving patient care — setting the stage for future partnerships in this critical field.
Collaborations
.png)
Contact Us
Interested in working with us?
Whether you're a researcher, student, clinician, or industry partner - we’re always open to meaningful collaborations.
If you have an idea, a question, or a project you'd like to explore together, don’t hesitate to reach out.
We believe that innovation in healthcare starts with a good conversation.
Gray Faculty of Medical and Health Sciences,
Tel Aviv University