Dr. Ayelet Goldstein (Ph.D, M.B.A)

Research areas:
My research bridges advanced computational methods with practical healthcare applications. I focus on developing interpretable, clinically grounded models and systems that translate complex medical data and guideline knowledge into actionable decision support and measurable quality indicators.

1) Data Analysis & Machine Learning in Healthcare
My work centers on the practical integration of data analysis and machine learning in real-world healthcare settings to extract clinically meaningful insights from medical data and support improved diagnosis and treatment.
A key line of my research develops data-driven patient grouping and risk stratification methods. For example, we developed a multi-dimensional approach to subgroup fibromyalgia patients based on multiple health parameters, enabling identification of the most informative groupings for studying this heterogeneous condition.
Examples include:
1.        Ophthalmology ML: applying machine learning to analyze retinal and optic nerve measurements to identify patterns associated with visual impairment and support earlier detection.
2.        Predictive modeling in diverse populations: predicting proliferative diabetic retinopathy using routinely collected blood and urine tests, and explicitly examining how sex and ethnicity influence disease risk and model performance to better target clinical attention.

2) Clinical Decision Support Systems (CDSS) & Quality Assessment
I develop and evaluate methods for decision support and automated quality assessment by transforming clinical knowledge and guidelines into computable representations that can be applied at scale.
In one project, I contributed to a holistic framework for assessing quality of care, using pressure ulcer management as an exemplar. The framework encodes procedural care knowledge into temporal abstraction patterns and applies a fuzzy temporal logic algorithm to quantify adherence to care protocols and identify clinically relevant deviations.
In another project, I helped develop a distributed decision support architecture that emphasizes patient-centered care, using mobile devices to deliver evidence-based guidance at the point of need, supporting chronic disease management and patient independence.
Currently, I advise a student developing a novel episodic, guideline-based CDSS, aimed at supporting non-continuous decision-making and follow-up processes by triggering recommendations at clinically meaningful episodes rather than continuous monitoring.

3) Knowledge Representation & Temporal Abstraction in Clinical Data
My research in clinical data analysis has led to the development of a Temporal Abstraction Knowledge Language designed to convert complex clinical data into higher-level concepts suitable for computational reasoning.
This language serves as the foundation for an inference engine I developed to identify clinically significant temporal patterns in patient records (e.g., sustained states, changes over time, recurring events, and timing-related deviations). The engine translates dense, irregular clinical timelines into clear, interpretable representations that can support decision support and quality measurement.

Articles in Refereed Journals:

1.        Canada, F. C., Parcerias, J.G., Bartomeu, J.P., Salvador, H., Cardenosa, A.L., Rosanas, E.P., Goldstein, A., Utilizing Optical Coherence Tomography and Machine Learning to Predict Vision Loss in Pediatric Neurofibromatosis Type 1 Patients, Scientific Reports, January 2026.

2.        Ben-Shahar, B., Shahar, Y., Jaffe, S., Cohen, O., Shalom, E., Selivanova, M., Rimon, E., Hochberg, I., Goldstein, A., Integrating retrospective quality assessment with real-time guideline application to support the episodic application of clinical guidelines over significant time periods, Journal of Biomedical Informatics, December 2025

3.         Ifrah R.*, Besser, A.*, Goldstein, A., Beiderman, Y., Gantz, L., Psychological Stress as a Mediator in the Relationships Between Personality Characteristics and Eye-Blinking Behavior, Behavioral Sciences, November 2025.

4.        Doron, R., Shneor, E., Ostrin L., Gordon-Shaag, A, Goldstein, A., Near Viewing Behaviors predict educational system in a machine learning model, Scientific Reports, July 2025.

5.        Ben-Eli, H. Cnaany, Y., Chower, I., Goldstein, A., The Effects of Age and Sex on the Risk Factors, Complications and Outcomes of Cataract Surgery Performed by Residents, Scientific Reports, January 2025.

6.        Shalom, E., Goldstein, A. (equal contribution), Weiss, R.Selivanova, M. Melamed Cohen N., Shahar, Y., Implementation and Evaluation of a System for Assessment of The Quality of Long-Term Management of Patients at a Geriatric Hospital. Journal of Biomedical Informatics, July 2024.

7.        Goldstein, A., Ding, K., Carrasquillo, O., Levine, B. Hasan, A., Levine, J., Prediction of Proliferative Diabetic Retinopathy using Machine Learning in Latino and Non-Hispanic Blacks Cohorts. Ophthalmic and Physiological Optics, July 2024

8.        Cnaany, Y., Goldstein, A.,(equal contribution),  Lavy, I., Chowers, I., Ben-Eli, H., Ophthalmology residents experience in cataract surgery and the risk for intraoperative surgery complications - Journal ophthalmology & therapy, March 2024

9.        Goldstein, A., Shahar, Y., Weisman, M.R., Peleg, H., Ben-Chetrit, E., Ben-Yehuda, A., Shalom, E., Goldstein, C., Shiloh, S.S., Almoznino, G., Multi-dimensional Validation of the Integration of Syntactic and Semantic Distance Measures for Clustering Fibromyalgia Patients in the Rheumatic Monitor Big Data Study, Bioengineering Journal, January 2024 

10.        Doron, R., Gordon-Shaag,A., Shneor, E., Goldstein, A., Ostrin, L.A., “Objective Quantification of Viewing Behaviors During Printed and Electronic Tasks in Emmetropic and Myopic Ultra-Orthodox Jewish Men”, Ophthalmic Physiol Opt. 2023 Jan 20. doi: 10.1111/opo.13092. 

11.        Shalom, E., Goldstein, A. Ariel, E., Sheinberg, M., Fung, N., Jones, V., Van Schooten, B., Shahar, Y., Distributed application of guideline-based decision support through mobile devices: Implementation and evaluation, Artificial Intelligence in Medicine, Vol.129, 2022.

12.        Peleg, M., Shahar, Y., Quaglini, S., Broens, T., Budasu, R., Fung, N.,  Fux, A., García-Sáez, G., Goldstein, A., González-Ferrer, A., Hermens, H., Assessment of a personalized and distributed patient guidance system, International Journal of Medical Informatics, Vol.101, Pages 108–130, 2017.

13.        Peleg, M., Shahar, Y., Quaglini, S., Fux, A., García-Sáez, G.,  Goldstein, A., Hernando, M.E., Klimov, D., Martínez-Sarriegui, I., Napolitano, C., Parimbelli, E., Rigla, M., Sacchi, L., Shalom, E., Soffer, P., 2017, MobiGuide: a personalized and patient-centric decision-support system and its evaluation in the atrial fibrillation and gestational diabetes domains, User Modeling and User-Adapted Interaction, Vol.27, Pages 159–213.

14.        Goldstein, A., Shahar, Y., Cohen, M., Orenbuch, E., Evaluation of an Automated Knowledge-Based Textual Summarization System for Longitudinal Clinical Data, in the Intensive Care Domain, Artifical Inteligence in Medicine, Vol.82, Pages 20-33, 2017.

15.        Goldstein, A., Shahar, Y., An Automated Knowledge-Based Textual Summarization System for Longitudinal, Multivariate Clinical Data, Journal of Biomedical Informatics, Vol.61, Pages 159-175, 2016. Selected as the Journal’s editor’s choice.

Articles in Conference Proceedings:

1.        Ben-Shahar, B., Shahar, Y., Jaffe, S., Cohen, O., Shalom, E., Slivanova, M., Rimon, E., Goldstein, A., Supporting the Episodic Application of Clinical Guidelines
 over Significant Time Periods, Medical Informatics Europe Conference (MIE), Aug 2024.

2.        Jaffe, S., Ben-Shahar, B., Shahar, Y., Goldstein, A., Shalom, E., Slavinova, M., Rimon, E., Cohen, O., Using Formal Knowledge to Support Episodic Evidence-Based Nursing Care, Medical Informatics Europe Conference (MIE), August 2024.

3.        Jaffe, S., Ben Shahar, B., Shahar, Y., Goldstein, A., Shalom, E., Slavinova, M., Rimon, E., Cohen, O., Formal Representation of Nursing Clinical Guidelines to Support Episodic Consultation. Third International Workshop on Artificial Intelligence in Nursing (AINurse24) in conjunction with the 22nd International Conference of Artificial Intelligence in Medicine (AIME 2024), Salt Lake City UT, July 2024

4.        Cnaany Y., Goldstein, A., Lavy, I. Chowers, I., Ben-Eli, H., Ophthalmology Residents Cataract Surgery: Pre-op risk factors, Intraoperative complications, and Outcomes, ARVO 2024, Seattle, Washington, USA.

5.        Goldstein, A., Levin, J., Gordon-Shaag, A., 2023, Machine learning for classification Proliferative Diabetic Retinopathy in Latino and African American Cohorts, Poster presentation at ARVO 2023, New Orleans, LA.

6.        Goldstein, A., Levin, J., Gordon-Shaag, A., 2023, Machine learning for classification Proliferative Diabetic Retinopathy in Latino and African American Cohorts, Oral presentation at ISVER 2023, Haifa, Israel.

7.        Shalom, E., Edry, R., Goldstein, A., Gafni, U., Shahar, Y., 2017, Completing “non-evidence” clinical guideline knowledge: implications for methodological support, Health Informatics Workshop: applications that use knowledge and data, Haifa, Israel. 

8.        Shalom, E., Shahar, Y., Goldstein, A., Ariel, E., Sheinberger, M., Fung, N., Jones, V., Van Schooten, B., 2015, Implementation of the Distributed Guideline-Based Decision Support Model in the MobiGuide Framework. Proceedings of the 7th international workshop on knowledge representation for health care (KR4HC), in conjunction with Artificial Intelligence in Medicine (AIME), Pavia, Italy.

9.        Goldstein, A., Shahar, Y., 2015, Generation of natural-language textual summaries from longitudinal clinical records. Proceedings of the 15th world congress on health and biomedical informatics (MEDINFO), São Paulo, Brazil.

10.        Shalom, E., Shahar, Y., Goldstein, A., Ariel, E., Quaglini, S., Sacchi, L., Fung, N., Jones, V., Broens, T., Garcia-Saez, G., and Hernando, E., 2014, Enhancing Guideline-based decision support with distributed computation through local mobile application. Proceedings of the 7th international workshop on process-oriented information systems in healthcare (ProHealth), as part of The 12th international conference on business process management (BPM), Eindhoven, The Netherlands.

11.        Goldstein, A., Shahar, Y., 2013, Implementation of a System for Intelligent 
Summarization of Longitudinal Clinical Records.  Proceedings of the 5th international workshop on knowledge representation for health care (KR4HC), in conjunction with Artificial Intelligence in Medicine, Murcia, Spain. (also published in: Process Support and Knowledge Representation in Health Care, Lecture Notes in Computer Science Vol.8268, Pages 68-82)

12.        Goldstein, A., Shahar, Y., 2012, A framework for automated knowledge-
based textual summarization of longitudinal medical records. Proceedings of the 4th international workshop on knowledge representation for health care (KR4HC), Tallinn, Estonia.

I collaborate with clinicians, researchers, and data science teams to develop and evaluate interpretable machine-learning methods, guideline-based clinical decision support, and automated quality assessment using real-world healthcare data.