EZEyal Zimlichman

Eyal Zimlichman

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Eyal Zimlichman has a total of 123 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Partnerships to advance patient safety and address preventable harm: case studies from international health care leaders

    by Rachel Bonesteel, Robert Saunders, Tilithia McBride, Susan Sheridan, David W Bates, Mark McClellan, Charles H Kahn, Eyal Zimlichman

    There have been notable improvements in patient safety in recent years; however, significant challenges remain in reducing the incidence of preventable patient harm. Supporting patient safety efforts is increasingly important given increasing complexity of care and changing health needs, especially with aging populations. Emerging technologies and capabilities open new possibilities to address longstanding patient safety problems. For example, predictive analytics to support provider decision-making, increased patient interest in engagement in their care, and artificial intelligence provide opportunities to further reduce harm. Many of these examples support a more proactive approach to patient safety by focusing on anticipating, predicting, and preventing patient harm; however, implementation is essential to avoid unintended consequences. Additionally, health care organizations oftentimes cannot accomplish this work on their own and strategic partnerships are crucial for continued improvement. This paper proposes a strategic focus for health care leaders as they build comprehensive plans to prevent harm from adverse events. Drawing on international case examples from the Future of Health Community, it outlines actionable approaches to partnerships that can be adapted and implemented across diverse health care organizations.

  • Open Access

    Transforming the future of health: building learning health systems across the globe

    by Sandra Yankah, Robert Saunders, Mark Tykocinski, Claudia Salzberg, Jonathan Gonzalez-Smith, Rachel Bonesteel, Cameron Joyce, Charles Kahn, Mark McClellan, Eyal Zimlichman

    Health care has faced disruptions over the past 5 years, including a global pandemic, supply chain interruptions, workforce shifts, and the introduction of new artificial intelligence (AI) tools. Health care organizations continue to leverage the learning health system (LHS) concept to adapt to these challenges through iterative feedback loops. The Future of Health (FOH), an international community of over 50 senior health leaders that focuses on shared challenges across international health systems, collaborated with the Duke-Margolis Institute for Health Policy in a consensus-building process with FOH members to identify opportunities for action in an LHS. Key areas for action identified include opportunities to leverage data and AI to support clinical decision-making, steps to create an organizational culture of learning, and strategies to engage patients and caregivers, illustrated through case examples.

  • Open Access

    Traditional Machine Learning, Deep Learning, and BERT (Large Language Model) Approaches for Predicting Hospitalizations From Nurse Triage Notes: Comparative Evaluation of Resource Management

    by Dhavalkumar Patel, Prem Timsina, Larisa Gorenstein, Benjamin S Glicksberg, Ganesh Raut, Satya Narayan Cheetirala, Fabio Santana, Jules Tamegue, Arash Kia, Eyal Zimlichman, et al.

    Background: Predicting hospitalization from nurse triage notes has the potential to augment care. However, there needs to be careful considerations for which models to choose for this goal. Specifically, health systems will have varying degrees of computational infrastructure available and budget constraints. Objective: To this end, we compared the performance of the deep learning, Bidirectional Encoder Representations from Transformers (BERT)–based model, Bio-Clinical-BERT, with a bag-of-words (BOW) logistic regression (LR) model incorporating term frequency–inverse document frequency (TF-IDF). These choices represent different levels of computational requirements. Methods: A retrospective analysis was conducted using data from 1,391,988 patients who visited emergency departments in the Mount Sinai Health System spanning from 2017 to 2022. The models were trained on 4 hospitals’ data and externally validated on a fifth hospital’s data. Results: The Bio-Clinical-BERT model achieved higher areas under the receiver operating characteristic curve (0.82, 0.84, and 0.85) compared to the BOW-LR-TF-IDF model (0.81, 0.83, and 0.84) across training sets of 10,000; 100,000; and ~1,000,000 patients, respectively. Notably, both models proved effective at using triage notes for prediction, despite the modest performance gap. Conclusions: Our findings suggest that simpler machine learning models such as BOW-LR-TF-IDF could serve adequately in resource-limited settings. Given the potential implications for patient care and hospital resource management, further exploration of alternative models and techniques is warranted to enhance predictive performance in this critical domain. International Registered Report Identifier (IRRID): RR2-10.1101/2023.08.07.23293699


  • Open Access

    Advancing the future of equitable access to health care: recommendations from international health care leaders

    by Beth Boyer, Katie Huber, Eyal Zimlichman, Robert Saunders, Mark McClellan, Charles Kahn, Ryan Noach, Claudia Salzberg

    Disparities in access to health care are persistent and contribute to poor health outcomes for many populations around the world. Barriers to access are often similar across countries, despite differences in how health systems are structured. Health care leaders can work to address these barriers through bold, evidence-based actions. The Future of Health (FOH), an international community of senior health leaders, collaborated with the Duke-Margolis Institute for Health Policy to identify priority organizational and policy actions needed to improve equitable access to health care through a consensus-building exercise, a targeted literature review, and an expert discussion group. This paper describes four key action areas for health care leaders that FOH members identified as critical to enabling the future of equitable access to health care: ensuring prioritization of and accountability for equitable access to care; establishing comprehensive, organization-wide strategies to address barriers to access; clearly defining and incentivizing improvement on key measures related to reducing disparities in access; and establishing cross-sector partnerships to improve equitable access.


  • Top Cited Papers

    Large Language Models Are Poor Medical Coders — Benchmarking of Medical Code Querying

    by Ali Soroush, Benjamin S. Glicksberg, Eyal Zimlichman, Yiftach Barash, Robert Freeman, Alexander W. Charney, Girish N Nadkarni, Eyal Klang


  • Open Access

    Unlocking the potential of large language models in healthcare: navigating the opportunities and challenges

    by Idit Tessler, Tzahi Yamin, Hadar Peeri, Eran E Alon, Eyal Zimlichman, Benjamin S Glicksberg, Eyal Klang

    This paper explores the emerging role of large language models (LLMs) in healthcare, offering an analysis of their applications and limitations. Attention mechanisms and transformer architectures enable LLMs to perform tasks like extracting clinical information and assisting in diagnostics. We highlight research that demonstrates early application of LLMs in various domains and along the care pathway. With their promise, LLMs pose ethical and practical challenges, including data bias and the need for human oversight. This review serves as a guide for clinicians and researchers, outlining potential healthcare applications – ranging from document translation to clinical decision support – while cautioning about inherent limitations and ethical considerations. The aim of this work is to encourage the knowledgeable use of LLMs in healthcare and drive further study in this important emerging field.


  • Open Access

    Advancing radiology practice and research: harnessing the potential of large language models amidst imperfections

    by Eyal Klang, Lee Alper, Vera Sorin, Yiftach Barash, Girish N Nadkarni, Eyal Zimlichman

    Large language models (LLMs) are transforming the field of natural language processing (NLP). These models offer opportunities for radiologists to make a meaningful impact in their field. NLP is a part of artificial intelligence (AI) that uses computer algorithms to study and understand text data. Recent advances in NLP include the Attention mechanism and the Transformer architecture. Transformer-based LLMs, such as GPT-4 and Gemini, are trained on massive amounts of data and generate human-like text. They are ideal for analysing large text data in academic research and clinical practice in radiology. Despite their promise, LLMs have limitations, including their dependency on the diversity and quality of their training data and the potential for false outputs. Albeit these limitations, the use of LLMs in radiology holds promise and is gaining momentum. By embracing the potential of LLMs, radiologists can gain valuable insights and improve the efficiency of their work. This can ultimately lead to improved patient care.


  • Open Access

    A Five-Decade Text Mining Analysis of Cochlear Implant Research: Where We Started and Where We Are Heading

    by Idit Tessler, Nir A. Gecel, Benjamin S. Glicksberg, Shaked Shivatzki, Yisgav Shapira, Eyal Zimlichman, Eran E. Alon, Eyal Klang, Amit Wolfovitz

    Background and Objectives: Since its invention in the 1970s, the cochlear implant (CI) has been substantially developed. We aimed to assess the trends in the published literature to characterize CI. Materials and Methods: We queried PubMed for all CI-related entries published during 1970–2022. The following data were extracted: year of publication, publishing journal, title, keywords, and abstract text. Search terms belonged to the patient’s age group, etiology for hearing loss, indications for CI, and surgical methodological advancement. Annual trends of publications were plotted. The slopes of publication trends were calculated by fitting regression lines to the yearly number of publications. Results: Overall, 19,428 CIs articles were identified. Pediatric-related CI was the most dominant sub-population among the age groups, with the highest rate and slope during the years (slope 5.2 ± 0.3, p < 0.001), while elderly-related CIs had significantly fewer publications. Entries concerning hearing preservation showed the sharpest rise among the methods, from no entries in 1980 to 46 entries in 2021 (slope 1.7 ± 0.2, p < 0.001). Entries concerning robotic surgery emerged in 2000, with a sharp increase in recent years (slope 0.5 ± 0.1, p < 0.001). Drug-eluting electrodes and CI under local-anesthesia have been reported only in the past five years, with a gradual rise. Conclusions: Publications regarding CI among pediatrics outnumbered all other indications, supporting the rising, pivotal role of CI in the rehabilitation of children with sensorineural hearing loss. Hearing-preservation publications have recently rapidly risen, identified as the primary trend of the current era, followed by a sharp rise of robotic surgery that is evolving and could define the next revolution.


  • Open Access

    Traditional Machine Learning, Deep Learning, and BERT (Large Language Model) Approaches for Predicting Hospitalizations From Nurse Triage Notes: Comparative Evaluation of Resource Management (Preprint)

    by Dhavalkumar Patel, Prem Timsina, Larisa Gorenstein, Benjamin S Glicksberg, Ganesh Raut, Satya Narayan Cheetirala, Fabio Santana, Jules Tamegue, Arash Kia, Eyal Zimlichman, et al.

    BACKGROUND Predicting hospitalization from nurse triage notes has the potential to augment care. However, there needs to be careful considerations for which models to choose for this goal. Specifically, health systems will have varying degrees of computational infrastructure available and budget constraints. OBJECTIVE To this end, we compared the performance of the deep learning, Bidirectional Encoder Representations from Transformers (BERT)–based model, Bio-Clinical-BERT, with a bag-of-words (BOW) logistic regression (LR) model incorporating term frequency–inverse document frequency (TF-IDF). These choices represent different levels of computational requirements. METHODS A retrospective analysis was conducted using data from 1,391,988 patients who visited emergency departments in the Mount Sinai Health System spanning from 2017 to 2022. The models were trained on 4 hospitals’ data and externally validated on a fifth hospital’s data. RESULTS The Bio-Clinical-BERT model achieved higher areas under the receiver operating characteristic curve (0.82, 0.84, and 0.85) compared to the BOW-LR-TF-IDF model (0.81, 0.83, and 0.84) across training sets of 10,000; 100,000; and ~1,000,000 patients, respectively. Notably, both models proved effective at using triage notes for prediction, despite the modest performance gap. CONCLUSIONS Our findings suggest that simpler machine learning models such as BOW-LR-TF-IDF could serve adequately in resource-limited settings. Given the potential implications for patient care and hospital resource management, further exploration of alternative models and techniques is warranted to enhance predictive performance in this critical domain. INTERNATIONAL REGISTERED REPORT RR2-10.1101/2023.08.07.23293699

  • Open Access

    Revolutionizing patient safety with artificial intelligence: the potential of natural language processing and large language models

    by Eyal Klang, Ezequiel García-Elorrio, Eyal Zimlichman

    Patient safety is a critical aspect of modern health care. Adverse events, half of them preventable, related to unsafe care are among the top ten causes of death and disability worldwide [ 1, 2]. Insecure care results in significant incremental expenses when, e.g. hospital-acquired infections, account for high rates of morbidity and mortality, as well as considerable costs [ 3]. Despite efforts to improve safety in the health-care system, issues still persist, and progress has been unsatisfactory over the last 30 years [ 4].