Dr Cyril Zakka completed his medical training at the American University of Beirut Medical Center (AUBMC), where he founded and served as the Director of the Artificial Intelligence in Medicine (AIM) program. Over the past 4 years, he has been working at the intersection of AI, robotics, and medicine to develop algorithms to improve on patient care, both in the clinic and the operating room. Currently, he's a postdoctoral fellow at the Hiesinger Lab in the department of Cardiothoracic Surgery, working on surgical robots and cardiac imaging.
Honors & Awards
Member, Gold Humanism Honor Society (GHHS) (2022-Present)
Bachelor of Science, Boston College (2018)
Doctor of Medicine, American University Of Beirut (2022)
BS, Boston College, Biology (2018)
MD, American University of Beirut Medical Center, Medicine (2022)
William Hiesinger, Postdoctoral Faculty Sponsor
Jad Farid Assaf, Shady Awwad, Cyril Zakka. "United States Patent 63/395,935 AUTOMATED DETECTION OF KERATOREFRACTIVE SURGERIES ON ANTERIOR SEGMENT OPTICAL COHERENCE TOMOGRAPHY (AS-OCT) SCANS AND METHODS OF USE", American University of Beirut, Aug 8, 2022
Technology and Education
Current Research and Scholarly Interests
Cyril Zakka's research is primarily focused on building unsupervised deep learning representation learners for use in a variety of medical tasks, such as medical imaging (e.g. cardiac MRIs and echocardiograms), and autonomous robotic surgical systems. He is particularly interested in developing algorithms that augment operating physicians' capabilities in order to improve on patient outcomes post-operatively.
Deep Learning-Based Estimation of Implantable Collamer Lens Vault Using Optical Coherence Tomography.
American journal of ophthalmology
2023; 253: 29-36
PURPOSE: To develop and validate a deep learning neural network for automated measurement of implantable collamer lens (ICL) vault using anterior segment optical coherence tomography (AS-OCT).DESIGN: Cross-sectional retrospective study.METHODS: A total of 2647 AS-OCT scans were used from 139 eyes of 82 subjects who underwent ICL surgery in 3 different centers. Using transfer learning, a deep learning network was trained and validated for estimating the ICL vault on OCT. A trained operator separately reviewed all OCT scans and measured the central vault using a built-in caliper tool. The model was then separately tested on 191 scans. A Bland-Altman plot was constructed and the mean absolute percentage error (MAPE), mean absolute error (MAE), root mean squared error (RMSE), Pearson correlation coefficient (r), and determination coefficient (R2) were calculated to evaluate the strength and validity of the model.RESULTS: On the test set, the model achieved a MAPE of 3.42%, an MAE of 15.82 m, a RMSE of 18.85 m, a Pearson correlation coefficient r of +0.98 (P < .00001), and a coefficient of determination R2 of +0.96. There was no significant difference between the vaults of the test set labeled by the technician vs those estimated by the model: 478 ± 95 m vs 475 ± 97 m, respectively, P=.064).CONCLUSIONS: Using transfer learning, our deep learning neural network was able to accurately compute the ICL vault from AS-OCT scans, overcoming the limitations of an imbalanced data set and limited training data. Such an algorithm can assist the postoperative assessment in ICL surgery.
View details for DOI 10.1016/j.ajo.2023.04.008
View details for PubMedID 37142173
Almanac: Retrieval-Augmented Language Models for Clinical Medicine.
Large-language models have recently demonstrated impressive zero-shot capabilities in a variety of natural language tasks such as summarization, dialogue generation, and question-answering. Despite many promising applications in clinical medicine, adoption of these models in real-world settings has been largely limited by their tendency to generate incorrect and sometimes even toxic statements. In this study, we develop Almanac, a large language model framework augmented with retrieval capabilities for medical guideline and treatment recommendations. Performance on a novel dataset of clinical scenarios (n= 130) evaluated by a panel of 5 board-certified and resident physicians demonstrates significant increases in factuality (mean of 18% at p-value < 0.05) across all specialties, with improvements in completeness and safety. Our results demonstrate the potential for large language models to be effective tools in the clinical decision-making process, while also emphasizing the importance of careful testing and deployment to mitigate their shortcomings.
View details for DOI 10.21203/rs.3.rs-2883198/v1
View details for PubMedID 37205549
View details for PubMedCentralID PMC10187428