Research at scale
Multicenter EHR, imaging, and registry data with rigorous phenotyping, outcome definitions, and LLM-supported analytics.
Learn moreWhere vision meets computation.
PershingLab advances eye care through AI, imaging informatics, and data science.
About the lab
The lab for computational ophthalmology
We develop and apply machine learning, computer vision, natural language processing, and large language models (LLMs) to ophthalmic data from the IRIS® Registry and other sources—electronic health records, imaging, and surgical video—to improve diagnosis, prognosis, and patient outcomes.
Our work is centered on the American Academy of Ophthalmology IRIS® Registry and sits at the intersection of ophthalmology, biomedical informatics, and artificial intelligence. We use IRIS Registry data for real-world evidence, outcomes research, and method development, and we collaborate closely with clinicians and national registry initiatives.
EHR + Imaging + NLP + LLM
Structured and free-text clinical data, OCT, visual fields, and LLM-driven analysis.
Why PershingLab
Clinical impact takes more than algorithms
We deliver the data infrastructure, methods, and clinical partnerships needed to bring AI from research to patient care.
Data & tools
Claims and registries, de-identified clinical notes, and IRIS® Registry data for research.
Learn moreClinical collaboration
Close partnership with Byers Eye Institute clinicians and national registries including IRIS®.
Learn moreTraining & dissemination
Fellows, residents, and collaborators trained in ophthalmic informatics and AI methods.
Learn moreResearch
Engineered for vision science & AI
We develop and apply ML, computer vision, NLP, and large language models (LLMs) to ophthalmic data—from EHR and imaging to surgical video—to improve diagnosis, prognosis, and patient outcomes.
Glaucoma progression & surgery
AI models to predict glaucoma progression and surgical outcomes using multicenter EHR and imaging data.
Computer vision for surgery
Deep learning on cataract and other surgical videos for skill assessment and outcome prediction.
NLP & LLMs for clinical text
Natural language processing and large language models on ophthalmic clinical notes for phenotyping, information extraction, and decision support.
Visual prognosis
Predicting visual prognosis for low-vision patients to support rehabilitation and care planning.
Team
People
Suzann Pershing, MD, MS
Principal Investigator
Chief of Ophthalmology at VA Palo Alto; Vice Chair for Education, Stanford Ophthalmology. Ophthalmic informatics, AI, and predictive modeling in eye care.
Md Enamul Haque, PhD
Sr Data Scientist
Sr Data Scientist at Stanford. Data science and analytics for ophthalmic research, clinical outcomes, and predictive modeling in eye care.
Luay Abdeljaber, PhD
Data Scientist
Data Scientist at Stanford. Data science and informatics for vision and eye care; medical AI, NLP, and active learning in ophthalmology.
Postdocs, students, collaborators
Join us — we're always looking for talented researchers.
Publications
Selected publications
Year
Topic
-
2024
Evaluating Visual Acuity in the American Academy of Ophthalmology IRIS® Registry
PubMed -
2024
Using Natural Language Processing to Identify Different Lens Pathology in Electronic Health Records
PubMed -
2023
Cataract Surgery in the Medicare Merit-Based Incentive Payment System: Episode-Based Cost Measure Development and Evaluation
PubMed -
2023
Impact of Type 2 Diabetes Mellitus and Insulin Use on Progression to Glaucoma Surgery in Primary Open Angle Glaucoma
PubMed -
2023
US Population Disparities in Ophthalmic Care: Blindness and Visual Impairment in the IRIS® Registry
PubMed -
2023
Thyroid Eye Disease and its Vision Threatening Manifestations in the Academy IRIS® Registry: 2014–2018
PubMed -
2023
Causes of Childhood Blindness in the United States using the IRIS Registry
PubMed -
2023
Analysis of the Readability and Accountability of Online Patient Education Materials Related to Glaucoma Diagnosis and Treatment
PubMed -
2023
Identifying Strategies to Reduce Low-Value Preoperative Testing for Low-Risk Procedures: a Qualitative Study
PubMed -
2022
The American Academy of Ophthalmology IRIS Registry: Current and Future State of Big Data Analytics
PubMed -
2022
Effectiveness of Microinvasive Glaucoma Surgery in the United States: IRIS Registry Analysis 2013–2019
PubMed -
2022
Outcomes of Over 40,000 Eyes Treated for Diabetic Macula Edema in Routine Clinical Practice: A Systematic Review and Meta-analysis
PubMed -
2022
Adjustable suture technique is associated with fewer strabismus reoperations in the IRIS Registry
PubMed -
2022
Relative Importance of Applicant Characteristics in Ophthalmology Residency Interview Selection: A Survey of Program Directors
PubMed -
2022
Readability and accountability of online patient education materials for common retinal diseases
PubMed -
2022
Predicting Acute Endophthalmitis for Patients with Cataract Surgery Using Hierarchical and Probabilistic Representation of Clinical Codes
-
2021
Implicit Bias and the Association of Redaction of Identifiers With Residency Application Screening Scores
PubMed -
2021
Endophthalmitis rate in immediately sequential vs delayed sequential bilateral cataract surgery within the IRIS Registry
PubMed -
2021
Bidirectional Association between Visual Impairment and Dementia Among US Older Adults Over Time
PubMed -
2021
Variability and Costs of Low-Value Preoperative Testing for Cataract Surgery Within the Veterans Health Administration
PubMed -
2021
Need for Retinal Detachment Reoperation based on Primary Repair Method among Commercially-insured Patients, 2003–2016
PubMed -
2021
Age, Gender, and Laterality of Retinal Vascular Occlusion: A Retrospective Study from the IRIS Registry
PubMed -
2021
The Impact of COVID-19 on Missed Ophthalmology Clinic Visits
PubMed -
2020
Receipt of Eye Care Services among Medicare Beneficiaries with and without Dementia
PubMed -
2020
Comparing cataract surgery complication rates in veterans receiving VA and community care
PubMed -
2020
Big data requirements for artificial intelligence
PubMed -
2020
Intraocular Pressure Changes after Cataract Surgery in Patients with and without Glaucoma: An Informatics-Based Approach
PubMed -
2020
Cataract Surgery Complexity and Surgical Complication Rates among Medicare Beneficiaries with and without Dementia
PubMed
Resources
Data & tools
Clinical data & registries
Structured EHR, ophthalmic imaging (OCT, visual fields), IRIS® Registry data, and de-identified clinical notes for research.
Claims & registries
Analysis of glaucoma risk factors and surgical outcomes using insurance claims and national registries.
Contact
Get in touch
Byers Eye Institute at Stanford
Stanford University School of Medicine
For collaborations, data access, or joining the lab, please reach out via Stanford Medicine channels.
Department of OphthalmologyWork with us
Collaborations, data access, or joining the lab—we’d love to hear from you.