Related Experiment Videos
OphthoChat: A HIPAA-Compliant, Artificial Intelligence-Driven Natural-Language Chatbot for Ophthalmic Electronic
Karen M Chen1, Kevin W Chen2, Advait Patil3
1Columbia University Irving Medical Center, Department of Ophthalmology, New York, New York.
Ophthalmology Science
|August 14, 2026
Summary
OphthoChat, an AI chatbot, provides fast and accurate querying of ophthalmic electronic medical records (EMRs) for clinicians. This tool enhances clinical research and practice by simplifying data access without coding knowledge.
Area of Science:
- Ophthalmology
- Artificial Intelligence in Healthcare
- Clinical Informatics
Background:
- Electronic Medical Records (EMRs) contain vast amounts of clinical data.
- Accessing specific information within EMRs can be time-consuming and requires technical expertise.
- Natural language processing (NLP) offers a potential solution for intuitive data retrieval.
Purpose of the Study:
- To introduce and evaluate OphthoChat, an AI-powered chatbot for querying ophthalmic EMRs.
- To enable clinicians to use conversational language for EMR data retrieval without coding.
- To ensure the chatbot is Health Insurance Portability and Accountability Act (HIPAA)-compliant.
Main Methods:
- A retrospective validation study was conducted using a clinical dataset.
- Over 50,000 EMR artifacts from 500 patients were processed into a vectorized database.
- OphthoChat, utilizing a retrieval-augmented generation architecture with GPT-4o, answered 1000 natural-language queries of varying complexity, with responses adjudicated by clinicians.
Main Results:
- OphthoChat achieved high performance with 96% overall accuracy, 93% sensitivity, and 97% specificity.
- The median time to answer a query was 35 seconds, an 11-fold improvement over manual review.
- Responses were highly traceable, with 97% of cited lines matching the reference standard, and performance remained robust across all query complexities.
Conclusions:
- OphthoChat facilitates rapid, accurate, and traceable EMR review in ophthalmology via natural language.
- The chatbot lowers the barrier for AI adoption in clinical research and practice by eliminating the need for programming skills.
- OphthoChat offers a scalable solution for accelerating outcomes research, clinical decision-making, and cohort identification by synthesizing complex EMR data.
Related Concept Videos
01:23Ophthalmic Drug Delivery Systems
Ophthalmic drug delivery faces major limitations due to poor absorption across the corneal membrane. This process is primarily driven by diffusion and is influenced by two main factors: the physicochemical properties of the drug and tear drainage. Most ophthalmic drugs, such as pilocarpine, epinephrine, atropine, and local anesthetics, are weak bases. They are typically formulated at an acidic pH to enhance chemical stability. However, this leads to high ionization, reducing their ability to...
01:25Glaucoma: Overview
Glaucoma is an eye condition characterized by increased intraocular pressure that damages the retina and optic nerve, leading to irreversible blindness if left untreated. The human eye has various components, including the cornea, iris, pupil, lens, and optic nerve. Aqueous humor is secreted by the epithelium of the ciliary body in the posterior chamber and flows through the trabecular meshwork and canal of Schlemm, maintaining normal intraocular pressure. The trabecular meshwork and the canal...