ArticleOphthalmology science2026
OphthoChat: A HIPAA-Compliant, Artificial Intelligence-Driven Natural-Language Chatbot for Ophthalmic Electronic Medical Record Querying and Analysis.
Article in Ophthalmology science, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
6 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Purpose: To introduce and evaluate OphthoChat, a Health Insurance Portability and Accountability Act-compliant, artificial intelligence (AI)‑powered natural language chatbot designed to enable clinicians to query ophthalmic electronic medical records (EMRs) using conversational language, without requiring coding experience. Design: Retrospective validation study using a clinical data set and clinician-authored queries. Participants: The study included 500 adult patients seen at Columbia University Irving Medical Center between 2020 and 2025: 250 patients who received intravitreal injections for wet age-related macular degeneration and 250 patients who underwent cataract surgery. Methods: We processed >50 000 EMR artifacts, including progress notes, operative reports, imaging summaries, and optical character recognition‑converted scanned documents, into a vectorized database. OphthoChat used a retrieval-augmented generation architecture powered by GPT-4o to answer 1000 natural-language queries stratified by complexity (simple, intermediate, advanced). Each response was evaluated against a reference standard determined by dual clinician adjudication. Main Outcome Measures: Primary metrics included response accuracy, sensitivity, specificity, and time-to-answer per query. Supporting chart citations were also assessed for traceability and rank. Results: OphthoChat achieved an overall accuracy of 96%, with a sensitivity of 93% and a specificity of 97%. Median time to answer a query was 35 seconds, an 11-fold speed improvement over manual chart review (6.6 minutes). Among correct responses, 97% of cited lines matched the reference standard, with a mean reciprocal rank of 0.92. Performance remained strong across all difficulty levels, including 91% accuracy on advanced narrative inference tasks. The system demonstrated robustness in processing complex chart histories while offering full traceability. Conclusions: OphthoChat enables fast, accurate, and traceable chart review in ophthalmology through natural-language dialogue. By eliminating the need for technical setup or programming knowledge, it significantly lowers the barrier to AI adoption in clinical research and practice. OphthoChat's ability to synthesize complex EMR data across structured and unstructured formats offers a scalable solution for accelerating outcomes research, clinical decision-making, and cohort identification. Further development will focus on EMR integration and subspecialty expansion. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.