Applications of natural language processing in ophthalmology: present and future

Area of Science:

• Ophthalmology
• Artificial Intelligence
• Natural Language Processing

Background:

• Technological advancements, including novel ophthalmic imaging and electronic health records (EHRs), have generated vast amounts of data in ophthalmology.
• Current artificial intelligence (AI) applications in ophthalmology primarily utilize image-based deep learning, leaving significant unstructured EHR text data underutilized.
• Natural Language Processing (NLP) offers a powerful AI approach to process and analyze human language within these text data.

Purpose of the Study:

• To introduce ophthalmologists to Natural Language Processing (NLP).
• To review current applications of NLP in ophthalmology.
• To explore potential future applications of NLP in the field.

Main Methods:

• A literature review was conducted using PubMed and Google Scholar.
• Searches focused on articles related to NLP and ophthalmology.
• Ancestor search was employed to expand the reference list.

Main Results:

• A total of 19 published studies on NLP in ophthalmology were identified.
• The majority of studies (16) focused on extracting specific text, such as visual acuity, from free-text notes for quantitative analysis.
• Other identified applications included domain embedding, predictive modeling, and topic modeling.

Conclusions:

• NLP presents a significant opportunity to leverage underutilized free-text data in EHRs for ophthalmology.
• Future applications may include enhanced data retrieval, note cleaning, automated question-answering, and translation of clinical notes.
• NLP can drive innovation in healthcare delivery and the treatment of ophthalmic conditions as medicine becomes more data-driven.