Read more

May 08, 2023
1 min read
Save

Natural language processing may improve patient care in ophthalmology

You've successfully added to your alerts. You will receive an email when new content is published.

Click Here to Manage Email Alerts

We were unable to process your request. Please try again later. If you continue to have this issue please contact customerservice@slackinc.com.

Key takeaways:

  • Natural language processing is trained on large text data.
  • NLP can be used to build models to summarize text, take notes and communicate with patients.

SAN DIEGO — Natural language processing could help streamline documentation and improve patient care, according to a presentation at DOS Digital Day at the American Society of Cataract and Refractive Surgery meeting.

Natural language processing (NLP) is a subfield of AI that helps computers understand, interpret and generate human language, Gurpal Virdi, MD, MA, said. These models have made advances in recent years using neural network architecture.

Practice management eye diagram
Natural language processing could help streamline documentation and improve patient care, according to a presentation at DOS Digital Day at the American Society of Cataract and Refractive Surgery meeting.
Image: Adobe Stock

“These transformers can be pretrained on large text data and fine-tuned for specific NLP tasks,” Virdi said.

Gurpal Virdi, MD, MA
Gurpal Virdi

NLP has several abilities that could be relevant to ophthalmology, Virdi said, including classifying named entities in given text to find people, medications and surgical procedures, providing text summaries of longer documents, and using chatbots to provide patients with information or assistance.

Programs built on NLP models can also be trained to pull meaningful information from unstructured data, such as clinical notes, to identify key terms, Virdi said. Such an ability could be useful in training health care-specific models for workflow automation for tasks including prior authorizations.

AI models could also be used in ophthalmology to summarize notes and act as digital scribes, Virdi said. Digitizing these processes could prevent errors, reduce physician burnout and improve patient satisfaction.

Implementing NLP models in the future is going to be a large task, particularly for ophthalmology, Virdi said.

“The current open-source large language models are cost prohibitive, and they’re not HIPAA compliant,” he said. “Coupled with our vast amount of EHR data, large language models that are specific to ophthalmology could help to improve patient care and enhance future research.”