May 18, 2022

The National Library of Medicine Explores Artificial Intelligence Using Two-Hundred Thousand Real Patient Questions from

From the News Release:

Researchers at The National Library of Medicine have teamed up with in a significant step towards developing intelligent computerized medical assistants for doctors. They are using thousands of real-language, unedited medical questions at the National Institutes of Health (NIH) in Bethesda, Maryland to see if computers can interpret the tone and meaning of questions phrased by online patients. The NIH has also been in contact with IBM, discussing the possibility of working with IBM’s Super Computer ‘Watson’ (of Jeopardy fame) to test these questions from

Over the past few years, has built a database of close to 200,000 unanswered medical questions. These questions have been supplied directly from users, and are consequently phrased in conversational language and not pre-scripted. It’s an ideal test for the ability of computers to communicate in the real world.

“We are using artificial intelligence techniques to explore the potential of computers to understand and respond to questions asked by consumers about their health,” said Dr. Milton Corn, National Institute of Health Deputy Director. “The material provided by is particularly valuable to us in our computational research because the patient questions are stated in the exact language as typed by users.”

Dr. Corn led NIH’s first foray into the World Wide Web through the launch of Medline and the popular abstract database PubMed, used today by physicians worldwide. He approached because the healthcare questions are from real users and the answers are from physicians.

Read the Complete Announcement

About Gary Price

Gary Price ( is a librarian, writer, consultant, and frequent conference speaker based in the Washington D.C. metro area. Before launching INFOdocket, Price and Shirl Kennedy were the founders and senior editors at ResourceShelf and DocuTicker for 10 years. From 2006-2009 he was Director of Online Information Services at, and is currently a contributing editor at Search Engine Land.