AI Chatbots May Be Able To Make Pathology Reports Easier For Patients To Read, Study Finds

MedPage Today (5/22, Fiore) reports, “Artificial intelligence (AI) chatbots may be able to help interpret pathology reports for patients, but at this point they need clinician review before being delivered, researchers said.” In the study, “Google’s Bard and OpenAI’s GPT-4 respectively interpreted 87.57% and 97.44% of reports correctly, according to” researchers. Additionally, the chatbots were “able to bring the reports down in Flesch-Kincaid reading level, from an overall mean of 13.19 to 8.17 for Bard and 7.45 for GPT-4 (P<0.001 for both), they reported in JAMA Network Open.”