Readability and Linguistic Characteristics of Alzheimer's Disease and Related Dementias Prevention, Symptom, and Treatment Information from Generative Artificial Intelligence Chatbots.

Authors

John Robert Bautista, Olivia Goth, Allison B Anbari, Kimberly R Powell

Published in

Journal of gerontological nursing. Volume 52. Issue 7. Pages 7-11. Epub Jul 01, 2026.

Abstract

To examine the readability and linguistic characteristics of Alzheimer's disease and related dementias (ADRD) prevention, symptom, and treatment information from generative artificial intelligence (GenAI) chatbots.
We analyzed 66 outputs from free-to-use GenAI chatbots. We extracted readability (word count, Fleisch Reading Ease, and Fleisch-Kincaid Grade Level) and linguistic scores (analytical thinking, clout, authenticity, and emotional tone) using Microsoft Word and the Linguistic Inquiry and Word Count software. Data were analyzed using descriptive statistics, t tests, analysis of variance, and multivariate analysis of variance.
ADRD information from GenAI chatbots, especially treatment information, had college-level readability. Linguistic analyses indicate a high analytical thinking score and low scores for clout, authenticity, and emotional tone.
Our sample of ADRD GenAI information exceeded recommended reading levels for patient education materials. Although the outputs exhibited logical thinking, they also included uncertain, inauthentic, and negative tones. ADRD caregivers should be aware of these characteristics when using GenAI chatbots for ADRD information-seeking.

PMID:
42391577
Bibliographic data and abstract were imported from PubMed on 03 Jul 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.