Safety, accuracy, empathy, information quality, and readability of publicly accessible LLM-based chatbots for traumatic brain injury and concussion questions: a cross-sectional comparative study

Xin Zuo, Huan Zuo, Min Zhang, Weihong Zheng · 2026

Read Safety, accuracy, empathy, information quality, and readability of publicly accessible LLM-based chatbots for traumatic brain injury and concussion questions: a cross-sectional comparative study by Xin Zuo, Huan Zuo, Min Zhang, Weihong Zheng (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13574619.txt.

Description

Xin Zuo and co-authors grade five public AI chatbots on brain injury questions in this 2026 study. People increasingly ask chatbots about concussion and traumatic brain injury, but the quality of the answers was unmeasured. The team sent sixty-five plain-language questions to five well-known chatbots and had five blinded experts score the replies.

Most replies rated safe, and every model earned the same middle accuracy score. Yet twenty-seven replies were judged potentially harmful, mostly for playing down urgency, over-reassuring readers about scan findings, or clearing people to drive or play too soon. Warmth, information quality, and plain readability varied more clearly between models. The authors say chatbots may supplement, but never replace, a clinician's judgment.

Catalog record

CREATORXin Zuo, Huan Zuo, Min Zhang, Weihong Zheng
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE38 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13574619

Browse the full library · About the Tower of Babel