From risk classification to clinical action: a prespecified paired pilot benchmark of public large language model interfaces for diabetes-related foot ulcer prevention

Yang Wen, Liyuan Chen, Xin Deng, Jiaping Lan, Xin Huang, Yang Liu, Lin Chen, Lei Li · 2026

Read From risk classification to clinical action: a prespecified paired pilot benchmark of public large language model interfaces for diabetes-related foot ulcer prevention by Yang Wen, Liyuan Chen, Xin Deng, Jiaping Lan, Xin Huang, Yang Liu, Lin Chen, Lei Li (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-13623619.txt.

Description

Yang Wen and co-authors benchmark public chatbot interfaces on diabetes foot care decisions, in a study published in 2026. Language models might help prevent foot ulcers in diabetes, but sorting a patient into the right risk class is only half the job; the follow-up actions matter just as much. The team ran a prespecified, blinded pilot using twenty cleaned, translated cases spread evenly across the four international risk categories.

Five public model interfaces each judged all twenty cases under fixed no-search conditions. Every interface matched the expert consensus risk category on all twenty cases, though the confidence interval shows how little twenty cases can prove. The team also scored referral choices, completeness, stability across repeats, and safety. The setup was deliberately idealized, so real clinic notes may prove harder.

Catalog record

CREATORYang Wen, Liyuan Chen, Xin Deng, Jiaping Lan, Xin Huang, Yang Liu, Lin Chen, Lei Li
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE70 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13623619

Browse the full library · About the Tower of Babel