Quality and Readability of ChatGPT Performance on Parkinson's Disease
Gabriele Riccio, Rosa Coppola, Maria Rosaria Chiariello, Augusta Giglio, Anna De Rosa · 2026
Read Quality and Readability of ChatGPT Performance on Parkinson's Disease by Gabriele Riccio, Rosa Coppola, Maria Rosaria Chiariello, Augusta Giglio, Anna De Rosa (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-13338990.txt.
Description
Gabriele Riccio and colleagues tested ChatGPT-4o in 2026 on Parkinson disease quizzes and patient questions. The chatbot is increasingly used for medical learning and health advice, yet its reliability, quality, usefulness, and readability need checking against expert judgment. Twenty two professional quizzes went to both the chatbot and two neurologists, while answers to 20 patient questions were scored by three neurologists.
Agreement between neurologists and the chatbot was only fair. Readability scores and quality ratings reveal where chatbot answers help and where they mislead. The study gives patients, students, and clinicians a measured view of when to trust chatbot answers on Parkinson disease and when to seek expert care.
Catalog record
| CREATOR | Gabriele Riccio, Rosa Coppola, Maria Rosaria Chiariello, Augusta Giglio, Anna De Rosa |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 18 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |