Artificial intelligence–powered chatbots for oral anticancer drug patient information: an assessment of quality
Sophie M. Sametinger, Renke Maas, Hagen F. Nicolaus, Wahram Andrikyan · 2026
Read Artificial intelligence–powered chatbots for oral anticancer drug patient information: an assessment of quality by Sophie M. Sametinger, Renke Maas, Hagen F. Nicolaus, Wahram Andrikyan (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/PMC13593639.txt.
Description
Sophie M. Sametinger led a study grading how well two AI chatbots answer patient questions about oral anticancer drugs, the cancer pills people take at home. In June 2024 the team put four typical patient questions about twenty such drugs to Microsoft's Copilot and Google's Gemini, three times each, and scored the replies against standard written patient information.
Accuracy was high for both systems, with median scores at the top of the scale. Completeness lagged, with Copilot covering a median of about three fifths of the relevant points and Gemini about three quarters. Readability was the weakest point, since both chatbots wrote at a level many patients would find hard going. The authors conclude that the tools are factually sound but not yet a full answer to patients' information needs.
Catalog record
| CREATOR | Sophie M. Sametinger, Renke Maas, Hagen F. Nicolaus, Wahram Andrikyan |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36745 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |