Abstract
ChatGPT is reported to be an acceptable tool to answer a majority of frequently asked patient questions. ChatGPT also converses in other languages including Urdu, which offers immense potential for the education of Pakistani patients. Therefore, this study evaluated ChatGPT’s Urdu answers to the ten most frequently asked questions on Total Hip Arthroplasty, which were then rated by an expert. Out of 10 answers in English, 9 (90%) were satisfactory requiring minimal clarification and 1 (10%) was satisfactory requiring moderate clarification. In both Roman and Nastaliq script Urdu, 1 (10%) answer was satisfactory requiring moderate clarification, while 9 (90%) were unsatisfactory requiring substantial clarification. In conclusion, as opposed to ChatGPT English responses, Urdu responses were much less rigorous, generic, and lacked scientific rigor. We have a long way to go before Pakistani patients with limited English language skills could benefit from AI chatbots like ChatGPT.
| Original language | English (US) |
|---|---|
| Pages (from-to) | S161-S164 |
| Journal | Journal of the Pakistan Medical Association |
| Volume | 74 |
| Issue number | 4 |
| DOIs | |
| Publication status | Published - Apr 2024 |
Keywords
- Arthroplasty
- Artificial Intelligence
- ChatGPT
- Hip
- Language Barrier
- Patient knowledge
- Replacement
Fingerprint
Dive into the research topics of 'Language-adaptive artificial intelligence: assessing CHATGPT'S answer to frequently asked questions on total hip arthroplasty questions'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver