Table 1.
Readability comparison between various information sources using Flesch-Kincaid readability score
| Questions Posed | Flesch-Kincaid Score (p value) |
|---|---|
| General information about prostate cancer | |
| ChatGPT | 43.0 ± 2.9 |
| ChatGPT (Year 8) | 57.7 ± 2.9 |
| Cancer Council Australia | 51.8 (p = 0.09, p = 0.11) |
| UpToDate (Basics) | 65.4 (p <0.05, p = 0.18) |
| Mayo Clinic | 53.5 (p <0.05, p = 0.14) |
| General information about prostate cancer screening | |
| ChatGPT | 34.9 ± 2.8 |
| ChatGPT (Year 8) | 45.5 ± 10.9 |
| UpToDate (Basics) | 71.6 (p <0.05, p = 0.06) |
| UptoDate (Beyond Basics) | 45.5 (p = 0.14, p = 1) |
| Low risk prostate cancer treatment | |
| ChatGPT | 18.6 ± 1.8 |
| ChatGPT (Year 8) | 36.7 ± 2.2 |
| UpToDate (Basics) | 52.3 (p <0.05, p <0.05) |
| Advanced prostate cancer treatment | |
| ChatGPT | 28.4 ± 3.3 |
| ChatGPT (Year 8) | 46.6 ± 1.1 |
| UpToDate (Beyond Basics) | 42.2 (p = 0.05, p = 0.06) |
| General information about renal cell cancer | |
| ChatGPT | 26.8 ± 4.0 |
| ChatGPT (Year 8) | 55.1 ± 1.5 |
| Cancer Council Australia | 48.2 (p <0.05, p <0.05) |
| UptoDate (Basics) | 68.5 (p <0.05, p <0.05) |
| UpToDate (Beyond Basics) | 43.8 (p <0.05, p <0.05) |
| Mayo Clinic | 57.2 (p <0.05, p = 0.15) |
| General information about bladder cancer | |
| ChatGPT | 36.2 ± 2.9 |
| ChatGPT (Year 8) | 51.6 ± 2.6 |
| Cancer Council Australia | 42.4 (p = 0.17, p = 0.07) |
| UpToDate (Basics) | 66.8 (p <0.05, p <0.05) |
| Mayo Clinic | 50.3 (p <0.05, p = 0.33) |
| Bladder cancer diagnosis and staging | |
| ChatGPT | 35.6 ± 0.7 |
| ChatGPT (Year 8) | 49.6 ± 1.6 |
| UpToDate (Beyond Basics) | 42.6 (p <0.05, p <0.05) |
| Non-muscle invasive bladder cancer treatment | |
| ChatGPT | 25.9 ± 1.1 |
| ChatGPT (Year 8) | 36.6 ± 1.3 |
| UpToDate (Beyond Basics) | 37.8 (p <0.05, p = 0.06) |
| Muscle invasive bladder cancer treatment | |
| ChatGPT | 31.2 ± 3.6 |
| ChatGPT (Year 8) | 61.1 ± 2.5 |
| UpToDate (Beyond Basics) | 35.8 (p = 0.17, p <0.05) |