Utility of ChatGPT and Large Language Models in Enhancing Patient Understanding of Urological Conditions
Bibliographic record
Abstract
Objectives: Large language models such as ChatGPT have been used to generate text in a conversational manner, and may be of use in providing patient information in a urological setting. This study evaluated the accuracy, presence of omissions, and preferability of traditional patient information to the large language models ChatGPT and Bing Chat. Methods: Eight common questions regarding urolithiasis and prostate cancer were selected from traditional patient information and posed to ChatGPT and Bing Chat. Responses from all sources were then evaluated by seven urologists in a blinded fashion for accuracy, omissions, and preferability. Results: We found that 96.43% of ratings of traditional patient information sources were rated accurate, compared to 94.6% for ChatGPT and Bing Chat; 7.1% of ratings of traditional patient information were rated as containing harmful omissions, compared to 10.71% for ChatGPT and 21.4% for Bing Chat; and 55.4% of rater first preferences were given to ChatGPT, compared to 35.7% for traditional patient information and 8.9% for Bing Chat. Conclusions: ChatGPT provided responses of a similar accuracy and preferability to traditional sources, highlighting its potential as a supplementary tool for urological patient information. However, concerns remain regarding omissions and complexity in model-generated responses.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.012 | 0.082 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".