Can ChatGPT provide high-quality patient information on male lower urinary tract symptoms suggestive of benign prostate enlargement?
Bibliographic record
Abstract
BACKGROUND: ChatGPT has recently emerged as a novel resource for patients' disease-specific inquiries. There is, however, limited evidence assessing the quality of the information. We evaluated the accuracy and quality of the ChatGPT's responses on male lower urinary tract symptoms (LUTS) suggestive of benign prostate enlargement (BPE) when compared to two reference resources. METHODS: Using patient information websites from the European Association of Urology and the American Urological Association as reference material, we formulated 88 BPE-centric questions for ChatGPT 4.0+. Independently and in duplicate, we compared the ChatGPT's responses and the reference material, calculating accuracy through F1 score, precision, and recall metrics. We used a 5-point Likert scale for quality rating. We evaluated examiner agreement using the interclass correlation coefficient and assessed the difference in the quality scores with the Wilcoxon signed-rank test. RESULTS: ChatGPT addressed all (88/88) LUTS/BPE-related questions. For the 88 questions, the recorded F1 score was 0.79 (range: 0-1), precision 0.66 (range: 0-1), recall 0.97 (range: 0-1), and the quality score had a median of 4 (range = 1-5). Examiners had a good level of agreement (ICC = 0.86). We found no statistically significant difference between the scores given by the examiners and the overall quality of the responses (p = 0.72). DISCUSSION: ChatGPT demostrated a potential utility in educating patients about BPE/LUTS, its prognosis, and treatment that helps in the decision-making process. One must exercise prudence when recommending this as the sole information outlet. Additional studies are needed to completely understand the full extent of AI's efficacy in delivering patient education in urology.
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 | 0.016 | 0.122 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| 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) | 0.006 | 0.002 |
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".