Readability of Chatbot Responses in Prostate Cancer and Urological Care: Objective Metrics Versus Patient Perceptions
Bibliographic record
Abstract
Large language models (LLMs) are increasingly explored as chatbots for patient education, including applications in urooncology. Since only 12% of adults have proficient health literacy and most patient information materials exceed recommended reading levels, improving readability is crucial. Although LLMs could potentially increase the readability of medical information, evidence is mixed, underscoring the need to assess chatbot outputs in clinical settings. Therefore, this study evaluates the measured and perceived readability of chatbot responses in speech-based interactions with urological patients. Urological patients engaged in unscripted conversations with a GPT-4-based chatbot. Transcripts were analyzed using three readability indices: Flesch-Reading-Ease (FRE), Lesbarkeitsindex (LIX) and Wiener-Sachtextformel (WSF). Perceived readability was assessed using a survey covering technical language, clarity and explainability. Associations between measured and perceived readability were analyzed. Knowledge retention was not assessed in this study. A total of 231 conversations were evaluated. The most frequently addressed topics were prostate cancer (22.5%), robotic-assisted prostatectomy (19.9%) and follow-up (18.6%). Objectively, responses were classified as difficult to read (FRE 43.1 ± 9.1; LIX 52.8 ± 6.2; WSF 11.2 ± 1.6). In contrast, perceived readability was rated highly for technical language, clarity and explainability (83-90%). Correlation analyses revealed no association between objective and perceived readability. Chatbot responses were objectively written at a difficult reading level, exceeding recommendations for optimized health literacy. Nevertheless, most patients perceived the information as clear and understandable. This discrepancy suggests that perceived comprehensibility is influenced by factors beyond measurable linguistic complexity.
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 | 0.011 | 0.075 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".