Readability, Reliability, and Quality Analysis of Internet-Based Patient Education Materials and Large Language Models on Meniere’s Disease
Bibliographic record
Abstract
ImportanceOnline patient education materials (PEMs) and large language model (LLM) outputs can provide critical health information for patients, yet their readability, quality, and reliability remain unclear for Meniere's disease.ObjectiveTo assess the readability, quality, and reliability of online PEMs and LLM-generated outputs on Meniere's disease.DesignCross-sectional study.SettingPEMs were identified from the first 40 Google Search results based on inclusion criteria. LLM outputs were extracted from unique interactions with ChatGPT and Google Gemini.ParticipantsThirty-one PEMs met inclusion criteria. LLM outputs were obtained from 3 unique interactions each with ChatGPT and Google Gemini.InterventionReadability was assessed using 5 validated formulas [Flesch Reading Ease (FRE), Flesch Kincaid Grade Level (FKGL), Gunning-Fog Index, Coleman-Liau Index, and Simple Measure of Gobbledygook Index]. Quality and reliability were assessed by 2 independent raters using the DISCERN tool.Main Outcome MeasuresReadability was assessed for adherence to the American Medical Association's (AMA) sixth-grade reading level guideline. Source reliability, as well as the completeness, accuracy, and clarity of treatment-related information, was evaluated using the DISCERN tool.ResultsThe most common PEM source type was academic institutions (32.2%), while the majority of PEMs (61.3%) originated from the United States. The mean FRE score for PEMs corresponded to a 10th- to 12th-grade reading level, whereas ChatGPT and Google Gemini outputs were classified at post-graduate and college reading levels, respectively. Only 16.1% of PEMs met the AMA's sixth-grade readability recommendation using the FKGL readability index, and no LLM outputs achieved this standard. Overall DISCERN scores categorized PEMs and ChatGPT outputs as "poor quality," while Google Gemini outputs were rated "fair quality." No significant differences were found in readability or DISCERN scores across PEM source types. Additionally, no significant correlation was identified between PEM readability, quality, and reliability scores.ConclusionsOnline PEMs and LLM-generated outputs on Meniere's disease do not meet AMA readability standards and are generally of poor quality and reliability.RelevanceFuture PEMs should prioritize improved readability while maintaining high-quality, reliable information to better support patient decision-making for patients with Meniere's disease.
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 | 0.030 | 0.103 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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".