Readability, Reliability, and Quality Analysis of Internet-Based Patient Education Materials and Large Language Models on Meniere’s Disease
Salahaldin Alamleh, Dorsa Mavedatnia, Gizelle Francis, Trung Ngoc Le, Joel C. Davies, Vincent Lin, Jong Wook Lee · Journal of Otolaryngology - Head and Neck Surgery · 2025
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.