Quality, Transparency, and Readability of Artificial Intelligence Chatbots as Sources of Plagiocephaly Information: A...

Parents increasingly use artificial intelligence chatbots for information about plagiocephaly, but the quality and readability of their responses remain uncertain. This cross-sectional study compared 4 mainstream artificial intelligence chatbots using 37 high-frequency English queries identified through Google Trends for "plagiocephaly" worldwide over the previous 5 years. On August 18, 2026, the queries were submitted to ChatGPT 5.5, Gemini 3.5 Flash, Perplexity, and Copilot, generating 148 responses. Information quality was assessed using DISCERN, Ensuring Quality Information for Patients, the JAMA Benchmark Criteria, and the Global Quality Scale; readability was assessed with 6 established indices. Between-model differences were tested using the Friedman test, with Kendall W effect sizes and Holm-adjusted paired Wilcoxon signed-rank tests. Quality scores differed significantly among models. Perplexity had the highest median DISCERN score [50.00 (47.00, 53.00)] and Gemini the lowest [38.00 (35.00, 40.00)]. Copilot had the highest median Ensuring Quality Information for Patients score [85.00 (75.00, 90.00)] and Gemini the lowest [60.00 (55.00, 60.00)]. Median JAMA scores were 1.00 for ChatGPT, Perplexity, and Copilot and 0.00 for Gemini; the median Global Quality Scale score was 4.00 for all models. None met recommended readability thresholds: Flesch-Kincaid Grade Level ranged from 11.66 to 13.14, Simple Measure of Gobbledygook from 12.77 to 15.10, and Flesch Reading Ease from 34.60 to 45.71. Artificial intelligence chatbots provided coherent, relatively complete plagiocephaly information, but quality varied, source transparency was limited, and readability was poor. Their responses should supplement professional assessment, with patient-facing content requiring professional review, source traceability, and lower reading levels.