ArticleCardiology and therapy2026
A Comparative Evaluation of ChatGPT and Google Search Output for Caregiver Education in Tetralogy of Fallot.
Article in Cardiology and therapy, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
3 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
introductionCaregivers of children with tetralogy of Fallot (TOF) frequently seek medical information online to better understand their child's diagnosis, treatment, and long-term care. Recently, generative artificial intelligence (AI) tools, including Google AI Overview and ChatGPT, have emerged as widely accessible sources of health information. However, the quality, readability, and accuracy of these platforms for caregiver education in congenital heart disease remain poorly characterized.
methodsForty frequently asked caregiver questions regarding TOF were identified using Google's "People Also Ask" feature. Each question was submitted to ChatGPT-5.5 and entered as a Google search query, generating 80 total responses. Google search output comprised 37 AI Overviews and three organic search excerpts. Responses were evaluated for word count, Flesch Reading Ease (FRE), and Flesch-Kincaid grade level (FKGL). Two independent reviewers assessed response accuracy using a 5-point Likert scale, while one reviewer evaluated educational quality using a modified Ensuring Quality Information for Patients (EQIP) instrument.
resultsCompared with Google search output (37 AI Overviews and three organic search excerpts), ChatGPT-5.5 generated significantly longer responses (327.9 ± 117.0 vs. 192.5 ± 85.9 words, p < 0.001), with a higher reading level (FKGL: 23.7 ± 8.5 vs. 15.4 ± 3.6, p < 0.001) and lower readability (FRE: 17.3 ± 14.9 vs. 27.4 ± 11.7, p < 0.001). ChatGPT-5.5 demonstrated higher reviewer-rated accuracy (4.95 ± 0.19 vs. 4.40 ± 0.44, p < 0.001) and higher modified EQIP scores (86.44% ± 7.01% vs. 59.62% ± 13.99%, p < 0.001).
conclusionsUnder the study's prompting conditions, ChatGPT-5.5 responses received higher reviewer-rated accuracy and modified EQIP scores than Google search output but were longer and had higher calculated reading-grade levels. These findings do not establish improved caregiver comprehension, which was not directly assessed.
Indexed as
Identifiers
42844537What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.