ArticlePatient preference and adherence2025
The Impact of Google Search versus ChatGPT on Patient Understanding and Potential Adherence in PICC Line Care: A Comparative Analysis.
Article in Patient preference and adherence, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 2 papers.
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
2 citing papers in PubMed.
- Review
- Generative AI vs web search for patient education: a comparative evaluation of OSA information quality.Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine · 2026Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
4 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Objective: To compare the quality and comprehensiveness of information on peripherally inserted central catheters (PICCs) provided by Google and the artificial intelligence (AI) tool ChatGPT, and to identify the implications for patient understanding, informed decision-making, and potential adherence in oncology care. Methods: In a simulated study, the top 20 PICC-related frequently asked questions (FAQs) were identified via a standardized Google search. These questions were posed to both platforms, and the responses were systematically analyzed and compared for source, type, and content. Results: Google's answers were fragmented and sourced mainly from government websites (45%). In contrast, ChatGPT provided comprehensive, synthesized responses, primarily from academic sources (70%), as inferred from the content, given its lack of explicit source attribution. Critically, significant discrepancies in key clinical information were found. For instance, Google's top answer for PICC longevity was "two to six weeks", while ChatGPT suggested "up to six months or more", creating a high potential for patient confusion and undermining trust in prescribed care plans. Conclusion: ChatGPT has the potential to offer more integrated health information than traditional search engines, thereby influencing how patients access knowledge. However, the presence of conflicting and decontextualized information introduces significant risks, such as patient confusion and anxiety, which can negatively impact trust, shared decision-making, and adherence to medical advice.
Indexed as
Identifiers
What 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.