Parenting Journal · Volume 2 · Issue 5 · Licensed source edition
Can Large Language Models Aid Caregivers of Pediatric Cancer Patients in Information Seeking? A Cross‐Sectional Investigation
Originally published 2025-01-07 · Cancer Medicine
Wiley · DOI 10.1002/cam4.70554 ↗
AI / system type
Generative AI/LLM information and search tools
Family implicationsDesign, ethics, stakeholder or technical evidence with child/family implications; household benefits are not assumed.
The AI connection
ChatGPT, Bard/Gemini, Bing Chat, and Google SGE generated pediatric cancer caregiver answers.
Why this reading matters
Shows why expert-rated factual quality and family usability must be examined separately in high-stakes information seeking.
Editorial reading guide · Trust
How can I judge an AI explanation of my child’s cancer beyond whether it sounds reassuring?
Tools differed in completeness, readability, and disclosure, with ChatGPT receiving strong ratings but producing more complex text. Inclusivity did not significantly differ, and empathy attracted mixed expert judgments.
Study context
Five pediatric oncology experts rated 104 answers from four public LLM-supported tools to 26 caregiver-oriented questions derived from a family handbook and expert input.
Age / stage: Pediatric cancer; no children or caregivers enrolled as users
Read with three questions
- Which tool strengths came with accessibility or disclosure trade-offs?
- What did the nonsignificant inclusivity result actually show?
- What remains unknown until caregivers use the answers in real conversations?
Keep the limits in view
The static expert benchmark used a study-adapted, unvalidated rubric and moderate inter-rater agreement. It did not test caregiver comprehension, follow-up dialogue, decisions, distress, or treatment outcomes.
The text below is the original article’s licensed repository edition. Its wording is not rewritten. Use the Paper Agent beside the text to locate evidence; open the source for figures, tables and complete context.
Opening the verified paper and agent…
Checking the article identity, license record, and saved source text.
Open the repository recordAttribution & reuse
Follow the original.
Original authorship, publication date, journal and DOI are preserved. This issue’s TRICK placement and reading questions are editorial additions, not claims made by the original authors.
Emre Sezgin; Daniel I. Jackson; A. Baki Kocaballi; Mindy Bibart; Sue Zupanec; Wendy Landier; Anthony Audino; Mark Ranalli; Micah Skeens (2025). Can Large Language Models Aid Caregivers of Pediatric Cancer Patients in Information Seeking? A Cross‐Sectional Investigation Cancer Medicine. https://doi.org/10.1002/cam4.70554
Permissions checked against the saved article notice; repository publication notices screened 2026-11-04. This is not a new peer-review decision. The source authors and publishers are not represented as endorsing this issue.