Search for: All records

Caring for a child with cancer involves navigating through complex medical information, often delivered through lengthy handbooks and consultations with healthcare providers. Overnight, parents are expected to become an expert on a domain which they knew noth- ing about. Conversational UIs, powered by Large Language Models (LLMs) and validated information sources, could play a key role in supporting caregivers. In this paper, we investigate the usability, acceptance, and perceived utility of an LLM-based conversational AI tool for pediatric cancer caregiving, grounded in the Children’s Oncology Group Family Handbook–the leading resource in pe- diatric oncology care. We employed a mixed-methods approach, interviewing and surveying 12 caregivers as they engaged with a functional prototype. We offer insights into caregiver’s needs and expectations from AI-driven tools, and design guidelines for devel- oping safer, more personalized, and supportive AI interventions for pediatric cancer care. 

When a child is hospitalized with a serious illness such as cancer, parents and other close family often take on new roles as caregivers. Previous qualitative studies indicate that caregiving coordination work changes systematically across illness and treatment phases, but less is known about individuals’ technology preferences and how technology needs might change over time. In this study, we employed Q-methodology, a sorting technique for quantitatively analyzing subjective opinion. We interviewed 20 caregivers of children with cancer, who sorted 25 statements about potential design solutions. We describe four distinct caregiving coordination technology archetypes at diagnosis, and show how caregivers’ preferences change over time, eventually converging on one set of priorities during extended hospitalization.