LLM-Based Conversational Agents for Patients with Cancer and Caregivers: A Scoping Review
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
This project aims to conduct a scoping review of large language model (LLM)–based conversational agents developed for patients with cancer and their caregivers. With the emergence of generative AI models such as ChatGPT, Gemini, and Claude, patient-facing conversational systems in oncology have undergone substantial changes in design, interaction patterns, and potential safety risks compared to earlier rule-based or traditional NLP-based chatbots. Despite these differences, existing literature often addresses LLM-based systems and earlier chatbot technologies together, limiting a clear understanding of LLM-specific characteristics. This scoping review will systematically map the types, purposes, evaluation methods, reported safety risks, and transparency of LLM-related development practices in oncology-focused conversational agents. The findings will provide an overview of current research trends and identify gaps to inform future development and evaluation of LLM-based systems for cancer care and caregiving contexts.
Fields of Study & Subjects
Artificial Intelligence in Healthcare and Education
AI in Service Interactions
Digital Mental Health Interventions
Publication details
- Publication date
- 1 January 2026
- Language
- EN
- Document type
- Preprint