Review of Large Language Models for Patient and Caregiver Support in Cancer Care Delivery

This narrative review examines the current landscape and evidence regarding large language model (LLM) applications designed to support patients with cancer and caregivers. We analyzed peer-reviewed literature, conference proceedings, and implementation studies exploring LLM use in oncology patient support. Applications cluster in four primary domains: education and information delivery, symptom checking and triage, telehealth integration, and clinical trial participation. Studies demonstrate promising accuracy for basic cancer information delivery, although performance varies for complex clinical scenarios. Early research shows preclinical feasibility and acceptability of LLM-enhanced tools for patients, but effectiveness data remain limited. Implementation barriers include scalable monitoring, equitable access, maintaining privacy standards, and validating accuracy across diverse populations. We also examine potential future applications across the cancer care continuum, from prevention through end-of-life care, and propose strategies for development and implementation. Additionally, we present a framework to guide physician-patient discussions regarding LLM use in oncology, addressing privacy concerns, setting appropriate expectations, and ensuring safe integration into care delivery. Future research should use robust evaluation frameworks focused on safety and patient-centered outcomes while carefully considering health equity implications. As these technologies evolve, maintaining focus on evidence-based validation will be crucial for realizing their potential to enhance cancer care delivery, engagement, and patient satisfaction.