The Effectiveness and Feasibility of Conversational Agents in Supporting Care for Patients With Cancer: Systematic Review and Meta-Analysis

Abstract

Background: Patients with cancer experience complex physical, psychosocial, and behavioral challenges that require continuous support. This need has intensified with the rising cancer burden worldwide and the limited scalability of traditional care models. In response, conversational agents (CAs) have emerged as promising digital interventions for enhancing cancer care, but evidence regarding their feasibility and effectiveness remains limited.

Objective: This study aimed to evaluate the feasibility and effectiveness of CAs in supporting care for patients with cancer and to summarize the key characteristics of CA interventions to inform future design and implementation.

Methods: We systematically searched PubMed, Cochrane Library, Web of Science, and Embase databases from the index date through February 3, 2025, and screened reference lists and trial registries for gray literature. Eligible studies included randomized controlled trials (RCTs) and nonrandomized interventions (NRIs) evaluating CA-delivered interventions targeting health outcomes in patients with cancer. Two reviewers independently selected studies and extracted data. Study quality was then appraised using the Cochrane Risk of Bias 2.0 tool for RCTs and the Joanna Briggs Institute (JBI) Critical Appraisal Checklist for NRIs. Extracted data included study characteristics, CA features, and implementation outcomes, including feasibility, acceptability, and usability. Meta-analyses were conducted on physical activity, pain, anxiety, depression, psychological distress, and quality of life. Narrative synthesis was used for outcomes with inconsistent reporting across studies, including health information acquisition and treatment-related side effects.

Results: In total, 17 studies involving 1817 patients with cancer were included, with 10 (58.8%) studies being included in the meta-analysis. The meta-analysis showed significant improvements in physical activity (mean difference [MD]=1.44, 95% CI 0.36-2.52, P<.01), pain (MD=-0.91, 95% CI -1.44 to -0.38, P<.01), anxiety (SMD=-0.19, 95% CI -0.35 to -0.02, P=.02), and quality of life (SMD=0.35, 95% CI 0.03-0.67, P=.03). No significant effects were observed on depression (SMD=-0.07, 95% CI -0.42 to 0.27, P=.68) or psychological distress (SMD=-0.33, 95% CI -0.66 to 0.01, P=.06). Narrative synthesis suggested that CAs have the potential to improve patients' acquisition of health information and help manage treatment-related side effects. Notably, CAs were generally found to be safe, feasible, acceptable, and usable among patients with cancer, particularly during the initial phase of use. However, user engagement tended to decline over time, underscoring the need for strategies to sustain long-term use.

Conclusions: This systematic review is the first comprehensive analysis to suggest that CAs are feasible, acceptable, usable, and effective interventions for patients with cancer. Nevertheless, the limited psychological benefits and suboptimal long-term user engagement indicate the need for further refinement. Future research should adopt theory-based designs and leverage emerging technologies to enhance personalization, empathy, and sustained engagement in CA interventions. Robust evidence from large-scale RCTs is needed to strengthen the evidence base.

Trial registration: PROSPERO CRD42025645982; https://www.crd.york.ac.uk/PROSPERO/view/CRD42025645982.

Keywords: artificial intelligence; cancer; care; conversational agent; conversational agents; meta-analysis; systematic review.

Figure 1

PRISMA flow diagram showing the study selection process. PRISMA: Preferred Reporting Items for Systematic Reviews and Meta-Analyses.

Figure 2

Forest plot of (A) quality of life, (B) physical activity (×1,000 steps), (C) pain, (D) anxiety, (E) depression, and (F) psychological distress.