Abstract
BACKGROUND: Breast cancer ranks as the most prevalent cancer among women globally, with significant variations in both incidence and mortality rates. Traditional health education improves knowledge and some behaviors but often fails to sustain long-term change due to its static and unidirectional nature. To overcome these limitations, we developed a spiral health education model integrating Problem-Based Learning, the Knowledge-Attitude-Practice framework, and Artificial Intelligence (PBL-KAP-AI). OBJECTIVE: This study aims to assess how the PBL-KAP-AI model influences health behaviors, health beliefs, and quality of life among breast cancer patients, while also exploring the potential mediating and moderating mechanisms involved. METHODS: A randomized trial with implementation limitations was conducted from January to March 2024, involving 488 breast cancer patients. Participants were randomly assigned to either the intervention or control group, with 244 participants in each group. Assessments were carried out pre- and post-intervention (3 months), evaluating health behaviors (HPLP-II), health beliefs, and quality of life (SF-36). Data were analyzed using t-tests, repeated measures ANOVA (RM-ANOVA), and Bootstrap-based mediation and moderation models. Strict blinding and allocation concealment were maintained throughout the study, with intervention quality ensured through random audits, AI record reviews, and participant interviews. Intent-to-treat (ITT) analysis was used for handling dropouts, ensuring the integrity of the data and the reliability of the results. RESULTS: The intervention group achieved significantly greater improvements in health behaviors (123.01 ± 9.90 vs. 98.12 ± 7.96), health beliefs (128.69 ± 15.89 vs. 107.65 ± 16.24), and quality of life (80.58 ± 7.28 vs. 71.37 ± 10.21; all p < 0.001). Mediation analysis showed satisfaction influenced quality of life through health behaviors, while moderated mediation revealed behavior levels shaped the pathway to health beliefs. CONCLUSION: The PBL-KAP-AI model effectively enhances behaviors, beliefs, and quality of life, offering an interactive, adaptive, and sustainable paradigm for digital health education.