Effects of the AI-HEALS intervention based on the Fogg behavior model on self-management in postoperative breast cancer patients: a randomized controlled trial study protocol

Abstract

Background Breast cancer is the most common malignancy among women, and postoperative self-management is critically associated with long-term quality of life. Traditional clinical nursing and mobile health interventions frequently lack behavioral theory support, thereby failing to meet individualized rehabilitation needs. The Fogg Behavior Model (FBM) provides a theoretical framework for precise intervention through the dimensions of motivation, ability, and prompts. Accordingly, this study developed an FBM-based AI-HEALS intervention and will validate its effectiveness via a Randomized Controlled Trial (RCT) to optimize digital transitional care after breast cancer surgery. Methods The study will conduct a single-blind, single-center randomized controlled trial in the Fourth Central Hospital of Baoding City, Hebei Province, with female postoperative breast cancer patients aged ≥18 years with stage I-III breast cancer. The control group received routine care, while the intervention group received the AI-HEALS intervention plan in addition to the routine care. Primary outcomes include changes in self-management behavior at baseline and 4, 12, and 24 weeks of follow-up. Secondary outcomes encompass mental health status, self-management efficacy, quality of life, and physiological-related indicators. Discussion The aim of this study was to develop an intervention programme for postoperative self-management in breast cancer patients by using the Fogg Behavior Model (FBM) as the theoretical framework and the AI-HEALS system as the intervention platform. Although FBM has shown effectiveness in explaining and promoting health behaviors in various chronic disease populations, systematic studies of its application to postoperative breast cancer self-management are lacking. Our intervention framework aims to stimulate motivation, enhance ability, and provide timely prompts to overcome the limitations of single-component or non-theory-based interventions in complex home-based rehabilitation scenarios. The AI-HEALS system addresses the challenges of traditional mHealth interventions—such as insufficient theoretical grounding, lack of personalisation, and inadequate handling of action triggers—and is expected to improve patients' self-management behaviors, mental health, and quality of life through precise knowledge delivery, dynamic AI-powered question-and-answer support, and full-cycle follow-up management. The development of the AI-HEALS system helps to reduce the burden on healthcare professionals, improve the distribution of healthcare resources, and have potential health economic benefits. Clinical trial registration: https://www.chictr.org.cn/showproj.html?proj=317062 , Identifier: ChiCTR2600126533.