van Vliet Milon H M, Versluis Anke, Chavannes Niels H, Scheltinga Bouke L, Albers Nele, Penfornis Kristell M, Baccinelli Walter, Meijer Eline
Department of Public Health and Primary Care, Leiden University Medical Center, Leiden, The Netherlands.
National eHealth Living Lab, Leiden University Medical Center, Leiden, The Netherlands.
Digit Health. 2024 Dec 5;10:20552076241300020. doi: 10.1177/20552076241300020. eCollection 2024 Jan-Dec.
Adopting healthy behavior is vital for preventing chronic diseases. Mobile health (mHealth) interventions utilizing virtual coaches (i.e., artificial intelligence conversational agents) can offer scalable and cost-effective solutions. Additionally, targeting multiple unhealthy behaviors, like low physical activity and smoking, simultaneously seems beneficial. We developed Perfect Fit, an mHealth intervention with a virtual coach providing personalized feedback to simultaneously promote smoking cessation and physical activity. Through innovative methods (e.g., sensor technology) and iterative development involving end-users, we strive to overcome challenges encountered by mHealth interventions, such as shortage of evidence-based interventions and insufficient personalization. This paper outlines the content of Perfect Fit and the protocol for evaluating its feasibility, acceptability, and preliminary effectiveness, the role of participant characteristics, and the study's feasibility.
A single-arm, mixed-method, real-world evaluation study will be conducted in the Netherlands. We aim to recruit 100 adult daily smokers intending to quit within 6 weeks. The personalized intervention will last approximately 16 weeks. Primary outcomes include Perfect Fit's feasibility and acceptability. Secondary outcomes are preliminary effectiveness and study feasibility, and we will measure participant characteristics. Quantitative data will be collected through questionnaires administered at baseline, post-intervention and 2, 6, and 12 months post-intervention. Qualitative data will be gathered via semi-structured interviews post-intervention. Data analysis will involve descriptive analyses, generalized linear mixed models (quantitative) and the Framework Approach (qualitative), integrating quantitative and qualitative data during interpretation.
This study will provide novel insight into the potential of interventions like Perfect Fit, as a multiple health behavior change strategy. Findings will inform further intervention development and help identify methods to foster feasibility and acceptability. Successful mHealth interventions with virtual coaches will prevent chronic diseases and promote public health.
采取健康行为对于预防慢性病至关重要。利用虚拟教练（即人工智能对话代理）的移动健康（mHealth）干预措施可以提供可扩展且具有成本效益的解决方案。此外，同时针对多种不健康行为，如低体力活动和吸烟，似乎是有益的。我们开发了“完美契合”（Perfect Fit），这是一种mHealth干预措施，配备虚拟教练提供个性化反馈，以同时促进戒烟和体力活动。通过创新方法（如传感器技术）以及涉及终端用户的迭代开发，我们努力克服mHealth干预措施所面临的挑战，如循证干预措施短缺和个性化不足。本文概述了“完美契合”的内容、评估其可行性、可接受性和初步有效性的方案、参与者特征的作用以及该研究的可行性。
将在荷兰进行一项单臂、混合方法、真实世界评估研究。我们的目标是招募100名打算在6周内戒烟的成年每日吸烟者。个性化干预将持续约16周。主要结果包括“完美契合”的可行性和可接受性。次要结果是初步有效性和研究可行性，我们将测量参与者特征。定量数据将通过在基线、干预后以及干预后2个月、6个月和12个月时发放的问卷收集。定性数据将通过干预后的半结构化访谈收集。数据分析将包括描述性分析、广义线性混合模型（定量）和框架法（定性），在解释过程中整合定量和定性数据。
本研究将为“完美契合”这类干预措施作为多种健康行为改变策略的潜力提供新的见解。研究结果将为进一步的干预开发提供信息，并有助于确定促进可行性和可接受性的方法。成功的带有虚拟教练的mHealth干预措施将预防慢性病并促进公共卫生。
