跳到正文
arXiv cs.AI· Jodi Chiam, Aloysius Lim, Cheryl Nott, Nicholas Mark, Ankur Teredesai, Sunil Shinde·· 10 小时前AI 评分38

基于GNN推荐系统的AI健康提醒平台在新加坡84,764人中提升步数与MVPA

Co-Pilot for Health: Personalized Algorithmic AI Nudging to Improve Health Outcomes

AI 导读

研究团队设计并落地了一个由GNN推荐系统驱动的数字算法提醒平台,结合可穿戴设备的行为数据,在新加坡对84,764人开展为期12周的个性化情境化提醒实验。相比未收到提醒的匹配对照组,接受AI优化每日提醒的目标组日均步数提升6.17%(p=3.09×10⁻⁴),每周MVPA分钟数提升7.61%(p=1.16×10⁻²)。提醒打开率为13.1%,打开后11.7%被评为有用、1.9%被评为无用。

正文 · 原文

View PDF HTML (experimental)

Abstract:The ability to shape health behaviors of large populations automatically, across wearable types and disease conditions at scale has tremendous potential to improve global health outcomes. We designed and implemented an AI driven platform for digital algorithmic nudging, enabled by a Graph-Neural Network (GNN) based Recommendation System, and granular health behavior data from wearable fitness devices. Here we describe the efficacy results of this platform with its capabilities of personalized and contextual nudging to $n=84,764$ individuals over a 12-week period in Singapore. We statistically validated that participants in the target group who received such AI optimized daily nudges increased daily physical activity like step count by 6.17% ($p = 3.09\times10^{-4}$) and weekly minutes of Moderate to Vigorous Physical Activity (MVPA) by 7.61% ($p = 1.16\times10^{-2}$), compared to matched participants in control group who did not receive any nudges. Further, such nudges were very well received, with a 13.1% of nudges sent being opened (open rate), and 11.7% of the opened nudges rated useful compared to 1.9% rated as not useful thereby demonstrating significant improvement in population level engagement metrics.
Comments: 20 pages, 2 figures
Subjects: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as: arXiv:2401.10816 [cs.HC]
  (or arXiv:2401.10816v3 [cs.HC] for this version)
  https://doi.org/10.48550/arXiv.2401.10816

arXiv-issued DOI via DataCite

Submission history

From: Aloysius Lim [view email]
[v1] Fri, 19 Jan 2024 17:03:37 UTC (1,590 KB)
[v2] Fri, 9 Feb 2024 00:55:52 UTC (1,039 KB)
[v3] Wed, 18 Nov 2026 02:11:33 UTC (653 KB)

来源:arXiv cs.AI · arxiv.org