WatchGuardian: Enabling User-Defined Personalized Just-in-Time Intervention on Smartwatch
ACM Transactions on Computing for Healthcare · 31.10.2026 · 7 (4) · 1-31
DOI: 10.1145/3788689 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Computing for Healthcare, online erschienen am 26.10.2026. Verfasst von Ying Lei und 15 weiteren Autor:innen. Beteiligte Einrichtung: Simon Fraser University, Surrey, British Columbia, Canada. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 175 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCI NIH HHS, NLM NIH HHS, National Cancer Institute of the National Institutes of Health.
Abstract (Originalsprache)
While just-in-time interventions (JITIs) have effectively targeted common health behaviors, individuals often have unique needs to intervene in personal undesirable actions that can negatively affect physical, mental, and social well-being. We present WatchGuardian, a smartwatch-based JITI system that empowers users to define custom interventions for personal actions with few samples. To detect new actions from limited data, we developed a few-shot learning pipeline that fine-tuned a pre-trained inertial measurement unit (IMU) model on public hand-gesture datasets. We then designed a data augmentation and synthesis process to train additional classification layers for customization. Our offline evaluation with 26 participants showed that with three, five, and ten examples, our approach achieved an accuracy of 76.8%, 84.7%, and 87.7%, and an F1 score of 74.8%, 84.2%, and 87.3%. We then conducted a 4-hour intervention study to compare WatchGuardian against a rule-based intervention. Our results demonstrated that our system led to a significant reduction by 64.0 \(\, \pm \, \) 22.6% in undesirable actions, substantially outperforming the baseline by 29.0%. Our findings underscore the effectiveness of a customizable, AI-driven JITI system for individuals in need of behavioral intervention in personal undesirable actions. We envision that our work can inspire broader applications of user-defined personalized intervention with advanced AI solutions.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Simon Fraser University, Surrey, British Columbia, Canada.
- Columbia University, New York, New York, USA.
- Stanford University, Stanford, California, USA.
- The Ohio State University, Columbus, Ohio, USA.
- Nationwide Children's Hospital, Columbus, Ohio, USA.
- Northeastern University, Boston, Massachusetts, USA.
ORCID-Profile: Ying Lei, Yancheng Cao, Will Ke Wang, Yuanzhe Dong, Changchang Yin, Weidan Cao, Ping Zhang, Jingzhen Yang, Bingsheng Yao, Yifan Peng, Chunhua Weng, Randy Auerbach, Lena Mamykina, Dakuo Wang, Yuntao Wang, Xuhai Xu
Förderung
- NCI NIH HHS
- NLM NIH HHS
- National Cancer Institute of the National Institutes of Health
Zitieren
APA
Lei, Y., Cao, Y., Wang, W. K., Dong, Y., Yin, C., Cao, W., Zhang, P., Yang, J., Yao, B., Peng, Y., Weng, C., Auerbach, R., Mamykina, L., Wang, D., Wang, Y., & Xu, X. (2026). WatchGuardian: Enabling User-Defined Personalized Just-in-Time Intervention on Smartwatch. ACM Transactions on Computing for Healthcare, 7(4), 1-31. https://doi.org/10.1145/3788689
Vancouver
Lei Y, Cao Y, Wang WK, Dong Y, Yin C, Cao W, et al. WatchGuardian: Enabling User-Defined Personalized Just-in-Time Intervention on Smartwatch. ACM Transactions on Computing for Healthcare. 2026;7(4):1-31. doi:10.1145/3788689
BibTeX
@article{Lei2026,
author = {Lei, Ying and Cao, Yancheng and Wang, Will Ke and Dong, Yuanzhe and Yin, Changchang and Cao, Weidan and Zhang, Ping and Yang, Jingzhen and Yao, Bingsheng and Peng, Yifan and Weng, Chunhua and Auerbach, Randy and Mamykina, Lena and Wang, Dakuo and Wang, Yuntao and Xu, Xuhai},
title = {WatchGuardian: Enabling User-Defined Personalized Just-in-Time Intervention on Smartwatch},
journal = {ACM Transactions on Computing for Healthcare},
year = {2026},
volume = {7},
number = {4},
pages = {1--31},
doi = {10.1145/3788689}
}
EUVIMED