Abstract
Multiple behaviors typically work together to influence health, making it hard to understand how one behavior might compensate for another. Rich multi-modal datasets from mobile sensors and advances in machine learning are today enabling new kinds of associations to be made between combinations of behaviors objectively assessed from daily life and self-reported levels of stress, mood, and health. In this article, we present a framework to (1) map multi-modal messy data collected in the “wild” to meaningful feature representations of health-related behaviors, (2) uncover latent patterns comprising combinations of behaviors that best predict health and well-being, and (3) use these learned patterns to make evidence-based recommendations that may improve health and well-being. We show how to use supervised latent Dirichlet allocation to model the observed behaviors, and we apply variational inference to uncover the latent patterns. Implementing and evaluating the model on 5,397 days of data from a group of 244 college students, we find that these latent patterns are indeed predictive of daily self-reported levels of stressed-calm, sad-happy, and sick-healthy states. We investigate the patterns of modifiable behaviors present on different days and uncover several ways in which they relate to stress, mood, and health. This work contributes a new method using objective data analysis to help advance understanding of how combinations of modifiable human behaviors may promote human health and well-being.
- Yoshua Bengio, Aaron Courville, and Pascal Vincent. 2013. Representation learning: A review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence 35, 8 (2013), 1798--1828.Google Scholar
Digital Library
- David M. Blei and John D. Lafferty. 2006. Dynamic topic models. In Proceedings of the 23rd International Conference on Machine Learning. ACM, New York, NY, 113--120.Google Scholar
- David M. Blei and Jon D. McAuliffe. 2007. Supervised topic models. In Advances in Neural Information Processing Systems.Google Scholar
- David M. Blei, Andrew Y. Ng, and Michael I. Jordan. 2003. Latent Dirichlet allocation. Journal of Machine Learning Research 3 (2003), 993--1022.Google Scholar
Digital Library
- Taridzo Chomutare, Eirik Arsand, and Gunnar Hartvigsen. 2011. Mobile peer support in diabetes. Studies in Health Technology and Informatics 169 (2011), 48--52. http://www.ncbi.nlm.nih.gov/pubmed/21893712.Google Scholar
- Ed Diener and Martin Seligman. 2017. Beyond money: Progress on an economy of well-being. Psychological Science in the Public Interest 5, 1 (2017), 1--31.Google Scholar
Cross Ref
- Katayoun Farrahi and Daniel Gatica-Perez. 2014. A probabilistic approach to mining mobile phone data sequences. Personal and Ubiquitous Computing 18, 1 (2014), 223--238.Google Scholar
Digital Library
- Robert G. Farrell, Catalina M. Danis, Sreeram Ramakrishnan, and Wendy A. Kellogg. 2012. Intrapersonal retrospective recommendation: Lifestyle change recommendations using stable patterns of personal behavior. In Proceedings of the ACM RecSys 1st International Workshop on Recommendation Technologies for Lifestyle Change, Vol. 891. 24--28. DOI:https://doi.org/10.1145/2365952.2366045Google Scholar
- Laura Ferrari and Marco Mamei. 2011. Discovering daily routines from Google Latitude with topic models. In Proceedings of the IEEE International Conference on Pervasive Computing and Communications Workshops. 432--437.Google Scholar
- Mouzhi Ge, Mehdi Elahi, Ignacio Fernaández-Tobías, Francesco Ricci, and David Massimo. 2015. Using tags and latent factors in a food recommender system. In Proceedings of the 5th ACM International Conference on Digital Health. 105--112. DOI:https://doi.org/10.1145/2750511.2750528Google Scholar
- Suzanne Hudd, Jennifer Dumlao, Diane Erdmann-Sager, Daniel Murray, Emily Phan, Nicholas Soukas, and Nori Yokozuka. 2000. Stress at college: Effects on health habits, health status and self-esteem. College Student Journal 34, 2 (2000), 217--227.Google Scholar
- Tâm Huynh, Mario Fritz, and Bernt Schiele. 2008. Discovery of activity patterns using topic models. In Proceedings of the 10th ACM International Conference on Ubiquitous Computing. 10--19.Google Scholar
Digital Library
- Imran Shuja Khawaja, Joseph J. Westermeyer, Prashant Gajwani, and Robert E. Feinstein. 2009. Depression and coronary artery disease: The association, mechanisms, and therapeutic implications. Psychiatry (Edgmont) 6, 1 (2009), 38.Google Scholar
- Jia Li, Yu Rong, Helen Meng, Zhihui Lu, Timothy Kwok, and Hong Cheng. 2018. TATC: Predicting Alzheimer’s disease with actigraphy data. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, New York, NY, 509--518.Google Scholar
- Ehimwenma Nosakhare and Rosalind Picard. 2019. Probabilistic latent variable modeling for assessing behavioral influences on well-being. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, New York, NY, 2718--2726.Google Scholar
Digital Library
- Gregory A. Panza, Beth A. Taylor, Paul D. Thompson, C. Michael White, and Linda S. Pescatello. 2017. Physical activity intensity and subjective well-being in healthy adults. Journal of Health Psychology 24, 9 (2017), 135910531769158.Google Scholar
- Tim Pawlowski, Paul Downward, and Simona Rasciute. 2011. Subjective well-being in European countries—On the age-specific impact of physical activity. European Review of Aging and Physical Activity 8, 2 (2011), 93--102.Google Scholar
- Santi Phithakkitnukoon, Teerayut Horanont, Giusy Di Lorenzo, Ryosuke Shibasaki, and Carlo Ratti. 2010. Activity-aware map: Identifying human daily activity pattern using mobile phone data. In Proceedings of the International Workshop on Human Behavior Understanding. 14--25.Google Scholar
- Dinh Phung, Brett Adams, Kha Tran, Svetha Venkatesh, and Mohan Kumar. 2009. High accuracy context recovery using clustering mechanisms. In Proceedings of the IEEE International Conference on Pervasive Computing and Communications. 1--9.Google Scholar
- Frans Pouwer, Nina Kupper, and Marcel C. Adriaanse. 2010. Does emotional stress cause type 2 diabetes mellitus? A review from the European Depression in Diabetes (EDID) research consortium. Discovery Medicine 9, 45 (2010), 112--118.Google Scholar
- Tom Quisel, Luca Foschini, Alessio Signorini, and David C. Kale. 2017. Collecting and analyzing millions of mHealth data streams. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, New York, NY, 1971--1980.Google Scholar
- Mashfiqui Rabbi, Min Hane Aung, Mi Zhang, and Tanzeem Choudhury. 2015. MyBehavior: Automatic personalized health feedback from user behaviors and preferences using smartphones. In Proceedings of the ACM International Joint Conference on Pervasive and Ubiquitous Computing. 707--718. DOI:https://doi.org/10.1145/2750858.2805840Google Scholar
- Richard M. Ryan, Jessey H. Bernstein, and Kirk Warren Brown. 2010. Weekends, work, and well-being: Psychological need satisfactions and day of the week effects on mood, vitality, and physical symptoms. Journal of Social and Clinical Psychology 29, 1 (2010), 95--122.Google Scholar
Cross Ref
- Akane Sano. 2015. Measuring College Students’ Sleep, Stress and Mental Health with Wearable Sensors and Mobile Phones. Ph.D. Dissertation. MIT.Google Scholar
- Akane Sano, Andrew J. Phillips, Andrew W. McHill, Sara Taylor, Laura K. Barger, Charles A. Czeisler, and Rosalind W. Picard. 2017. Influence of weekly sleep regularity on self-reported wellbeing. Sleep 40, Suppl. 1 (2017), A67--A68.Google Scholar
- Akane Sano, Sara Taylor, Andrew W. McHill, Andrew J. Phillips, Laura K. Barger, Elizabeth Klerman, and Rosalind Picard. 2018. Identifying objective physiological markers and modifiable behaviors for self-reported stress and mental health status using wearable sensors and mobile phones. Journal of Medical Internet Research 20, 6 (2018), e210.Google Scholar
Cross Ref
- Julia Seiter, Oliver Amft, Mirco Rossi, and Gerhard Tröster. 2014. Discovery of activity composites using topic models: An analysis of unsupervised methods. Pervasive and Mobile Computing 15 (2014), 215--227.Google Scholar
Digital Library
- Janine H. Stubbe, Marleen H. M. de Moor, Dorret I. Boomsma, and Eco J. C. de Geus. 2007. The association between exercise participation and well-being: A co-twin study. Preventive Medicine 44, 2 (2007), 148--152.Google Scholar
Cross Ref
- Sara Taylor, Natasha Jaques, Ehimwenma Nosakhare, Akane Sano, and Rosalind Picard. 2017. Personalized multitask learning for predicting tomorrow’s mood, stress, and health. IEEE Transactions on Affective Computing 14, 8 (2017), 1.Google Scholar
- Rui Wang, Fanglin Chen, Zhenyu Chen, Tianxing Li, Gabriella Harari, Stefanie Tignor, Xia Zhou, Dror Ben-Zeev, and Andrew T. Campbell. 2014. StudentLife: Assessing mental health, academic performance and behavioral trends of college students using smartphones. In Proceedings of the ACM International Joint Conference on Pervasive and Ubiquitous Computing. 3--14.Google Scholar
- Paul Wicks, Michael Massagli, Jeana Frost, Catherine Brownstein, Sally Okun, Timothy Vaughan, Richard Bradley, and James Heywood. 2010. Sharing health data for better outcomes on PatientsLikeMe. Journal of Medical Internet Research 12, 2 (2010), e19. DOI:https://doi.org/10.2196/jmir.1549Google Scholar
- Simone Wilson-Salandy and Mary A. Nies. 2012. The effect of physical activity on the stress management, interpersonal relationships, and alcohol consumption of college freshmen. SAGE Open 2, 4 (2012), 1--4.Google Scholar
Index Terms
Toward Assessing and Recommending Combinations of Behaviors for Improving Health and Well-Being
Recommendations
Probabilistic Latent Variable Modeling for Assessing Behavioral Influences on Well-Being
KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningHealth research has an increasing focus on promoting well-being and positive mental health, to prevent disease and to more effectively treat disorders. The availability of rich multi-modal datasets and advances in machine learning methods are now ...
Physical analytics to model health behaviors
WPA '14: Proceedings of the 2014 workshop on physical analyticsMobile phones are a pervasive platform for opportunistic sensing of social and health related behaviors. In this talk, I discuss how sensor data from mobile phones can be used to model and predict health outcomes. The talk starts with a review of ...
Toward Ubiquitous Assessment of Neonates' Health Condition
UbiComp '18: Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable ComputersNeonates needs an intensive health care during their early life. The cost of health care is high. In addition, health care might not be accessible to neonates in rural areas. In this paper, we propose the development of a smart, accessible, and cost-...






Comments