Digital health; Digital receipt-based diet monitoring; Machine learning; Social structuring of digital health use; Lived experience of digital health ; ChronoGraph; Temporal graph traversal
Schönenberger Katja A., Cossu Luca, Prendin Francesco, Cappon Giacomo, Wu Jing, Fuchs Klaus L., Mayer Simon, Herzig David, Facchinetti Andrea, Bally Lia (2022), Digital Solutions to Diagnose and Manage Postbariatric Hypoglycemia, in Frontiers in Nutrition
, 9, 1.
WuJing, FuchsKlaus, LianJie, HaldimannMirella Lindsay, SchneiderTanja, MayerSimon, ByunJaewook, GassmannRoland, BrombachChristine, FleischElgar (2021), Estimating Dietary Intake from Grocery Shopping Data - A Comparative Validation of Relevant Indicators in Switzerland, in nutrients
, 14 (1)(159), 1-26.
Mayer Simon, Fuchs Klaus, Brügger Dominic, Lian Jie, Ciortea Andrei (2021), Improving customer decisions in web-based e-commerce through guerrilla modding, in Nature Machine Intelligence
, 3(12), 1008-1010.
FuchsKlaus, MayerSimon, Schneider Tanja (2021), Die Datafizierung von Alltagspraktiken: Datenaktivismus als neue Verantwortung?, in Henkel Anna (ed.), transcript Verlag, Bielefeld, 183-196.
Byun Jaewook (2020), Enabling time-centric computation for efficient temporal graph traversals from multiple sources, in IEEE Transactions on Knowledge and Data Engineering
MoenninghoffAnnette, FuchsKlaus, WuJing, AlbertJan, MayerSimon, The Effect of a Future-Self Avatar mHealth Intervention on Physical Activity and Food Purchases: The FutureMe Randomized Controlled Trial, in Journal of Medical Internet Research
Diet-related non-communicable diseases are the leading cause of mortality worldwide, accounting for more deaths than all other, non-diet-related mortality causes combined (Forouzanfar et al., 2015). Previous research on developing effective strategies to improve dietary consumption primarily focus on the individual level (Schneider, 2019), on monitoring dietary intake and behavioral interventions influencing dietary habits. Unfortunately, until today, such strategies that are enabled by digital dietary self-tracking remain limited by resource- and personal constraints (Vignerová et al. 2011), are discontinued due to the manual logging involved (Fuchs et al. 2018), are not tailored to the individual (Brug et al. 2003), or suffer under self-selection of healthy individuals (König et al. 2018). Aiming to overcome these drawbacks, this interdisciplinary Swiss-Korean research collaboration entitled ‘FoodCoach’ proposes a novel, scalable and tailored approach towards diet monitoring and interventions. Therefore, we plan to apply artificial intelligence to process customers’ automatically collected digital receipts from grocery purchases in order to i) estimate households’ and individual dietary behavior, and ii) tailor adaptive interventions to participants, based on their purchase behavior and estimated nutritional context, in order to support healthier food choices. Thereby, ‘FoodCoach’ aims to overcome the contemporary limitations of modern diet-related mobile health applications (mHealth). Simultaneously, the proposed project identifies potential adoption drivers (e.g. convenience) and barriers (e.g. privacy concerns) by exploring people’s lived experience of digital receipt-based dietary tracking based on survey and focus group research. This affords the opportunity for users' responses (but also non-users' responses) to co-shape the set-up of the study, the design of the interfaces, as well as the kinds of information and hence interventions provided. The project aims to compile the largest digital receipt-based diet panel globally and assess this novel approach’s accuracy, scalability, efficacy and ability to reach previously uninvolved users, an important prerequisite in the mitigation of diet-related diseases.