The DiaGame Study: Multimodal Data Collection in Free-Living Conditions Using Consumer-Level Wearable Devices and Apps in People with Diabetes

The everlasting interest in precision medicine has instigated a need for patient-specific multidimensional data collection. By leveraging consumer-level wearable devices and applications we can support this need by collecting multimodal data in uncontrolled free-living conditions. We used a continuous glucose monitor, a smartwatch with in-house developed application, and a smartphone application over a period of 14 days to collect data from 60 participants with diabetes. Data were collected on 77,683 CGM measurements, 4,073 moods, 3,517 meals, 1,394 insulin injections, and 1,364 bouts of physical activity. Participants were able to effectively use the devices and applications, with 45 participants reporting data on all modalities and all participants reporting data on at least two modalities (in addition to the data collected from the smartwatch’s internal sensors). These findings highlight the efficiency and effectiveness of consumer-level wearable devices to collect data from the comfort of the people’s homes. Thereby, facilitating the need for a cost-effective and scalable approach for precision monitoring to the public.