HEART-Watch: A multimodal physiological dataset from a Google Pixel Watch across different physical states

Consumer-grade smartwatches offer a new option for personalized health monitoring for general consumers, as cardiovascular diseases continue to prevail as the leading cause of global mortality. The development and validation of reliable cardiovascular monitoring algorithms for these consumer-grade devices requires realistic biosignal data from diverse sets of participants. However, the availability of public consumer-grade smartwatch datasets with synchronized cardiovascular biosignals remains limited, and existing datasets often lack rich demographic diversity in their participant cohorts, potentially leading to biased algorithm development. This paper presents HEART-Watch, a multimodal physiological dataset of synchronized wrist-worn Google Pixel Watch electrocardiogram (ECG), photoplethysmography, and accelerometer signals from a diverse cohort of 40 healthy adults across three physical states – sitting, standing and walking – alongside reference chest ECG. Intermittent upper arm blood pressure measurements and concurrent biosignals were collected as an additional biomarker for future research. The motivation, methodology, and initial analyses of results are presented. HEART-Watch is intended to support the development and benchmarking of robust cardiovascular algorithms on consumer-grade smartwatches across diverse populations.Author summary: Consumer-grade smartwatches are driving a global shift towards continuous and accessible healthcare for the general population. However, developing robust and equitable cardiovascular monitoring algorithms for these devices requires high-quality datasets for training and validation. Many consumer-grade smartwatches restrict access to raw sensor data, limiting researchers’ ability to obtain high-quality biosignals directly from the devices. Additionally, participant demographics in existing datasets often do not reflect the diversity present in real-world conditions, frequently focusing on young adults from a single ethnic background. Here, we establish the HEART-Watch dataset to address these challenges by collecting synchronized biosignals directly from a Google Pixel Watch across sitting, standing, and walking conditions in a diverse cohort of 40 participants. This work provides the research community with a realistic and inclusive resource to develop and evaluate cardiovascular monitoring algorithms for consumer-grade devices across a broad range of ages, body types, and backgrounds.