AI Insight
Researchers have released OpenMyHeartCounts (OpenMHC), the largest publicly accessible wearable health dataset containing over 60 million hours of data from 19 sensor channels collected from 11,894 participants over a decade through the My Heart Counts study app. The release includes open-source implementations of recent wearable foundation models and establishes a unified benchmark for evaluating model performance across health prediction, data imputation, and time-series forecasting tasks. This dataset links wearable sensor data with up to 169 variables related to health, lifestyle, mood, and behavior.
Why it matters
This release addresses a major barrier in wearable health AI research by providing unprecedented open access to large-scale, real-world health monitoring data and standardized evaluation methods. By democratizing access to both data and models, it could accelerate the development of AI systems for continuous health monitoring, early disease detection, and personalized health coaching through mobile and wearable devices.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Abstract: Mobile and wearable devices offer an unprecedented opportunity for continuous, passive health monitoring and active health coaching. However, the largest wearable datasets are not publicly available for research, and leading wearable foundation models trained on such datasets are rarely open-weight or come with reproducible training code. To accelerate open science in wearable health, we release OpenMyHeartCounts (OpenMHC), the largest and most comprehensive broadly accessible wearable health dataset to date, released to qualified researchers, alongside open-source implementations of recent wearable foundation models. OpenMHC, derived from over a decade of data collected through the My Heart Counts study app, includes >60 million hours of wearable data across 19 sensor channels (e.g., step count, heart rate, sleep, workouts) and up to 169 linked variables, including health, lifestyle, mood, and behavior from 11,894 consenting participants. Furthermore, we introduce a unified, open benchmark that enables standardized comparison of wearable health models across three tracks: health and behavior downstream prediction, multivariate data imputation, and time-series forecasting. We benchmark classical methods alongside recent wearable and multivariate time series foundation models. By releasing data under broad research access, alongside open-source code and model weights, at this unprecedented scale, we aim to democratize wearable health AI research and enable the community to drive open progress in this domain.
Source: OpenMHC: Accelerating the Science of Wearable Foundation Models