OpenMHC 发布:最大开放可穿戴健康数据集与基础模型基准
OpenMHC: Accelerating the Science of Wearable Foundation Models
研究团队推出 OpenMyHeartCounts(OpenMHC)可穿戴健康数据集及配套开源模型与代码,数据来自 My Heart Counts 研究 App 十余年积累,含 11,894 名参与者、超 67M 参与者小时、最多 19 个传感器通道和 170 项健康行为变量。
Authors:Narayan Schuetz, Yuze Bai, Lianggang Pan, Edgar Eggert, Favour Nerrise, Juan Delgado-SanMartin, Max Rosenblattl, Milana Gurbanova, Mohammad Asadi, Anders Johnson, Steven G. Hershman, Paul Schmiedmayer, Dennis Wang, Allan Lawrie, Daniel Seung Kim, Xin Liu, Akshay Paruchuri, Ehsan Adeli, Euan A. Ashley, Kelly W. Zhang
Abstract:Mobile and wearable devices offer an unprecedented opportunity for continuous, passive health monitoring and active health coaching. However, the largest wearable datasets are proprietary, and leading wearable foundation models trained on them are rarely open weight or include reproducible training code. To accelerate open science in wearable health, we introduce OpenMyHeartCounts (OpenMHC), the largest and most comprehensive wearable health dataset broadly accessible to qualified researchers, alongside open-source implementations and weights for recent wearable foundation models. Derived from over a decade of data collected through the My Heart Counts study app, OpenMHC comprises over 67M participant-hours of wearable recordings across up to 19 sensor channels (e.g., step count, heart rate, sleep, workouts) and up to 170 health, lifestyle, mood, and behavioral variables from 11,894 participants. Furthermore, we establish a benchmark for standardized evaluation across three tasks: (1) health and behavioral outcome prediction, (2) multivariate data imputation, and (3) time-series forecasting. Benchmarking classical methods alongside recent wearable and time-series foundation models, we find that while foundation models perform strongly, carefully tuned classical baselines like XGBoost remain highly competitive. By uniting broad-access wearable data with open code and model weights, OpenMHC provides a framework needed to drive reproducible advances in wearable health AI.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.16235 [cs.LG] |
| (or arXiv:2607.16235v4 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2607.16235 arXiv-issued DOI via DataCite |
|
| Journal reference: | NeurIPS 2026 |
Submission history
From: Kelly Zhang [view email]
[v1]
Thu, 25 Jun 2026 18:59:23 UTC (2,544 KB)
[v2]
Tue, 21 Jul 2026 10:33:05 UTC (2,817 KB)
[v3]
Sat, 8 Aug 2026 18:21:20 UTC (2,819 KB)
[v4]
Tue, 17 Nov 2026 07:48:50 UTC (4,268 KB)
来源:arXiv cs.AI · arxiv.org