Digital Health Monthly: Scientific Webinar Series
Grant Planning for Wearable-Based Research: Insights and Best Practices
Academic and Population Health Research
Open-Source Digital Dataset Library
Upcoming Digital Health Monthly:
Scientific Webinar Series
Accelerating DHT Research and Drug Development with Open-Source Big Data from Population Studies
Tuesday, December 3 @ 12 PM ET
Digital Health Monthly: Scientific Webinar Series
Sensor-based DHTs are shedding an illuminating light on how people function in their real-world environments. Drug developers, researchers, patients, and regulators are realizing the multifaceted value sensor-based DHTs can bring to clinical research.
As their adoption continues to grow, the ActiGraph team is excited to continue ‘Digital Health Monthly’, a monthly series of science-focused webinars to share the latest high-impact developments in clinical research from innovators in the digital health field. Each month, we feature brief data-driven presentations from clinical researchers, data scientists, and biostatisticians on a focused topic with dedicated time for audience Q&A. We believe that together, we can move the digital health technology field forward faster, and we are excited for this opportunity to facilitate important discussions on the latest research with members of the digital health community.
What You'll Find
This library is a collection of open-source digital datasets, a brief description of each study, measurement domains, and links to websites where researchers can access the datasets.
Value to Researchers
These resources can help researchers who are planning studies using wearables investigate the reliability and variability of digital measures. This information can inform decisions such as study design, power analyses, and measure selection (see an example here).
These datasets also provide clinical researchers with rich and diverse data that they otherwise may not have the means to collect, expanding the opportunities for broader analyses to address key health-related questions and resulting in thousands of peer-reviewed publications.
National Health and Nutrition Examination Survey (NHANES)
About: The National Health and Nutrition Examination Survey (NHANES) collects data about the health of adults and children in the United States.
Measurement Domains: Physical Activity, Mobility, Sleep
Data Access: https://wwwn.cdc.gov/nchs/nhanes/
UK Biobank
About: UK Biobank is the world’s most comprehensive dataset of biological, health, and lifestyle information.
Measurement Domains: Physical Activity, Mobility
Data Access: https://www.ukbiobank.ac.uk/use-our-data/
National Health and Aging Trends Study (NHATS)
About: NHATS gathers information on a nationally representative sample of Medicare beneficiaries ages 65 and older.
Measurement Domains: Physical Activity, Mobility
Data Access: https://www.nhats.org/researcher/data-access
Canadian Longitudinal Study on Aging (CLSA)
About: The CLSA is a large, national research platform on health and aging allowing researchers to answer critical questions on the biological, medical, psychological, social, lifestyle and economic aspects of aging, disability and disease.
Measurement Domains: Physical Activity, Mobility
Data Access: https://www.clsa-elcv.ca/data-access/
Molecular Transducers of Physical Activity Consortium (MoTrPAC)
About: MoTrPAC is a national research initiative that aims to generate a molecular map of the effects of exercise and training.
Measurement Domains: Physical Activity, Mobility
Data Access: https://motrpac-data.org/
Labeled Raw Accelerometry Data Captured During Walking, Stair Climbing and Driving
About: The database contains raw accelerometry data collected during outdoor walking, stair climbing, and driving for 32 healthy adults. Accelerometry data were collected simultaneously at both wrists and ankles.
Measurement Domains: Mobility
Data Access: https://physionet.org/content/accelerometry-walk-climb-drive/1.0.0/
Activities of Daily Living (ADL) Dataset
About: This labeled dataset contains multiple instances of 9 Activities of Daily Living (ADL)-related actions namely Walk, Sit Down, Stand Up, Open Door, Close Door, Pour Water, Drink Glass, Brush Teeth and Clean Table while the participants wore 6 IMU sensors on different body parts.
Measurement Domains: Physical Activity, Mobility
Data Access: https://data.mendeley.com/datasets/wjpbtgdyzm/1
Human Activity Recognition (HAR) Dataset
About: Human Activity Recognition (HAR) refers to the capacity of machines to perceive human actions. This dataset contains information on 18 different activities collected using smartphone sensors (Accelerometer and Gyroscope).
Measurement Domains: Physical Activity, Human Activity Recognition
Data Access: https://data.mendeley.com/datasets/45f952y38r/5
Daily Life Activities in Persons with Multiple Sclerosis
About: A wearable sensor dataset featuring data collected from 38 persons with multiple sclerosis (PwMS), 21 of which are identified as fallers and 17 as non-fallers based on 6 month fall history. Both in lab and remote data are available.
Measurement Domains: Physical Activity, Fall Risk
Data Access: https://simtk.org/projects/msense_ms_adls
Long Term Movement Monitoring Database
About: The Long Term Movement Monitoring database contains 3-day 3D accelerometer recordings of 71 elder community residents, used to study gait, stability, and fall risk.
Measurement Domains: Mobility, Fall Risk
Data Access: https://physionet.org/content/ltmm/1.0.0/
UMAFall: Fall Detection Dataset
About: The dataset contains mobility traces generated by a group of 19 experimental subjects that emulated a set of predetermined ADL (Activities of Daily Life) and falls. The traces are aimed at evaluating fall detection algorithms.
Measurement Domains: Fall Risk
Data Access: https://figshare.com/articles/dataset/UMA_ADL_FALL_Dataset_zip/4214283
FallRiskPD Dataset
About: This dataset provides spatio-temporal gait parameters recorded from 35 Parkinson's disease patients during real-world gait and unsupervised 4x10 Meter Walking tests.
Measurement Domains: Gait, Fall Risk
Data Access: https://osf.io/h6apq/wiki/home/
Gait in Parkinson's Disease
About: A collection of multichannel recordings from force sensors beneath the feet of 93 patients with Parkinson's Disease, and 73 healthy controls, collected from three studies. This database also includes demographic information, measures of disease severity and other related measures.
Measurement Domains: Gait
Data Access: https://physionet.org/content/gaitpdb/1.0.0/
Mobilise-D
About: Mobilise-D was a 5-year, IMI-funded project that produced validated and accepted digital mobility outcomes to monitor the daily life gait of people with various mobility problems, including chronic obstructive pulmonary disease (COPD), Parkinson’s disease (PD), multiple sclerosis (MS), hip fracture recovery, and congestive heart failure, aiming to improve follow-up and personalized care. Open-source algorithm package is also available.
Measurement Domains: Gait
Data Access: https://mobilise-d.eu/data/
OxWalk
About: Wrist and hip-based activity tracker dataset for free-living step detection and gait recognition, including step annotation based on video captured during data collection.
Measurement Domains: Gait
Data Access: https://ora.ox.ac.uk/objects/uuid:19d3cb34-e2b3-4177-91b6-1bad0e0163e7
Clemson Pedometer Project
About: This project recorded a large data set of raw accelerometer data and marked the time occurrences of all steps so that pedometer algorithms could be evaluated objectively against a gold standard.
Measurement Domains: Gait
Data Access: https://cecas.clemson.edu/~ahoover/pedometer/
Gaitmap
About: These datasets contain open source packages for IMU data processing from foot locations.
Measurement Domains: Gait
Data Access: https://github.com/mad-lab-fau/gaitmap-datasets?tab=readme-ov-file
Machine Learning and Data Analytics (MaD) Lab Digital Health Datasets
About: A dataset containing IMU recordings with full motion capture reference from 14 participants (approx. 10000 strides). Each participant was equipped with 15 synchronized IMUs. The main goal of the dataset is to compare the recorded signals of the 6 sensors attached to each foot.
Measurement Domains: Gait
Data Access: https://www.mad.tf.fau.de/research/datasets/#collapse_10
Submit a Dataset
This is not a complete list of open-source digital data sets. If you’d like to share a data set that you think should be included in this library, please let us know!