Dataset Information

Validation of an open-source smartphone step counting algorithm in clinical and non-clinical settings.

ABSTRACT:

Background

Step counts are increasingly used in public health and clinical research to assess wellbeing, lifestyle, and health status. However, estimating step counts using commercial activity trackers has several limitations, including a lack of reproducibility, generalizability, and scalability. Smartphones are a potentially promising alternative, but their step-counting algorithms require robust validation that accounts for temporal sensor body location, individual gait characteristics, and heterogeneous health states.

Objective

Our goal was to evaluate an open-source step-counting method for smartphones under various measurement conditions against step counts estimated from data collected simultaneously from different body locations ("internal" validation), manually ascertained ground truth ("manual" validation), and step counts from a commercial activity tracker (Fitbit Charge 2) in patients with advanced cancer ("wearable" validation).

Methods

We used eight independent datasets collected in controlled, semi-controlled, and free-living environments with different devices (primarily Android smartphones and wearable accelerometers) carried at typical body locations. Five datasets (N=103) were used for internal validation, two datasets (N=107) for manual validation, and one dataset (N=45) used for wearable validation. In each scenario, step counts were estimated using a previously published step-counting method for smartphones that uses raw sub-second level accelerometer data. We calculated mean bias and limits of agreement (LoA) between step count estimates and validation criteria using Bland-Altman analysis.

Results

In the internal validation datasets, participants performed 751.7±581.2 (mean±SD) steps, and the mean bias was -7.2 steps (LoA -47.6, 33.3) or -0.5%. In the manual validation datasets, the ground truth step count was 367.4±359.4 steps while the mean bias was -0.4 steps (LoA -75.2, 74.3) or 0.1 %. In the wearable validation dataset, Fitbit devices indicated mean step counts of 1931.2±2338.4, while the calculated bias was equal to -67.1 steps (LoA -603.8, 469.7) or a difference of 0.3 %.

Conclusions

This study demonstrates that our open-source step counting method for smartphone data provides reliable step counts across sensor locations, measurement scenarios, and populations, including healthy adults and patients with cancer.

SUBMITTER: Straczkiewicz M

PROVIDER: S-EPMC10081434 | biostudies-literature | 2023 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Validation of an open-source smartphone step counting algorithm in clinical and non-clinical settings.

Straczkiewicz Marcin M Keating Nancy L NL Thompson Embree E Matulonis Ursula A UA Campos Susana M SM Wright Alexi A AA Onnela Jukka-Pekka JP

medRxiv : the preprint server for health sciences 20230328

<h4>Background</h4>Step counts are increasingly used in public health and clinical research to assess wellbeing, lifestyle, and health status. However, estimating step counts using commercial activity trackers has several limitations, including a lack of reproducibility, generalizability, and scalability. Smartphones are a potentially promising alternative, but their step-counting algorithms require robust validation that accounts for temporal sensor body location, individual gait characteristic ...[more]

PMID: 37034681

Similar Datasets

Project description:BackgroundStep counts are increasingly used in public health and clinical research to assess well-being, lifestyle, and health status. However, estimating step counts using commercial activity trackers has several limitations, including a lack of reproducibility, generalizability, and scalability. Smartphones are a potentially promising alternative, but their step-counting algorithms require robust validation that accounts for temporal sensor body location, individual gait characteristics, and heterogeneous health states.ObjectiveOur goal was to evaluate an open-source, step-counting method for smartphones under various measurement conditions against step counts estimated from data collected simultaneously from different body locations ("cross-body" validation), manually ascertained ground truth ("visually assessed" validation), and step counts from a commercial activity tracker (Fitbit Charge 2) in patients with advanced cancer ("commercial wearable" validation).MethodsWe used 8 independent data sets collected in controlled, semicontrolled, and free-living environments with different devices (primarily Android smartphones and wearable accelerometers) carried at typical body locations. A total of 5 data sets (n=103) were used for cross-body validation, 2 data sets (n=107) for visually assessed validation, and 1 data set (n=45) was used for commercial wearable validation. In each scenario, step counts were estimated using a previously published step-counting method for smartphones that uses raw subsecond-level accelerometer data. We calculated the mean bias and limits of agreement (LoA) between step count estimates and validation criteria using Bland-Altman analysis.ResultsIn the cross-body validation data sets, participants performed 751.7 (SD 581.2) steps, and the mean bias was -7.2 (LoA -47.6, 33.3) steps, or -0.5%. In the visually assessed validation data sets, the ground truth step count was 367.4 (SD 359.4) steps, while the mean bias was -0.4 (LoA -75.2, 74.3) steps, or 0.1%. In the commercial wearable validation data set, Fitbit devices indicated mean step counts of 1931.2 (SD 2338.4), while the calculated bias was equal to -67.1 (LoA -603.8, 469.7) steps, or a difference of 3.4%.ConclusionsThis study demonstrates that our open-source, step-counting method for smartphone data provides reliable step counts across sensor locations, measurement scenarios, and populations, including healthy adults and patients with cancer.

Project description:BackgroundAccurate measurement devices are required to objectively quantify physical activity. Wearable activity monitors, such as pedometers, may serve as affordable and feasible instruments for measuring physical activity levels in older adults during their normal activities of daily living. Currently few available accelerometer-based steps counting devices have been shown to be accurate at slow walking speeds, therefore there is still lacking appropriate devices tailored for slow speed ambulation, typical of older adults. This study aimed to assess the validity of step counting using the pedometer function of the ADAMO Care Watch, containing an embedded algorithm for measuring physical activity in older adults.MethodsTwenty older adults aged ≥ 65 years (mean ± SD, 75±7 years; range, 68-91) and 20 young adults (25±5 years, range 20-40), wore a care watch on each wrist and performed a number of randomly ordered tasks: walking at slow, normal and fast self-paced speeds; a Timed Up and Go test (TUG); a step test and ascending/descending stairs. The criterion measure was the actual number of steps observed, counted with a manual tally counter. Absolute percentage error scores, Intraclass Correlation Coefficients (ICC), and Bland-Altman plots were used to assess validity.ResultsADAMO Care Watch demonstrated high validity during slow and normal speeds (range 0.5-1.5 m/s) showing an absolute error from 1.3% to 1.9% in the older adult group and from 0.7% to 2.7% in the young adult group. The percentage error for the 30-metre walking tasks increased with faster pace in both young adult (17%) and older adult groups (6%). In the TUG test, there was less error in the steps recorded for older adults (1.3% to 2.2%) than the young adults (6.6% to 7.2%). For the total sample, the ICCs for the ADAMO Care Watch for the 30-metre walking tasks at each speed and for the TUG test were ranged between 0.931 to 0.985.ConclusionThese findings provide evidence that the ADAMO Care Watch demonstrated highly accurate measurements of the steps count in all activities, particularly walking at normal and slow speeds. Therefore, these data support the inclusion of the ADAMO Care Watch in clinical applications for measuring the number of steps taken by older adults at normal, slow walking speeds.

Dataset Information

Validation of an open-source smartphone step counting algorithm in clinical and non-clinical settings.

Background

Objective

Methods

Results

Conclusions

Publications

Validation of an open-source smartphone step counting algorithm in clinical and non-clinical settings.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets