What is the clinical evidence from this study?

Study design: Observational. Population: Patients undergoing cardiac stress testing (n=50). Intervention: Smartphone-derived physical activity data model vs. Observed peak METs from cardiac stress test. Primary outcome: Explained variability in observed peak METs (R-squared 0.68, 95% CI 46%, 81%).

July 21, 2021Open Access

Smartphone-recorded physical activity for estimating cardiorespiratory fitness

Key Result

A multivariable regression model incorporating smartphone-derived physical activity data, age, and body mass index explained 68% of the variability in observed peak METs.

Study Design

Type

Observational (n=50)

Multicenter

Structured PICO

Does smartphone-derived physical activity data accurately estimate cardiorespiratory fitness in older adults undergoing cardiac stress testing?

Population

50 older adults (median age 67, 38% female) undergoing diagnostic workup or risk stratification for coronary heart disease or other heart diseases at a single center, who owned an iPhone 5S or above or Apple Watch.

Intervention

Estimation of cardiorespiratory fitness using multivariable regression models incorporating smartphone-derived physical activity data (specifically root mean square of the successive differences of daily distance averaged over 365 days), age, and body mass index.

Outcome

Cardiorespiratory fitness measured as peak metabolic equivalents of task (METs) achieved on a maximal treadmill stress test.surrogate

Smartphone-derived physical activity data, combined with age and BMI, can accurately estimate cardiorespiratory fitness in older adults, offering a potential point-of-care tool for risk stratification.

Main Result

Effect estimate: R-squared 0.68 (95% CI 46%, 81%)

Limitations

Small sample of patients at risk for heart disease
Restriction to a single manufacturer (Apple Inc.)
Unable to include physical activity when not carrying an iPhone
Used a stress treadmill estimation of fitness (METs) rather than VO2max

Abstract

While cardiorespiratory fitness is strongly associated with mortality and diverse outcomes, routine measurement is limited. We used smartphone-derived physical activity data to estimate fitness among 50 older adults. We recruited iPhone owners undergoing cardiac stress testing and collected recent iPhone physical activity data. Cardiorespiratory fitness was measured as peak metabolic equivalents of task (METs) achieved on cardiac stress test. We then estimated peak METs using multivariable regression models incorporating iPhone physical activity data, and validated with bootstrapping. Individual smartphone variables most significantly correlated with peak METs (p-values both < 0.001) included daily peak gait speed averaged over the preceding 30 days (r = 0.63) and root mean square of the successive differences of daily distance averaged over 365 days (r = 0.57). The best-performing multivariable regression model included the latter variable, as well as age and body mass index. This model explained 68% of variability in observed METs (95% CI 46%, 81%), and estimated peak METs with a bootstrapped mean absolute error of 1.28 METs (95% CI 0.98, 1.60). Our model using smartphone physical activity estimated cardiorespiratory fitness with high performance. Our results suggest larger, independent samples might yield estimates accurate and precise for risk stratification and disease prognostication.

Bookmark

View Full Paper