Resting and Postexercise Heart Rate Detection From Fingertip and Facial Photoplethysmography Using a Smartphone Camera: A Validation Study

Abstract

Background: Modern smartphones allow measurement of heart rate (HR) by detecting pulsatile photoplethysmographic (PPG) signals with built-in cameras from the fingertips or the face, without physical contact, by extracting subtle beat-to-beat variations of skin color.

Objective: The objective of our study was to evaluate the accuracy of HR measurements at rest and after exercise using a smartphone-based PPG detection app.

Methods: A total of 40 healthy participants (20 men; mean age 24.7, SD 5.2 years; von Luschan skin color range 14-27) underwent treadmill exercise using the Bruce protocol. We recorded simultaneous PPG signals for each participant by having them (1) facing the front camera and (2) placing their index fingertip over an iPhone's back camera. We analyzed the PPG signals from the Cardiio-Heart Rate Monitor + 7 Minute Workout (Cardiio) smartphone app for HR measurements compared with a continuous 12-lead electrocardiogram (ECG) as the reference. Recordings of 20 seconds' duration each were acquired at rest, and immediately after moderate- (50%-70% maximum HR) and vigorous- (70%-85% maximum HR) intensity exercise, and repeated successively until return to resting HR. We used Bland-Altman plots to examine agreement between ECG and PPG-estimated HR. The accuracy criterion was root mean square error (RMSE) ≤5 beats/min or ≤10%, whichever was greater, according to the American National Standards Institute/Association for the Advancement of Medical Instrumentation EC-13 standard.

Results: We analyzed a total of 631 fingertip and 626 facial PPG measurements. Fingertip PPG-estimated HRs were strongly correlated with resting ECG HR (r=.997, RMSE=1.03 beats/min or 1.40%), postmoderate-intensity exercise (r=.994, RMSE=2.15 beats/min or 2.53%), and postvigorous-intensity exercise HR (r=.995, RMSE=2.01 beats/min or 1.93%). The correlation of facial PPG-estimated HR was stronger with resting ECG HR (r=.997, RMSE=1.02 beats/min or 1.44%) than with postmoderate-intensity exercise (r=.982, RMSE=3.68 beats/min or 4.11%) or with postvigorous-intensity exercise (r=.980, RMSE=3.84 beats/min or 3.73%). Bland-Altman plots showed better agreement between ECG and fingertip PPG-estimated HR than between ECG and facial PPG-estimated HR.

Conclusions: We found that HR detection by the Cardiio smartphone app was accurate at rest and after moderate- and vigorous-intensity exercise in a healthy young adult sample. Contact-free facial PPG detection is more convenient but is less accurate than finger PPG due to body motion after exercise.

Keywords: heart rate; mobile apps; mobile phone; photoplethysmography; smartphone.

Figure 1

(A) Cardiio smartphone app. (B) Setup to acquire photoplethysmographic (PPG) signals from the participant's face. (C) Obtaining PPG signals from the fingertip. (D) Example of a report produced by the Cardiio smartphone app.

Figure 2

Scatter plots comparing measurements of heart rate (HR) estimated from the Cardiio smartphone phone app photoplethysmographic (PPG) signals and from a reference electrocardiogram (ECG). P<.001 for all correlations. (A) Resting estimated HR from fingertip PPG signals. (B) Resting estimated HR from facial PPG signals. (C) Postexercise HR from fingertip PPG signals. (D) Postexercise HR from facial PPG signals.

Figure 3

Bland-Altman plots of limits of agreement in resting heart rate (HR) estimated from the Cardiio smartphone app and a reference electrocardiogram (ECG). (A) Resting estimated HR from fingertip PPG signals. (B) Resting estimated HR from facial PPG signals. (C) Postexercise HR from fingertip PPG signals. (D) Postexercise HR from facial PPG signals.