Heart Rate Estimation Through Autocorrelation from Single Axis Accelerometer of Smartphone

Area of Science:

• Biomedical Engineering
• Mobile Health Technology
• Cardiovascular Monitoring

Background:

• Smartphones are increasingly used for health monitoring due to their widespread adoption.
• Accurate heart rate (HR) monitoring is crucial for diagnosing and managing cardiac conditions.

Purpose of the Study:

• To develop and evaluate an autocorrelation-based technique for predicting heart rate from single-axis accelerometer data on mobile phones.
• To assess the accuracy of this method in individuals with Sinus Rhythm (SR) and Atrial Fibrillation (AF).

Main Methods:

• Utilized mobile phone accelerometer data and applied Butterworth and Bessel filters for signal preprocessing.
• Developed an autocorrelation-based algorithm to extract the cardiac signal and calculate HR.
• Validated the technique using simultaneous accelerometer and ECG data from 300 individuals (SR and AF).

Main Results:

• The method achieved a Mean Absolute Error (MAE) of 4.54 Beats Per Minute (BPM) for subjects in Sinus Rhythm, meeting clinical accuracy standards.
• A higher MAE of 15.7 BPM was observed in subjects with Atrial Fibrillation, indicating lower accuracy in arrhythmic populations.

Conclusions:

• The proposed mobile phone-based technique shows promise for accurate heart rate prediction in individuals with normal heart rhythms.
• Further research and refinement are necessary to improve the accuracy of this method for patients with cardiac arrhythmias like Atrial Fibrillation.