Atrial Fibrillation Detection via Accelerometer and Gyroscope of a Smartphone

Abstract

We present a smartphone-only solution for the detection of atrial fibrillation (AFib), which utilizes the built-in accelerometer and gyroscope sensors [inertial measurement unit, (IMU)] in the detection. Depending on the patient's situation, it is possible to use the developed smartphone application either regularly or occasionally for making a measurement of the subject. The smartphone is placed on the chest of the patient who is adviced to lay down and perform a noninvasive recording, while no external sensors are needed. After that, the application determines whether the patient suffers from AFib or not. The presented method has high potential to detect paroxysmal ("silent") AFib from large masses. In this paper, we present the preprocessing, feature extraction, feature analysis, and classification results of the envisioned AFib detection system based on clinical data acquired with a standard mobile phone equipped with Google Android OS. Test data was gathered from 16 AFib patients (validated against ECG), as well as a control group of 23 healthy individuals with no diagnosed heart diseases. We obtained an accuracy of 97.4% in AFib versus healthy classification (a sensitivity of 93.8% and a specificity of 100%). Due to the wide availability of smart devices/sensors with embedded IMU, the proposed methods could potentially also scale to other domains such as embedded body-sensor networks.

Newer technologies for detection of atrial fibrillation

“…The patient is advised to lie down in a supine position, and the smartphone is placed on the patient’s chest to detect atrial fibrillation by measuring the regularity of cardiac mechanical activity. The device was reported to have a sensitivity of 94% and a specificity of 100% for detection of atrial fibrillation compared with simultaneous electrocardiography in this study 121. A larger case-control study, which included 150 consecutive patients in atrial fibrillation and 150 age and sex matched patients in sinus rhythm, reported the sensitivity and specificity of this device for detection of atrial fibrillation to be 95% (95% confidence interval 91% to 98%) and 96% (92% to 99%), respectively, compared with simultaneous five lead telemetry electrocardiographic recording interpreted by two cardiologists 122…”

Recent Advances in Seismocardiography

“…Simple time domain [47,61,81,82,107] Statistical time domain [41,56,65,106] Simple frequency domain [41,56] Statistical frequency domain [40,41,47,78] 2.4. Machine Learning…”

Atrial Fibrillation Detection From Face Videos by Fusing Subtle Variations

“…For each ROI, we record the mean RGB values of pixels inside it and further eliminate the noises by a moving-average filter on the nearest 15 points. Then, we employ three various (6,7,11,12) pulse extraction methods [12]- [14] to acquire the videoextracted pulse rhythms. An ideal example of the final pulse rhythm signals can be seen in Fig.…”

“…However, the acquisition of ECG signals requires specific biomedical equipment, which limits the application of monitoring AF risk in daily life. Recently, many researchers [9]- [11] have tried to capture the cardiac pulse signal with the wearable device and smart phone for predicting AF. Nevertheless, the measurement needs to be conducted in a skin-contact manner that is inconvenience and uncomfortable for the examinee.…”