New Smartphone App Can Detect Dangerous Heart Condition

There’s no denying that smartphone technology is getting smarter with each passing day. Several mobile app development companies are developing high performance, feature-packed software applications to run on smartphone devices.

Now, Finnish scientists edged their way a little further into healthcare with the development of a new smartphone apps that can be used to detect a dangerous heart condition, called Atrial fibrillation,with existing hardware.

Abbreviated as AF or A-fib, Atrial fibrillation is a common type of abnormal and often rapid heart rate which leads to a stroke, blood clots, heart failure and other heart-related complications.

The newly developed and tested smartphone app is a simple and non-invasive method to detect atrial fibrillation accurately, scientists at the University of Turku in Finland have noted. The low-cost app uses the smartphone’s own accelerometer and gyroscope to diagnose atrial fibrillation, they said.

“Atrial fibrillation is a dangerous medical condition present in 2 percent of the global population and accounting for up to seven million strokes per year,” said lead author Tero Koivistoa, vice-director of the Technology Research Centre (TRC), University of Turku, Finland.

In order to test the potential of their smartphone app to detect atrial fibrillation without any add-on hardware, the researchers included 16 patients with atrial fibrillation from the Turku Heart Center and 20 recordings from healthy volunteers (control group) to validate the developed algorithm.

To detect atrial fibrillation, a smartphone was placed on the chests of the patients, and accelerometer and gyroscope recordings were taken. The captured data was then uploaded to a desktop where a machine learning algorithm looks for the presence of atrial fibrillation.

“We use the accelerometer and gyroscope of the smartphone to acquire a heart signal from the patient. A measurement recording is taken, and the acquired data is pre-processed by signal processing methods,” said Koivisto.

“Multiple features such as autocorrelation and spectral entropy are then extracted from the pre-processed data. Finally, a machine learning algorithm (KSVM) is used to determine if the patient suffers from atrial fibrillation,” he explained.

The app using recordings from the smartphone had 98.5 percent sensitivity and 95.2 percent specificity for the arrhythmia or abnormal rhythm of the heartbeat, which often does not show initial symptoms and is difficult to detect by visiting a doctor.

“This is a low cost, non-invasive way to detect atrial fibrillation that people can do themselves without any help from medical staff,” Koivisto concluded.

Koivisto and colleagues reported their findings at the European Society of Cardiology meeting in Rome, Italy.