Performance of Noncontact Video-Based Detection of Pulse Rate and Atrial Fibrillation on the iOS Platform

We developed a video-based monitoring technology to detect atrial fibrillation and pulse rate without the need for a patient to adopt a dedicated wearable device. It is a low-cost, software-only solution running on smart devices. The technology minimises requirements for patient compliance with recording procedures since it passively monitors patients while they use their personal device for other purposes. In the past, we reported results for Android based devices (tablets and smartphones). In this work, we investigate performance of an implementation of the technology on the iOS platform using a personal iPhone X smartphone device. Our analysis is based on a clinical validation study involving 22 patients diagnosed with paroxysmal and persistent Atrial Fibrillation. Results demonstrate very high accuracy in estimating pulse rate (97% of estimated pulse rate values have no more than 5 BPM deviation from reference heart rate), as well as specificity and sensitivity of 0.88 and 0.80 respectively in detection of atrial fibrillation.