Dataset Information

Contact-Free Screening of Atrial Fibrillation by a Smartphone Using Facial Pulsatile Photoplethysmographic Signals.

ABSTRACT:

Background

We aimed to evaluate a novel method of atrial fibrillation (AF) screening using an iPhone camera to detect and analyze photoplethysmographic signals from the face without physical contact by extracting subtle beat-to-beat variations of skin color that reflect the cardiac pulsatile signal.

Methods and results

Patients admitted to the cardiology ward of the hospital for clinical reasons were recruited. Simultaneous facial and fingertip photoplethysmographic measurements were obtained from 217 hospital inpatients (mean age, 70.3±13.9 years; 71.4% men) facing the front camera and with an index finger covering the back camera of 2 independent iPhones before a 12-lead ECG was recorded. Backdrop and background light intensity was monitored during signal acquisition. Three successive 20-second (total, 60 seconds) recordings were acquired per patient and analyzed for heart rate regularity by Cardiio Rhythm (Cardiio Inc, Cambridge, MA) smartphone application. Pulse irregularity in ?1 photoplethysmographic readings or 3 uninterpretable photoplethysmographic readings were considered a positive AF screening result. AF was present on 12-lead ECG in 34.6% (n=75/217) patients. The Cardiio Rhythm facial photoplethysmographic application demonstrated high sensitivity (95%; 95% confidence interval, 87%-98%) and specificity (96%; 95% confidence interval, 91%-98%) in discriminating AF from sinus rhythm compared with 12-lead ECG. The positive and negative predictive values were 92% (95% confidence interval, 84%-96%) and 97% (95% confidence interval, 93%-99%), respectively.

Conclusions

Detection of a facial photoplethysmographic signal to determine pulse irregularity attributable to AF is feasible. The Cardiio Rhythm smartphone application showed high sensitivity and specificity, with low negative likelihood ratio for AF from facial photoplethysmographic signals. The convenience of a contact-free approach is attractive for community screening and has the potential to be useful for distant AF screening.

SUBMITTER: Yan BP

PROVIDER: S-EPMC6015414 | biostudies-literature | 2018 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Contact-Free Screening of Atrial Fibrillation by a Smartphone Using Facial Pulsatile Photoplethysmographic Signals.

Yan Bryan P BP Lai William H S WHS Chan Christy K Y CKY Chan Stephen Chun-Hin SC Chan Lok-Hei LH Lam Ka-Ming KM Lau Ho-Wang HW Ng Chak-Ming CM Tai Lok-Yin LY Yip Kin-Wai KW To Olivia T L OTL Freedman Ben B Poh Yukkee C YC Poh Ming-Zher MZ

Journal of the American Heart Association 20180405 8

<h4>Background</h4>We aimed to evaluate a novel method of atrial fibrillation (AF) screening using an iPhone camera to detect and analyze photoplethysmographic signals from the face without physical contact by extracting subtle beat-to-beat variations of skin color that reflect the cardiac pulsatile signal.<h4>Methods and results</h4>Patients admitted to the cardiology ward of the hospital for clinical reasons were recruited. Simultaneous facial and fingertip photoplethysmographic measurements w ...[more]

PMID: 29622592

Similar Datasets

Project description:ObjectiveTo assess whether atrial fibrillation (AF) self-screening stations in general practice waiting rooms improve AF screening, diagnosis, and stroke risk management.Design, settingIntervention study (planned duration: twelve weeks) in six New South Wales general practices (two in rural locations, four in greater metropolitan Sydney), undertaken during 28 August 2020 - 5 August 2021.ParticipantsPeople aged 65 years or more who had not previously been diagnosed with AF, and had appointments for face-to-face GP consultations. People with valvular AF were excluded.InterventionAF self-screening station and software, integrated with practice electronic medical record programs, that identified and invited participation by eligible patients, and exported single-lead electrocardiograms and automated evaluations to patients' medical records.Main outcome measuresScreening rate; incidence of newly diagnosed AF during intervention and pre-intervention periods; prescribing of guideline-recommended anticoagulant medications.ResultsAcross the six participating practices, 2835 of 7849 eligible patients (36.1%) had face-to-face GP appointments during the intervention period, of whom 1127 completed AF self-screening (39.8%; range by practice: 12-74%). AF was diagnosed in 49 screened patients (4.3%), 44 of whom (90%) had CHA2 DS2 -VA scores of 2 or more (high stroke risk). The incidence of newly diagnosed AF during the pre-intervention period was 11 cases per 1000 eligible patients; during the intervention period, it was 22 per 1000 eligible patients (screen-detected: 17 per 1000 eligible patients; otherwise detected: 4.6 per 1000 eligible patients). Prescribing of oral anticoagulation therapy for people newly diagnosed with AF and high stroke risk was similar during the pre-intervention (20 of 24, 83%) and intervention periods (46 of 54, 85%).ConclusionsAF self-screening in general practice waiting rooms is a feasible approach to increasing AF screening and diagnosis rates by reducing time barriers to screening by GPs. AF self-screening could reduce the number of AF-related strokes.Trial registrationAustralian New Zealand Clinical Trials Registry ACTRN12620000233921 (prospective).

Dataset Information

Contact-Free Screening of Atrial Fibrillation by a Smartphone Using Facial Pulsatile Photoplethysmographic Signals.

Background

Methods and results

Conclusions

Publications

Contact-Free Screening of Atrial Fibrillation by a Smartphone Using Facial Pulsatile Photoplethysmographic Signals.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets