eduzhai > Applied Sciences > Engineering >

Digital biomarkers and artificial intelligence for mass diagnosis of atrial fibrillation in a population sample at risk of sleep disordered breathing

  • king
  • (0) Download
  • 20210505
  • Save

... pages left unread,continue reading

Document pages: 35 pages

Abstract: Atrial fibrillation (AF) is the most prevalent arrhythmia and is associatedwith a five-fold increase in stroke risk. Many individuals with AF goundetected. These individuals are often asymptomatic. There are ongoing debateson whether mass screening for AF is to be recommended. However, there isincentive in performing screening for specific at risk groups such asindividuals suspected of sleep-disordered breathing where an importantassociation between AF and obstructive sleep apnea (OSA) has been demonstrated.We introduce a new methodology leveraging digital biomarkers and recentadvances in artificial intelligence (AI) for the purpose of mass AF diagnosis.We demonstrate the value of such methodology in a large population sample atrisk of sleep disordered breathing. Four databases, totaling n=3,088 patientsand p=26,913 hours of ECG raw data were used. Three of the databases (n=125,p=2,513) were used for training a machine learning model in recognizing AFevents from beat-to-beat interval time series. The visit 1 of the sleep hearthealth study database (SHHS1, n=2,963, p=24,400) consists of overnightpolysomnographic (PSG) recordings, and was considered as the test set. InSHHS1, expert inspection identified a total of 70 patients with a prominent AFrhythm. Model prediction on the SHHS1 showed an overallSe=0.97,Sp=0.99,NPV=0.99,PPV=0.67 in classifying individuals with or withoutprominent AF. PPV was non-inferior (p=0.03) for individuals with anapnea-hypopnea index (AHI) > 15 versus AHI < 15. Over 22 of correctlyidentified prominent AF rhythm cases were not documented as AF in the SHHS1.Individuals with prominent AF can be automatically diagnosed from an overnightsingle channel ECG recording, with an accuracy unaffected by the presence ofOSA. AF detection from overnight ECG recording revealed a large proportion ofundiagnosed AF and may enhance the phenotyping of OSA.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...