Logo

American Heart Association

  80
  0


Final ID: MDP1536

AI-Based ECG Denoising Improves Smartwatch ECG Interpretation

Abstract Body (Do not enter title and authors here): Background/Aim: Smartwatch ECGs (SW-ECG) have emerged as a noninvasive solution to assess abnormal heart rhythms such as atrial fibrillation (AF). However, SW-ECGs recorded in free-living settings are often noisy and yield Inconclusive results from automated AF detection algorithms. We developed a deep learning model to denoise single-lead ECGs and reduce the number of inconclusive tracings that require manual overread.

Methods: Using the MIMIC-III waveform database (N=2,988 patients, 10.1% AF), we created pairs of clean (high signal quality index based on dynamic beat template matching) 30-sec, single-lead ECGs and their noisy counterparts by injecting various combinations of noise including baseline wander, electrode motion and synthetic noise of different colors. The noisy ECGs served as the input to a 1D U-Net that was trained to reconstruct the corresponding clean ECG (AI-ECG-Denoise). We evaluated the performance of an offline automated ECG classifier before and after applying AI-ECG-Denoise on a held-out test set from MIMIC-III (N=34 patients, 52.9% AF) comprising 1,000 single-lead ECGs that we injected with noise at different signal-to-noise ratios (SNRs), and an external test set of 701 free-living SW-ECGs from 115 healthy consented study subjects using a prototype watch.

Results: In the MIMIC-III test set, AI-ECG-Denoise significantly reduced the number of Inconclusive ECG results across noisy ECGs with SNRs ranging from -10 to 30 dB with no significant difference in sensitivity and specificity for AF down to an SNR of 3 dB. In the external wrist-worn test set, AI-ECG-Denoise significantly reduced the number of Inconclusive free-living SW-ECG Interpretations (p<0.001) by 33.3% [95% CI: 25.1, 39.9], recategorizing the majority as Normal, with no significant difference in specificity per McNemar’s test (99.2% [98.4, 99.8] before and 98.8% [97.8, 99.6] after denoising).

Conclusion: A deep learning model for ECG denoising decreased the number of Inconclusive results in the detection of AF from SW-ECGs. This could help reduce user anxiety and limit the overreading time spent by the physicians.
  • Liao, Shun  ( Google , Mountain View , California , United States )
  • Di Achille, Paolo  ( Google , Mountain View , California , United States )
  • Vakharia, Tanay  ( Google , Mountain View , California , United States )
  • Faranesh, Tony  ( Google , Mountain View , California , United States )
  • Shreibati, Jacqueline  ( Google , Mountain View , California , United States )
  • Poh, Ming-zher  ( Google , Mountain View , California , United States )
  • Author Disclosures:
    Shun Liao: No Answer | Paolo Di Achille: DO have relevant financial relationships ; Employee:Google:Active (exists now) | Tanay Vakharia: No Answer | Tony Faranesh: No Answer | Jacqueline Shreibati: DO have relevant financial relationships ; Advisor:Toku :Past (completed) | Ming-Zher Poh: DO have relevant financial relationships ; Employee:Google:Active (exists now)
Meeting Info:

Scientific Sessions 2024

2024

Chicago, Illinois

Session Info:

Out of Office: Health Technology in the Community

Monday, 11/18/2024 , 12:50PM - 02:05PM

Moderated Digital Poster Session

More abstracts on this topic:
A large-scale multi-view deep learning-based assessment of left ventricular ejection fraction in echocardiography

Jing Linyuan, Metser Gil, Mawson Thomas, Tat Emily, Jiang Nona, Duffy Eamon, Hahn Rebecca, Homma Shunichi, Haggerty Christopher, Poterucha Timothy, Elias Pierre, Long Aaron, Vanmaanen David, Rocha Daniel, Hartzel Dustin, Kelsey Christopher, Ruhl Jeffrey, Beecy Ashley, Elnabawi Youssef

A RETROSPECTIVE EVALUATION OF RESOURCE UTILIZATION AND OUTCOMES IN PATIENTS USING MOBILE ECG DEVICES FOLLOWING ABLATION FOR ATRIAL FIBRILLATION

Fairman Alix, Loh Alexander, Druml Lauren, Triplett Cynthia, Liu Taylor, Pursnani Seema

More abstracts from these authors:
AI-Enabled Photoplethysmography Can Help Detect Elevated Blood Pressure And Predict Near-Term Incidence Of Hypertension

Di Achille Paolo, Su Hao-wei, Ko Ho, Taylor James, Shreibati Jacqueline, Thompson Matthew, Poh Ming-zher

Mental Health & Heart Health Innovation: Connecting the Dots, Seeing the Gaps

Shreibati Jacqueline, Jones Bell Megan

You have to be authorized to contact abstract author. Please, Login
Not Available