Smartwatch Detection of Heart Rhythm Issues
Author Information
Author(s): Han Dong, Moon Jihye, Díaz Luís Roberto Mercado, Chen Darren, Williams Devan, Mohagheghian Fahimeh, Ghetia Om, Peitzsch Andrew G., Kong Youngsun, Nishita Nishat, Ghutadaria Ohm, Orwig Taylor A., Otabil Edith Mensah, Noorishirazi Kamran, Hamel Alexander, Dickson Emily L., DiMezza Danielle, Lessard Darleen, Wang Ziyue, Mehawej Jordy, Filippaios Andreas, Naeem Syed, Gottbrecht Matthew F., Fitzgibbons Timothy P., Saczynski Jane S., Barton Bruce, Ding Eric Y., Tran Khanh-Van, McManus David D., Chon Ki H.
Hypothesis
Can a multimodal smartwatch approach improve the detection of atrial fibrillation and other arrhythmias in real-life settings?
Conclusion
The proposed model achieved high sensitivity for detecting PAC/PVC and maintained excellent accuracy for AF detection.
Supporting Evidence
- The model achieved 83% sensitivity for PAC/PVC detection.
- The model maintained a high accuracy of 97.31% for AF detection.
- It was 14 times more efficient and 2.7 times faster than previous models.
- The model outperformed the best state-of-the-art model by 20.81% for PAC/PVC sensitivity.
Takeaway
This study shows that smartwatches can help doctors find heart problems by using special sensors to monitor your heart over time.
Methodology
The study used a 1D bi-directional Gated Recurrent Unit deep learning model on multimodal data collected from smartwatches.
Limitations
The study may be limited by the specific populations and settings from which the data were collected.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website