ID: 4122070 Performance of Novel Machine Learning Software: Automating QTc Measurement and AAD Dosing in a Prospective Cohort
Atrial fibrillation (AF) is the most common arrhythmia worldwide. Rhythm control strategies such as antiarrhythmic drugs (AADs) have been shown to reduce mortality. Some AADs require three-day hospitalization to assess QTc intervals for the potential of dangerous arrhythmias associated with QT prolongation. To streamline AAD loading and increase patient access, a novel software application was designed using a machine learning (ML) algorithm (SafeBeat Rx, San Francisco, CA) to evaluate QTc from mobile ECG (mECG) and recommend personalized AAD doses.
Authors
- M. Cho
- Alejandro Marcos Alvarez
- William B. McHugh
- Basanta Sharma Paudel (ORCID: https://orcid.org/0000-0002-7490-7989)
- Rachita Navara (ORCID: https://orcid.org/0000-0002-6183-4258)
- R. DeLeon
- I. Montgomery
- Azeem Rathore (ORCID: https://orcid.org/0000-0001-8195-3935)
- Gonzalo Pavez
- Kalpesh Patel (ORCID: https://orcid.org/0000-0002-1092-6857)
- Maria Dopierała (ORCID: https://orcid.org/0009-0003-7265-4994)
- Riya Ravuri
- Esha Ananth
- Aditi Pallod
- R. Venkateswaran
- Dekai Chen
- S. Sheth
- J. Higgins
Publication Details
- Journal
- Heart Rhythm
- Published
- 2024-09-01
- DOI
- https://doi.org/10.1016/j.hrthm.2024.07.063
- Primary Topic
- ECG Monitoring and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00