Patent Application: Model for Detecting Atrial Fibrillation and Sleep Apnea

ChangeBridge: Patent Apps - Health Informatics (G16H)

Published September 23rd, 2025

Detected March 26th, 2026

Summary

The USPTO has published a patent application (US20260088174A1) for a method of establishing a model to detect atrial fibrillation and sleep apnea using machine learning. The application details a process involving training electrocardiograms, feature extraction, and symptom labeling.

View original document View source feed page

What changed

This document is a published patent application from the USPTO detailing a novel method for detecting atrial fibrillation (AF) and sleep apnea (SA) using a machine learning model. The proposed method involves processing electrocardiogram data, extracting relevant features, and training a model based on labeled segments indicating the presence of AF and SA symptoms. The application, filed by inventors Che-Wei LIN, FEBRYAN SETIAWAN, and Cheng-Yu LIN, outlines a computer-implemented system for this process.

While patent applications are not regulatory rules, they can indicate emerging technologies and future compliance considerations in the healthcare and technology sectors. Compliance officers should be aware that such patented technologies could eventually lead to new medical devices or diagnostic tools that may be subject to future FDA or other regulatory oversight. No immediate compliance actions are required based on this patent application, but it highlights advancements in AI-driven health diagnostics.

Source document (simplified)

← USPTO Patent Applications

METHOD OF ESTABLISHING MODEL AND METHOD FOR DETECTING ATRIAL FIBRILLATION AND SLEEP APNEA

Application US20260088174A1 Kind: A1 Mar 26, 2026

Inventors

Che-Wei LIN, FEBRYAN SETIAWAN, Cheng-Yu LIN

Abstract

A method of establishing a model for detecting atrial fibrillation (AF) and sleep apnea (SA) is implemented by a computer system that stores training electrocardiograms, and includes steps of: dividing the training electrocardiograms into training segments, each of which contains a common length of time of recorded electrical activity of a heart; for each of the training segments, labeling the training segment with a symptom indicator that indicates whether the training segment is related to AF and whether the training segment is related to SA; for each of the training segments, performing feature extraction on the training segment to obtain an entry of feature data; and establishing the model by using a machine learning algorithm based on the entries of feature data and the symptom indicators.