US 11,990,239 B2
System and method for analyzing noise in electrophysiology studies
Adrian Francis Warner, Delafield, WI (US); Daniel Richard Schneidewend, Menomonee Falls, WI (US); and Mark Kohls, Delafield, WI (US)
Assigned to GE PRECISION HEALTHCARE LLC, Wauwatosa, WI (US)
Filed by GE Precision Healthcare LLC, Wauwatosa, WI (US)
Filed on Jul. 12, 2019, as Appl. No. 16/509,782.
Prior Publication US 2021/0012895 A1, Jan. 14, 2021
Int. Cl. G16H 50/20 (2018.01); G06N 3/08 (2023.01)
CPC G16H 50/20 (2018.01) [G06N 3/08 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A system for analyzing noise in one or more electrophysiology studies, the system comprising:
at least one processor; and,
at least one memory device that stores an application that adapts the at least one processor to:
acquire one or more entire electrophysiology study signals in real time from one or more electrophysiology patients via one or more sensors operative to sense electrical activity produced by a patient, the one or more entire electrophysiology study signal being a waveform in a range of about 0 Hz to about 200 Hz and including a cardiac component and an electromagnetic noise component;
isolate a region of interest within an entire electrophysiology study signal, the region of interest corresponding to a portion between R-waves of the entire electrophysiology study signal, the region of interest representing the electromagnetic noise component substantially without the cardiac component;
pass the region of interest to an input layer of a machine learning model trained from a set of known noise fingerprints representative of sources of electromagnetic noise;
identify a source of electromagnetic noise in the entire electrophysiology study signal based on the trained machine learning model; and
transmit a noise source indicator corresponding to the source of electromagnetic noise.