US 11,720,817 B2
Waveform annotator
Raajen Patel, Houston, TX (US); Alexander Csicsery-Ronay, Taos, NM (US); and Vincent Gagne, Taos, NM (US)
Assigned to Medical Informatics Corp., Houston, TX (US)
Filed by Medical Informatics Corp., Houston, TX (US)
Filed on Jul. 1, 2019, as Appl. No. 16/459,297.
Prior Publication US 2021/0004710 A1, Jan. 7, 2021
Int. Cl. A61B 5/00 (2006.01); G06N 20/00 (2019.01); G16H 15/00 (2018.01); G16H 50/20 (2018.01); G16H 30/40 (2018.01); G16H 10/60 (2018.01); A61B 5/339 (2021.01); A61B 5/349 (2021.01)
CPC G06N 20/00 (2019.01) [A61B 5/339 (2021.01); A61B 5/349 (2021.01); A61B 5/7435 (2013.01); G16H 10/60 (2018.01); G16H 15/00 (2018.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01)] 20 Claims
OG exemplary drawing
 
1. A method of annotating physiological waveform data, comprising:
analyzing a physiological data waveform corresponding to a first type of physiological data, based on a model corresponding to the first type of physiological data;
generating a first annotation automatically corresponding to the physiological data waveform based on the model, wherein the first annotation corresponds to a repeating feature of the physiological data waveform;
sending the physiological data waveform to a user display device;
sending the first annotation to the user display device for display on the physiological data waveform with the corresponding repeating feature of the physiological data waveform;
receiving a modification to the first annotation, wherein the modification repositions the first annotation on the physiological data waveform;
creating a second annotation based on the modification;
saving the second annotation in an annotation database; and
training the model using machine learning based on the second annotation and the physiological data waveform, generating a trained model.