US 12,251,229 B2
Computing device for detecting heart rhythm disorders
Théophile Mohr Durdez, Marseilles (FR)
Assigned to SUBSTRATE HD, Marseilles (FR)
Appl. No. 17/044,126
Filed by SUBSTRATE HD, Marseilles (FR)
PCT Filed Mar. 26, 2019, PCT No. PCT/FR2019/050682
§ 371(c)(1), (2) Date Sep. 30, 2020,
PCT Pub. No. WO2019/186050, PCT Pub. Date Oct. 3, 2019.
Claims priority of application No. 1852850 (FR), filed on Mar. 30, 2018.
Prior Publication US 2021/0121118 A1, Apr. 29, 2021
Int. Cl. A61B 5/361 (2021.01); A61B 5/00 (2006.01); G06F 18/21 (2023.01); G06N 20/00 (2019.01); G16H 50/20 (2018.01)
CPC A61B 5/361 (2021.01) [A61B 5/7267 (2013.01); A61B 5/746 (2013.01); G06F 18/2185 (2023.01); G06N 20/00 (2019.01); G16H 50/20 (2018.01)] 6 Claims
OG exemplary drawing
 
1. A device for detecting heart rhythm disorders, wherein the device comprises:
a memory storing data defining a first classification model for detecting heart rhythm disorders and a second classification model for detecting heart rhythm disorders, the first classification model for detecting heart rhythm disorders being derived from a first processing, by machine learning, of data associated with cardiac electrograms having a first duration, and the second classification model for detecting heart rhythm disorders being derived from a second processing, by machine learning, of data associated with cardiac electrograms having a second duration, the first duration being less than the second duration;
wherein the device has stored thereon:
a classifier program including instructions for analyzing cardiac electrogram data based on the first and second classification models, and for returning a classification value; and
a driver program including instructions for:
storing in the memory cardiac electrogram data received as input,
aggregating the received cardiac electrogram data according to the first and second durations,
analyzing the data aggregated according to the first and second durations with the classifier program on the basis of the first and second classification models respectively, and
returning alert data when the analysis by the classifier program on the basis of the first classification model returns a classification value associated with a heart rhythm disorder;
wherein the device further comprises at least one processor configured for executing the classifier program and the driver program;
wherein the second duration is an integer multiple of the first duration, and wherein the driver program further includes instructions for applying the second classification model for detecting heart rhythm disorders such that the classification value for electrogram data having the second duration corresponds to a linear combination of the classification values obtained by cutting the electrogram data having the second duration into a plurality of sub-groups of electrogram data having the first duration and by applying the first classification model for detecting heart rhythm disorders to each of these sub-groups of electrogram data; and
wherein the driver program further includes instructions for computing a weighted average of the classification values obtained by applying the first classification model for detecting heart rhythm disorders to each of the sub-groups of electrogram data.