IP Library › Granted Patent US 12,525,359
Granted Patent B2
US 12,525,359 · App. 18/212,496 · Granted Jan 13, 2026

Systems and methods for clustering physiological events

Inventors: Abhijit Rajan (Shoreview, MN); David L. Perschbacher (Blaine, MN); Deepa Mahajan (North Oaks, MN)
Assignee: Cardiac Pacemakers, Inc.
G16H50/30A61B5/7282A61B5/742A61B5/7475G16H15/00G16H40/20G16H40/67
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,525,359
App. No.
18/212,496
Granted
Jan 13, 2026
Kind
B2
Abstract

Systems and methods for managing physiological events generated by a medical device in a patient are discussed. An exemplary system includes a controller circuit to receive information about a plurality of physiological events detected by a medical device in a patient, generate for each of the physiological events a respective feature set using the received information, and cluster the physiological events into different event groups using values of temporal or morphological features of the generated feature sets. The event groups each include a respective set of physiological events. The controller circuit can identify from at least one event group a representative event representing the physiological events of that event group, and output to a user or a process the representative event and an indication that the representative event has been determined and represents the set of physiological events in the even group.

Claims (64)

1 . A system for managing a plurality of physiological events detected by a medical device in a patient, the system comprising:

a controller circuit, configured to:

receive information about the plurality of physiological events;

for each of the plurality of physiological events, generate a respective feature set using the received information, the feature set including temporal or morphological features with respective values;

cluster the plurality of physiological events into different event groups using the values of the temporal or morphological features of the generated feature sets, the different event groups each including a respective set of physiological events;

determine, from at least one of the different event groups, a representative event representing the set of physiological events in the at least one event group; and

output to a user or a process of the system the representative event and an indication that the representative event has been determined and represents the set of physiological events in the at least one event group, including:

initiating an automatic display of information about the determined representative event and hiding information about the set of physiological events other than the determined representative event of the at least one event group from displaying automatically on a user interface; and

in response to a user command via the user interface, initiating an on-demand display of information about one or more of the set of physiological events, other than the determined representative event, of the at least one event group.

2 . The system of claim 1 , wherein the user command includes a user selection of a physiological event from the set of physiological events of the at least one event group, and wherein the controller circuit is configured to display information about the selected physiological event on the user interface in response to the user selection.

3 . The system of claim 1 , comprising a user interface configured to receive an adjudication of the representative event from a user,

wherein the controller circuit is configured to assign the received adjudication of the representative event to each of the set of physiological events of the at least one event group.

4 . The system of claim 1 , wherein the controller circuit is configured to prioritize storage of information about the determined representative event over storage of information about the set of physiological events of the at least one event group in a storage device.

5 . The system of claim 1 , wherein the controller circuit is configured to prioritize transmission of information about the determined representative event over transmission of information about the set of physiological events of the at least one event group between different devices.

6 . The system of claim 1 , wherein the plurality of physiological events include cardiac arrhythmia episodes detected from the patient, and the generated respective feature set includes at least one of:

a heart rate distribution feature;

an arrhythmia duration;

a morphology feature; or

time of day the plurality of physiological events were detected.

7 . The system of claim 1 , wherein to determine the representative event, the controller circuit is configured to:

determine a centroid of the set of physiological events of the at least one event group in a feature space using feature sets generated respectively from at least a portion of the set of physiological events; and

determine the representative event of the at least one event group as a physiological event closest to the determined centroid.

8 . The system of claim 1 , wherein to cluster the plurality of physiological events, the controller circuit is configured to:

initialize a cluster center using a feature set of one of the plurality of physiological events;

iteratively update the cluster center using a central tendency of feature sets respectively generated from physiological events in an event group until a convergence criterion or an iteration stopping criterion is met; and

assign a physiological event to a clustered event group based on a similarity metric between the physiological event and the iteratively updated cluster center.

9 . The system of claim 1 , wherein the controller circuit is configured to:

compute respective similarity metrics between each of the received plurality of physiological events and a user-specified physiological event using feature sets generated respectively from the received plurality of physiological events and the user-specified physiological event;

determine the set of physiological events of the at least one event group with the respective similarity metrics exceeding a similarity threshold; and

determine the user-specified physiological event as the representative event of the least one event group.

10 . The system of claim 9 , comprising a user interface configured to:

display the received plurality of physiological events in a graphical representation of a feature space;

receive a user input to identify the user-specified physiological event, and a user input of the similarity threshold or a user selection of a pre-determined cluster density; and

display information of the user-specified physiological event and an indication that the representative event represents the set of physiological events in the at least one event group.

11 . The system of claim 9 , wherein the controller circuit is configured to:

generate an estimate of amount of workload reduction, or an estimate of error rate, associated with assigning a user adjudication of the representative event to each of the set of physiological events of the at least one event group; and

determine or adjust the similarity threshold based on the generated estimate of amount of workload reduction or the generated estimate of error rate.

12 . A method for managing a plurality of physiological events detected by a medical device in a patient, the method comprising:

receiving information about the plurality of physiological events;

for each of the plurality of physiological events, generating a respective feature set using the received information;

clustering the plurality of physiological events into different event groups using the generated feature sets of the plurality of physiological events, the different event groups each including a respective set of physiological events;

determining, from at least one of the different event groups, a representative event representing the set of physiological events in the at least one event group; and

outputting to a user or a process the representative event and an indication that the representative event has been determined and represents the set of physiological events in the at least one event group, including:

initiating an automatic display of information about the determined representative event and hiding information about the set of physiological events other than the determined representative event of the at least one event group from displaying automatically on a user interface; and

in response to a user command via the user interface, initiating an on-demand display of information about one or more of the set of physiological events, other than the determined representative event, of the at least one event group.

13 . The method of claim 12 , comprising:

receiving an adjudication of the representative event from a user via the user interface; and

automatically assigning the received adjudication of the representative event to each of the set of physiological events of the at least one event group.

14 . The method of claim 12 , comprising prioritizing storage or transmission of information about the determined representative event over storage or transmission of information about the set of physiological events of the at least one event group.

15 . The method of claim 12 , wherein clustering the plurality of physiological events into different event groups includes:

initializing a cluster center using a feature set of one of the plurality of physiological events;

iteratively updating the cluster center using a central tendency of feature sets respectively generated from physiological events in an event group until a convergence criterion or an iteration stopping criterion is met; and

assigning a physiological event to a clustered event group based on a similarity metric between the physiological event and the iteratively updated cluster center.

16 . The method of claim 12 , wherein clustering the plurality of physiological events into different event groups includes:

computing respective similarity metrics between each of the received plurality of physiological events and a user-specified physiological event using feature sets generated respectively from the received plurality of physiological events and the user-specified physiological event;

determining the set of physiological events of the at least one event group with the respective similarity metrics exceeding a similarity threshold; and

identifying the user-specified physiological event as the representative event of the least one event group.

17 . The method of claim 16 , comprising, via a user interface:

displaying the received plurality of physiological events in a graphical representation of a feature space;

receiving the user-specified physiological event, and a user input of the similarity threshold or a user selection of a pre-determined cluster density; and

displaying information of the user-specified physiological event and an indication that the representative event represents the set of physiological events in the at least one event group.

18 . The method of claim 16 , comprising:

generating an estimate of amount of workload reduction, or an estimate of error rate, associated with assigning a user adjudication of the representative event to each of the set of physiological events of the at least one event group; and

determining or adjusting the similarity threshold based on the generated estimate of amount of workload reduction or the generated estimate of error rate.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 21, 2023
From: RAJAN, ABHIJIT; PERSCHBACHER, DAVID L.; MAHAJAN, DEEPA
To: CARDIAC PACEMAKERS, INC.
Reel/Frame 064017/0817 →
Continuity (2)
Provisional Application 63359333 · Jul 8, 2022
Related Publication 20240013924A1 · Jan 11, 2024
References Cited (40)
US 7941208B2 · Sauer · 2011 [cited by examiner]
US 9533165B1 · Gunderson · 2017 [cited by examiner]
US 10123741B2 · Wang · 2018 [cited by examiner]
US 10368769B2 · Cao · 2019 [cited by examiner]
US 10548535B2 · Zhang · 2020 [cited by examiner]
US 11089958B2 · Brisben · 2021 [cited by examiner]
US 11806543B2 · Mahajan · 2023 [cited by examiner]
US 11980472B2 · Gill · 2024 [cited by examiner]
US 12033753B2 · Ghosh · 2024 [cited by examiner]
US 12123654B2 · Poltorak · 2024 [cited by examiner]
US 12213792B2 · Perschbacher · 2025 [cited by examiner]
US 12251201B2 · Poltorak · 2025 [cited by examiner]
US 20050256413A1 · Astrom et al. · 2005 [cited by applicant]
US 20080125824A1 · Sauer · 2008 [cited by examiner]
US 20110112597A1 · Snell · 2011 [cited by examiner]
US 20140228714A1 · Chau et al. · 2014 [cited by applicant]
US 20140236026A1 · Zhang · 2014 [cited by examiner]
US 20140236029A1 · Averina · 2014 [cited by examiner]
US 20150342466A1 · Thakur · 2015 [cited by examiner]
US 20170027462A1 · Mahajan · 2017 [cited by examiner]
US 20170231505A1 · Mahajan · 2017 [cited by examiner]
US 20170290550A1 · Perschbacher · 2017 [cited by examiner]
US 20180028086A1 · Cao · 2018 [cited by examiner]
US 20180310892A1 · Perschbacher · 2018 [cited by examiner]
US 20180315285A1 · Janssen · 2018 [cited by examiner]
US 20190008384A1 · Brisben · 2019 [cited by examiner]
US 20190231207A1 · Perschbacher · 2019 [cited by examiner]
US 20190232067A1 · Mahajan · 2019 [cited by examiner]
US 20200016420A1 · Mahajan · 2020 [cited by examiner]
US 20200357493A1 · Kelly · 2020 [cited by examiner]
US 20210045640A1 · Poltorak · 2021 [cited by examiner]
US 20220280095A1 · Perschbacher · 2022 [cited by examiner]
US 20240017081A1 · Mahajan · 2024 [cited by examiner]
CN 119546369A · 2025 [cited by applicant]
JP 2025522902A · 2025 [cited by applicant]
WO WO2024010690A1 · 2024 [cited by applicant]
“International Application Serial No. PCT/US2023/025844, International Preliminary Report on Patentability mailed Jan. 23, 2025”, 9 pgs. [cited by applicant]
“International Application Serial No. PCT/US2023/025844, International Search Report mailed Sep. 29, 2023”, 4 pgs. [cited by applicant]
“International Application Serial No. PCT/US2023/025844, Written Opinion mailed Sep. 29, 2023”, 7 pgs. [cited by applicant]
“Japanese Application Serial No. 2025-500250, Voluntary Amendment filed Jan. 17, 2025”, w/ English claims, 7 pgs. [cited by applicant]
Cited By (1)
US 12,694,967