IP Library › Granted Patent US 12,539,078
Granted Patent B2
US 12,539,078 · App. 17/687,393 · Granted Feb 3, 2026

System and method for personalized biofeedback from a wearable device

Inventor: Rohan Dixit (San francisco, CA)
Assignee: Zenso, Inc.
A61B5/486A61B5/02405A61B5/02438A61B5/7267G16H20/70G16H40/67A61B5/7405A61B5/742A61B5/7455
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 12,539,078
App. No.
17/687,393
Granted
Feb 3, 2026
Kind
B2
Abstract

A method and system for personalized biofeedback from a wearable device that can include collecting a set of biometric inputs comprising at least heart activity data; generating a heart rate variability signal from the heart activity data; determining a feedback treatment plan which is based at least in part by processing of biometric inputs which comprises analyzing the heart rate variability signal; and delivering feedback based on the feedback treatment plan.

Claims (35)

1 . A method for a wearable device comprising:

at a biosensor on the wearable device, collecting a set of biometric inputs of a user comprising at least heart activity data;

generating a heart rate variability signal from the heart activity data;

analyzing the heart rate variability signal and determining a user specific health baseline from the biometric input data by comparing the user biometric input data to general population data;

determining a feedback treatment plan based on the user specific health baseline which comprises outputting a set of parameters of a feedback treatment plan comprising at least a heart rate variability activation threshold for when biofeedback session is initiated and a heart rate variability target threshold used to determine when to end a biofeedback session;

at a feedback system of the wearable device, continuously monitoring the heart rate variability signal throughout the day and automatically delivering real-time feedback based on the feedback treatment plan during multiple biofeedback sessions per day responsive to real-time biometric conditions when the heart rate variability signal is below the heart rate variability activation threshold and ending each biofeedback session conditional on the heart rate variability target threshold, wherein the heart rate variability activation threshold and heart rate variability target threshold parameters are dynamically adjusted based on the user specific health baseline and a real-time analysis of biofeedback session effectiveness as measured by heart rate variability changes during each biofeedback session, thereby customizing providing titration of biofeedback for enhanced application of biofeedback the user.

2 . The method of claim 1 , wherein delivering the feedback comprises delivering biofeedback in a form of feedback selected from the set of haptic, visual, and audio feedback.

3 . The method of claim 2 , wherein determining the feedback treatment plan further comprises processing the biometric inputs as model inputs into a machine learning model, the model contributing to the outputting of at least one parameter of the feedback treatment plan.

4 . The method of claim 3 , wherein the set of parameters of the feedback treatment plan is a timing parameter for duration of a biofeedback session.

5 . The method of claim 1 , wherein delivering feedback comprises activating feedback in synchronization with the heart rate variation signal.

6 . The method of claim 5 , wherein determining a feedback treatment plan based on processing of the biometric inputs can include determining at least one feedback synchronization parameter.

7 . The method of claim 1 , wherein delivering the feedback comprises triggering a digital communication event that includes cognitive behavioral therapy information.

8 . The method of claim 1 , wherein collecting the set of biometric inputs can further include collecting pharmaceutical usage data; wherein determining a feedback treatment plan based on processing of the biometric inputs is additionally based on the pharmaceutical usage data.

9 . The method of claim 8 , further comprising outputting a pharmaceutical usage recommendation.

10 . The method of claim 1 , wherein the heart rate variability activation threshold and heart rate variability target threshold are optionally further modified through a user interface input.

11 . A non-transitory computer-readable medium of a wearable device storing instructions that, when executed by one or more computer processors of a computing platform, cause the computing platform to perform the operations:

collecting a set of biometric inputs comprising at least heart activity data;

generating a heart rate variability signal from the heart activity data;

analyzing the heart rate variability signal and determining a user specific health baseline from the biometric input data by comparing the user biometric input data to general population data;

determining a feedback treatment plan based on the user specific health baseline which comprises outputting a set of parameters of a feedback treatment plan comprising at least a heart rate variability activation threshold for when biofeedback session is initiated and a heart rate variability target threshold used to determine when to end a biofeedback session;

continuously monitoring the heart rate variability signal throughout the day and automatically delivering real-time feedback at a feedback system of the wearable device based on the feedback treatment plan during multiple biofeedback sessions per day responsive to real-time biometric conditions when the heart rate variability signal is below the heart rate variability activation threshold and ending each biofeedback session conditional on the heart rate variability target threshold, wherein the heart rate variability activation threshold and heart rate variability target threshold parameters are dynamically adjusted based on the user specific health baseline and a real-time analysis of biofeedback session effectiveness as measured by heart rate variability changes during each biofeedback session, thereby providing titration of biofeedback for enhanced application of biofeedback the user.

12 . The non-transitory computer-readable medium of claim 11 , wherein delivering the feedback comprises delivering biofeedback in a form of feedback selected from the set of haptic, visual, and audio feedback.

13 . The non-transitory computer-readable medium of claim 12 , wherein delivering feedback comprises activating feedback in synchronization with the heart rate variability signal.

14 . The non-transitory computer-readable medium of claim 12 , wherein collecting the set of biometric inputs can further include collecting pharmaceutical usage data; wherein determining a feedback treatment plan based on processing of the biometric inputs is additionally based on the pharmaceutical usage data; and further comprising outputting a pharmaceutical usage recommendation.

15 . A system comprising of:

a wearable device comprising at least one biosensor and a feedback system;

one or more computer-readable mediums storing instructions that, when executed by the one or more computer processors, cause a computing platform to perform operations comprising:

collecting a set of biometric inputs from the at least one biosensor comprising at least heart activity data;

generating a heart rate variability signal from the heart activity data;

analyzing the heart rate variability signal and determining a user specific health baseline from the biometric input data by comparing the user biometric input data to general population data;

determining a feedback treatment plan based on the user specific health baseline outputting a set of parameters of a feedback treatment plan comprising at least a heart rate variability activation threshold for when biofeedback session is initiated and a heart rate variability target threshold used to determine when to end a biofeedback session;

continuously monitoring the heart rate variability signal throughout the day and automatically delivering real-time feedback to the feedback system based on the feedback treatment plan during multiple biofeedback sessions per day responsive to real-time biometric conditions when the heart rate variability signal is below the heart rate variability activation threshold and ending each biofeedback session conditional on the heart rate variability target threshold, wherein the heart rate variability activation threshold and heart rate variability target threshold parameters are dynamically adjusted based on the user specific health baseline and a real-time analysis of biofeedback session effectiveness as measured by heart rate variability changes during each biofeedback session, thereby providing titration of biofeedback for enhanced application of biofeedback the user.

16 . The system of claim 15 , wherein delivering feedback comprises activating biofeedback in synchronization with the heart rate variation signal.

17 . The system of claim 15 , wherein collecting the set of biometric inputs can further include collecting pharmaceutical usage data; wherein determining a feedback treatment plan based on processing of the biometric inputs is additionally based on the pharmaceutical usage data; and further comprising outputting a pharmaceutical usage recommendation.

18 . The system of claim 15 , wherein the heart rate variability activation threshold and heart rate variability target threshold are optionally further modified through a user interface input.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 3, 2025
From: DIXIT, ROHAN
To: ZENSO, INC.
Reel/Frame 072762/0253 →
Continuity (2)
Provisional Application 63156575 · Mar 4, 2021
Related Publication 20220280105A1 · Sep 8, 2022
References Cited (29)
US 6168563B1 · Brown · 2001 [cited by applicant]
US 6270455B1 · Brown · 2001 [cited by applicant]
US 6840904B2 · Goldberg · 2005 [cited by applicant]
US 7565132B2 · Ayed · 2009 [cited by applicant]
US 9699528B2 · Dixit · 2017 [cited by applicant]
US 10284924B2 · Dixit · 2019 [cited by applicant]
US 10735831B2 · Dixit · 2020 [cited by applicant]
US 20080035147A1 · Kirby et al. · 2008 [cited by applicant]
US 20100079264A1 · Hoellwarth · 2010 [cited by applicant]
US 20100169111A1 · Brue et al. · 2010 [cited by applicant]
US 20110015468A1 · Aarts et al. · 2011 [cited by applicant]
US 20120203076A1 · Fatta et al. · 2012 [cited by applicant]
US 20140039914A1 · Dansereau et al. · 2014 [cited by applicant]
US 20140073486A1 · Ahmed · 2014 [cited by examiner]
US 20140081666A1 · Teller et al. · 2014 [cited by applicant]
US 20150199010A1 · Coleman et al. · 2015 [cited by applicant]
US 20150342518A1 · Persidsky · 2015 [cited by examiner]
US 20150370994A1 · Madan et al. · 2015 [cited by applicant]
US 20160234572A1 · Dixit · 2016 [cited by examiner]
US 20160367157A1 · Blake · 2016 [cited by examiner]
US 20170300648A1 · Charlap · 2017 [cited by applicant]
US 20180096738A1 · Moturu et al. · 2018 [cited by applicant]
US 20190109830A1 · McFarland et al. · 2019 [cited by applicant]
US 20190254590A1 · Venkatraman · 2019 [cited by examiner]
US 20190336077A1 · Kuhn et al. · 2019 [cited by applicant]
US 20200389711A1 · Dixit · 2020 [cited by applicant]
US 20210177318A1 · Lintereur · 2021 [cited by examiner]
US 20220256255A1 · Dixit · 2022 [cited by applicant]
IN 201941034439A · 2019 [cited by applicant]