IP Library Granted Patent US 12,633,415
Granted Patent B2
US 12,633,415 · App. 17/540,186 · Granted May 19, 2026

Pre-emptive asthma risk notifications based on medicament device monitoring

Inventors: Meredith A. Barrett (Redwood City, CA); Mike Lohmeier (Sun Prairie, WI); Shannon M. Hamilton (Berkeley, CA); Michael J. Tuffli (Kentfield, CA); Dmitry Stupakov (Cupertino, CA); Christopher Hogg (San Francisco, CA); John David Van Sickle (Oregon, WI)
Assignee: ResMed Inc.
G16H50/30G16H10/65G16H20/13G16H40/63
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 12,633,415
App. No.
17/540,186
Granted
May 19, 2026
Kind
B2
Abstract

This description provides asthma risk notifications in advance of predicted rescue usage events in order to help effect behavior changes in a patient to prevent those events from occurring. Rescue medication events, changes in environmental conditions, and other contextually relevant information are detected by sensors associated with the patient's medicament device/s and are collected from other sources, respectively, to provide a basis to determine a patient's risk score. This data is analyzed to determine the severity of the patient's risk for an asthma event and is used to send notifications accordingly.

Claims (53)

1 . A method comprising:

accessing a set of historical rescue inhaler usage events for a patient, wherein a historical rescue inhaler usage event is recorded when a rescue inhaler unit dispenses a rescue medication to the patient;

implementing a medicament device sensor attached to a rescue inhaler unit sensor configured to:

monitor medicament usage of the rescue inhaler unit;

record the set of historical rescue inhaler usage events; and

establish a network connection with a client device, and transmit locally stored rescue event data to the client device such that the sensor and client device are paired using a passkey;

in response to accessing the set of historical rescue inhaler usage events:

generating a push notification comprising a query to a client device associated with the patient;

assigning a label representing a known risk score to each historical rescue inhaler usage event of the accessed set;

determining a patient-specific baseline risk threshold for the patient based on a subset of the accessed set of historical rescue inhaler usage events that occurred within a period of time preceding a current day, wherein the patient-specific baseline risk threshold is determined based on a value representing a percentage of the subset of the rescue inhaler usage events;

creating a training dataset comprising:

the accessed set of historical rescue inhaler usage events, the label assigned to each historical rescue inhaler usage event;

provider data including aggregated rescue medication event data, wherein the provider data is deidentified to protect privacy, and the patient-specific baseline risk threshold;

training a machine-learned model to determine the risk score using the training dataset, wherein the machine-learned model is trained to determine the risk score based on a set of input values and the patient-specific baseline risk threshold, wherein the machine-learned model is trained based on an iterative functional gradient descent algorithm,

wherein the algorithm optimizes a cost function by iteratively selecting parameters to minimize an error identified by the cost function; and

in response to the risk score, updating a treatment regimen by altering a dosage of: antibiotics, corticosteroids, beclomethasone, budesonide, and

fluticasone salmeterol or formoterol.

2 . The method of claim 1 , further comprising:

responsive to a triggering condition, accessing a set of parameter values for a model for predicting asthma risk;

accessing a set of input values for the current day, the set of input values comprising at least one historical patient parameter, at least one environment condition parameter, and at least one current patient parameter; and

inputting the set of parameter values, the set of input values, and the patient-specific baseline risk threshold into the machine-learned model to determine the risk score for the current day.

3 . The method of claim 1 , wherein the machine-learned model is further trained to:

determine an expected count of rescue usage events for the current day based on the set of input values; and

determine the risk score based on a comparison of the expected count of rescue usage.

4 . The method of claim 1 , wherein each parameter value of the set of parameter values is determined using a boosted gradient model.

5 . The method of claim 1 , wherein the risk score is a numerical value representing a likelihood that the patient will experience a number of rescue usage events on the current day exceeding the patient-specific baseline risk threshold.

6 . The method of claim 1 , wherein the patient-specific baseline risk threshold is periodically determined based on a prior period including events from a window of time preceding the current day.

7 . A non-transitory computer readable storage medium storing instructions encoded thereon, that, when executed by a processor cause the processor to:

access a set of historical rescue inhaler usage events for a patient, wherein a historical rescue inhaler usage event is recorded when a rescue inhaler unit dispenses a rescue medication to the patient;

implement a medicament device sensor attached to a rescue inhaler unit configured to:

monitor medicament usage of the rescue inhaler unit;

record the set of historical rescue inhaler usage events; and

establish a network connection with a client device, and transmit locally stored rescue event data to the client device such that the sensor and client device are paired using a passkey;

in response to accessing the set of historical rescue inhaler usage events, generate a push notification comprising a query to a client device associated with the patient;

assign a label representing a known risk score to each historical rescue inhaler usage event of the accessed set;

determine a patient-specific baseline risk threshold for the patient based on a subset of the accessed set of historical rescue inhaler usage events that occurred within a period of time preceding a current day, wherein the patient-specific baseline risk threshold is determined based on a value representing a percentage of the subset of the rescue inhaler usage events;

create a training dataset comprising the accessed set of historical rescue inhaler usage events, the label assigned to each historical rescue inhaler usage event, provider data including aggregated rescue medication event data, wherein the provider data is deidentified to protect privacy, and the patient-specific baseline risk threshold;

train a machine-learned model to determine the risk score using the training dataset, wherein the machine-learned model is trained to determine the risk score based on a set of input values and the patient-specific baseline risk threshold, wherein the machine-learned model is trained based on an iterative functional gradient descent algorithm, wherein the algorithm optimizes a cost function by iteratively selecting a plurality of parameters to minimize an error identified by the cost function; and

in response to the risk score, update a treatment regimen by altering a dosage of:

antibiotics, corticosteroids, beclomethasone, budesonide, and fluticasone salmeterol or formoterol.

8 . The non-transitory computer readable storage medium of claim 7 further comprising instructions that cause the processor to:

responsive to a triggering condition, access a set of parameter values for a model for predicting asthma risk;

access a set of input values for the current day, the set of input values comprising at least one historical patient parameter, at least one environment condition parameter, and

at least one current patient parameter; and

input the set of parameter values, the set of input values, and the patient-specific baseline risk threshold into the machine-learned model to determine the risk score for the current day.

9 . The non-transitory computer readable storage medium of claim 7 , wherein the machine-learned model is further trained to:

determine an expected count of rescue usage events for the current day based on the set of input values; and

determine the risk score based on a comparison of the expected count of rescue usage.

10 . The non-transitory computer readable storage medium of claim 7 , wherein each parameter value of the set of parameter values is determined using a boosted gradient model.

11 . The non-transitory computer readable storage medium of claim 7 , wherein the risk score is a numerical value representing a likelihood that the patient will experience a number of rescue usage events on the current day exceeding the patient-specific baseline risk threshold.

12 . The method of claim 1 , wherein the treatment regimen further comprises:

restricting geographic areas with adverse atmospheric conditions and air pollution or scheduling an appointment with a health care provider.

13 . The method of claim 1 , wherein the medicament device sensor comprises a clock for recording the time and date of events.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 16, 2025
From: RECIPROCAL LABS CORPORATION
To: RESMED INC.
Reel/Frame 072887/0709 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 24, 2022
From: BARRETT, MEREDITH A.; LOHMEIER, MIKE; HAMILTON, SHANNON M.; TUFFLI, MICHAEL J.; STUPAKOV, DMITRY; HOGG, CHRISTOPHER; VAN SICKLE, JOHN DAVID
To: RECIPROCAL LABS CORPORATION (D/B/A PROPELLER HEALTH)
Reel/Frame 059393/0684 →
Continuity (2)
Continuation 15724968 · Oct 4, 2017
Related Publication 20220093262A1 · Mar 24, 2022
References Cited (35)
US 8807131B1 · Tunnell et al. · 2014 [cited by applicant]
US 12171740B2 · Azouz · 2024 [cited by examiner]
US 20030214409A1 · Hickle · 2003 [cited by applicant]
US 20080249983A1 · Meisels et al. · 2008 [cited by applicant]
US 20080300497A1 · Krause et al. · 2008 [cited by applicant]
US 20110184250A1 · Schmidt et al. · 2011 [cited by applicant]
US 20120010867A1 · Eder · 2012 [cited by applicant]
US 20120266251A1 · Birtwhistle et al. · 2012 [cited by applicant]
US 20130282295A1 · White et al. · 2013 [cited by applicant]
US 20140006314A1 · Yu et al. · 2014 [cited by applicant]
US 20140142456A1 · Fischer et al. · 2014 [cited by applicant]
US 20140334264A1 · Thaker · 2014 [cited by applicant]
US 20160314256A1 · Su et al. · 2016 [cited by applicant]
US 20170109493A1 · Hogg · 2017 [cited by examiner]
US 20170238850A1 · Gonzales et al. · 2017 [cited by applicant]
US 20180158552A1 · Liu et al. · 2018 [cited by applicant]
US 20190180379A1 · Nayak et al. · 2019 [cited by applicant]
US 20200058403A1 · Barrett · 2020 [cited by examiner]
US 20200194125A1 · Adolphus · 2020 [cited by examiner]
US 20220115107A1 · Gondalia · 2022 [cited by examiner]
US 20220319660A1 · Belanger-Basset · 2022 [cited by examiner]
US 20220375623A1 · Hirons · 2022 [cited by examiner]
US 20220405619A1 · Ramamurthy · 2022 [cited by examiner]
US 20240153608A1 · Ma · 2024 [cited by examiner]
JP 2009532072A · 2009 [cited by applicant]
JP 2015219617A · 2015 [cited by applicant]
WO WO2016172614A1 · 2016 [cited by applicant]
European Patent Office, Extended European Search Report and Opinion, EP Patent Application No. 18864689.7, Jun. 7, 2021, ten pages. [cited by applicant]
Frey, U. et al., “Complexity of Chronic Asthma and Chronic Obstructive Pulmonary Disease: Implications for Risk Assessment, and Disease Progression and Control,” The Lancet, vol. 372, No. 9643, Sep. 20, 2008, pp. 1088-1… [cited by applicant]
PCT International Search Report and Written Opinion, PCT Application No. PCT/US2018/048909, Nov. 2, 2018, 13 pages. [cited by applicant]
Silkoff, P.E. et al., “The Aerocrine exhaled nitric oxide monitoring system NIOX is cleared by the US Food and Drug Administration for monitoring therapy in asthma,” 2004, pp. 1241-1256. [cited by applicant]
United States Office Action, U.S. Appl. No. 15/724,968, filed Aug. 31, 2020, 14 pages. [cited by applicant]
United States Office Action, U.S. Appl. No. 15/724,968, filed Apr. 1, 2020, 25 pages. [cited by applicant]
United States Office Action, U.S. Appl. No. 15/724,968, filed Aug. 20, 2019, 16 pages. [cited by applicant]
Japan Patent Office, Office Action, Japanese Patent Application No. 2020-541336, Mar. 28, 2022, four pages. [cited by applicant]