patent.fyi
Applications  /  US 2026/0354769
United States Patent Application Publication

US 2026/0354769 A1

Published
Nov 12, 2026
Filed
Jan 27, 2026
Earliest date on the face
Jan 27, 2025
Classification
A61B 5/7275
First published here
Nov 19, 2026

Generated automatically. Not reviewed by a person. Not legal advice or an opinion.

Section 1 · machine-generated

What if?

Questions about how individual parts of claim 1 might be changed. A question may describe something different from what the claim language recites, or a version of it; no view is offered on which.

1.1Contactless radar monitoring

What ifWhat if room-mounted radar units recorded cardiac activity and movement without a body-worn monitor?
Claim language“a physiological monitor worn by a user”

A wall-mounted frequency-modulated radar tracks gross movement from changes in target range and velocity. During still intervals, a processor extracts heartbeat timing from small chest displacements in the radar phase signal.

1.3Single wearable age adjustment

What ifWhat if all wearable metrics produced one joint age adjustment?
Claim language“a first plurality of age adjustments”

A regression model combines resting heart rate, exercise heart rate recovery, sleep duration, and daily step count into one mortality risk estimate. The processor matches that estimate to a reference age on a five-year mortality curve and subtracts chronological age to obtain one adjustment.

1.4Waist circumference measurement

What ifWhat if the body-size measurement consisted of waist circumference in centimeters?
Claim language“a body mass index of the user”

A nonstretch tape measures circumference midway between the lowest palpable rib and the top of the hip bone at the end of a normal exhalation. The processor uses the measured circumference as an input to the health-data age calculation.

1.5Single health age adjustment

What ifWhat if the health measurements produced one adjustment from a joint risk estimate?
Claim language“a second plurality of age adjustments”

A survival model takes chronological age, body mass index, and maximal oxygen consumption as inputs and returns one five-year mortality probability. The processor finds the age with the same probability on a reference curve and subtracts chronological age to obtain one health-data adjustment.

1.6Direct risk-to-age lookup

What ifWhat if the system read effective age directly from a reference mortality curve?
Claim language“adjusting the chronological age of the user”

A fitted model converts the wearable metrics and health measurements into a single five-year mortality probability. The processor interpolates between adjacent ages on a reference curve to find the age associated with that probability.

Section 2 · machine-generated

Variations

Further arrangements of the same subject matter, described here as of the publication date at the foot of this page.

Other field of use

Effective age for endurance horse conditioning

A girth-mounted electrocardiogram recorder and inertial sensor collect cardiac activity and movement during stall rest and scheduled training. Software derives resting heart rate from quiet standing, exercise recovery from post-session heart rate, recumbent sleep time from posture and cardiac patterns, and movement intensity from acceleration. Stable records supply chronological age and body mass index expressed as mass divided by squared withers height, and a treadmill test supplies maximal oxygen consumption. An equine cohort model maps both metric groups to age offsets using all-cause mortality records, and the software adds the offsets to chronological age.

Component substitution

Chest electrodes for cardiac activity sensing

A chest strap uses two dry electrodes to acquire a single-lead electrocardiogram in place of an optical pulse sensor. The strap records the electrocardiogram at 250 samples per second and three-axis acceleration at 50 samples per second on a shared clock. Software detects ventricular peaks, rejects intervals with poor electrode contact, and derives waking resting heart rate and exercise recovery from the accepted beats. The processor derives sleep and movement metrics from the synchronized signals and combines their age adjustments with those calculated from recorded health measurements.

Parameter or scale variation

Separate windows for daily and exercise metrics

A wearable stores cardiac and motion data in 24-hour blocks, and a processor recalculates effective age every seven days. The processor takes the median of daily resting heart rate, sleep fragmentation, and movement intensity values from a trailing 28-day window. It calculates exercise recovery from the median 60-second heart rate drop across qualifying sessions in a trailing 56-day window. Reference tables calibrated using the same windows convert the metrics into age adjustments, which the processor adds to chronological age along with the body mass index and maximal oxygen consumption adjustments.

Combination with existing systems

Integration with a cardiac rehabilitation system

A cardiac rehabilitation system sends scheduled session times and recorded exercise stop times to a service that receives timestamped cardiac and motion data from a wearable. The service uses the stop times to calculate session-specific heart rate recovery and uses out-of-session data to calculate resting heart rate, sleep fragmentation, and daily movement intensity. The rehabilitation record supplies chronological age, body mass index, and maximal oxygen consumption from a supervised exercise test. The service calculates both groups of age adjustments and writes the effective age, input dates, and contribution values back to the rehabilitation record.

Automated or data-driven variant

Joint estimation of metric age adjustments

A training pipeline links wearable metrics and health measurements to follow-up time and all-cause mortality outcomes in a reference cohort. It fits a regularized survival model with chronological age as the time axis and both metric groups as simultaneous predictors. For each input, the processor divides its centered log-hazard contribution by the local slope of the reference log hazard with respect to age to obtain an adjustment in years. The processor adds the adjustments to chronological age and stores each contribution with the model version.

Automatic signal quality gating for age updates

A wearable transmits cardiac and movement samples with timestamps and sensor contact flags. Software scores one-minute blocks using contact status, cardiac waveform quality, and accelerometer clipping, then excludes failed blocks from the metrics that depend on those signals. An update runs when each wearable metric has enough valid data for its observation window and the body mass index and maximal oxygen consumption records meet configured freshness limits. Otherwise, the service retains the last effective age and records which input failed its update criterion.

Specific version of a part

Gait from pressure measurements

A floor mat with a grid of pressure sensors registers the position and time of each footfall during a walking assessment. A processor calculates stride length from the spacing between successive contacts of the same foot.

Wrist optical and motion sensing

A wrist monitor samples a reflective optical pulse sensor at 64 Hz and a three-axis accelerometer at 32 Hz. A microcontroller time-stamps both streams against the same clock and transfers them over a short-range radio link.

One-minute heart rate recovery

The processor takes the median heart rate over the final 15 seconds of a marked exercise interval. It subtracts the median heart rate measured from 55 to 65 seconds after exercise ends and records the difference in beats per minute.

Treadmill oxygen uptake measurement

A flow sensor and gas analyzers measure breath-by-breath oxygen uptake during a graded treadmill test. A processor records the highest 30-second average in milliliters of oxygen per kilogram per minute when oxygen uptake plateaus despite increasing workload.

Summed signed age adjustments

The processor stores each adjustment as a signed number of years and adds the wearable and health-data adjustments to chronological age. It retains the unrounded total for later calculations and rounds the displayed effective age to one decimal place.

Section 3 · quoted from USPTO records

Other work

Passages reproduced word for word from two earlier-published U.S. patent documents, placed beside the language of claim 1. No characterization is offered. Each passage is marked A or B for the document it comes from; ¶ numbers are the paragraph numbers in the USPTO’s published full text of that document.

Document AUS 2015/0087929 A1
Published
Mar 26, 2015
Filed
Sep 22, 2014
Class
A61B 5/7278
Document BUS 12,053,288 B2
Published
Aug 6, 2024
Filed
Apr 20, 2023
Class
A61B 5/377
Claim 1
Document A
Document B
1.1acquiring data from a physiological monitor worn by a user, the data including cardiac activity data for the user and movement data for the user;
In some embodiments, the at least one complete data user combination of self-reported and measured data comprises raw data streams, demographic and biometric parameters, and metrics computed from the raw data and demographic and biometric parameters. In some embodiments, the raw data streams comprise time-stamped series of heart-rate data, motion, and velocity data.
A · US 2015/0087929 A1 · ¶ 19
In some aspects, the data acquisition device 101 can be worn by the subject 108 to collect data from the one or more physiological sensors 104.
B · US 12,053,288 B2 · ¶ 45
1.2calculating a plurality of metrics for the user based on the data from the physiological monitor, the plurality of metrics including at least: a resting heart rate for the user based on the cardiac activity data; an exercise metric for the user based on the cardiac activity data recorded during an exercise activity, a sleep metric derived from the data for the user, and a movement metric for the user derived from the movement data for the user;
In some embodiments, the metrics computed from the raw data and demographic and biometric parameters comprise average speed, fastest speed, and total distance traveled each week.
A · US 2015/0087929 A1 · ¶ 19
The instructions also include generating, using the physiological measures and from the demographic data, segmented training-data that specifies a plurality of epochs of time and data for the subject in each epoch. The instructions also include generating, using the segmented training-data, sleep-structure features for the subject.
B · US 12,053,288 B2 · ¶ 10
1.3calculating a first plurality of age adjustments based on the plurality of metrics;
A predefined number of most important features contributing to brain age excess are shown to the user, each feature in terms of one or more of the following: directionality and strength of contribution to brain age excess, mean feature value, normative distribution of the specific feature adjusted by age, gender, or other potentially confounding factors (e.g., sociodemographic, physiological).
B · US 12,053,288 B2 · ¶ 124
1.4acquiring a plurality of health data measurements for the user including at least: a chronological age of the user, a body mass index of the user, and a maximal oxygen consumption for the user;
The system takes advantage of the availability of specific data streams, biometric and demographic parameters, and maximal aerobic capacity values measured over a large population of users to estimate maximal aerobic capacity values for users that are missing one or more key data points.
A · US 2015/0087929 A1 · ¶ 26
The instructions also include receiving demographic data for the subject, the demographic data may include a chronological age for the subject when the physiological measures were recorded.
B · US 12,053,288 B2 · ¶ 10
1.5calculating a second plurality of age adjustments based on the plurality of health data measurements; and
1.6calculating an effective age of the user by adjusting the chronological age of the user according to each of the first plurality of age adjustments and each of the second plurality of age adjustments.

An empty cell means only that no passage was reproduced there.

Statements in these documents
Current solutions to determine a person's brain age use structural and functional MRI scans or laboratory-based polysomnographic (PSG) recordings, which are costly, inappropriate as a large-scale screening tool, and inappropriate for continuous monitoring over multiple nights.
B · US 12,053,288 B2 · ¶ 6
However, sensory (e.g., auditory) stimulation during sleep is often applied at times that do not correctly correspond to the aimed sleeping patterns of a subject, such as the positive SO peak.
B · US 12,053,288 B2 · ¶ 8
Cite aspatent.fyi, US 2026/0354769 A1, claim 1, first published 2026-11-19T03:31:31-05:00, https://patent.fyi/US20260354769/, SHA-256 2e4168aae1d4f74c2c3e5167eab5d83d93b534753a292f9e7e6a0a18d04d0ed4
First published
Permanent addresshttps://patent.fyi/US20260354769/
Content fingerprint (SHA-256)2e4168aae1d4f74c2c3e5167eab5d83d93b534753a292f9e7e6a0a18d04d0ed4
Methodv2026-11-18.2 · automated, not reviewed by a person
Correctionscorrections@patent.fyi