patent.fyi
Applications  /  US 2026/0354745
United States Patent Application Publication

US 2026/0354745 A1

Published
Nov 12, 2026
Filed
Nov 22, 2023
Earliest date on the face
Nov 22, 2022
Classification
A61B 5/441
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.

1.1Room conditions as inputs

What ifWhat if the method acquires room temperature and humidity readings and uses them to estimate skin dryness under those conditions?
Claim language“acquiring mind-body data”

A wall-mounted sensor logs air temperature and relative humidity every five minutes. A lookup table built from controlled exposure measurements maps the two-hour average readings to an expected change in skin hydration for a reference population.

1.2Skin heat balance calculation

What ifWhat if the method calculates skin surface temperature from a heat balance using fixed physical parameters and measured room conditions?
Claim language“a correlation between the mind-body data and the skin condition”

A solver sets the conductive heat flow from deeper tissue equal to convective and radiative heat loss at a covered skin site with negligible evaporation. It uses a fixed deep-tissue reference temperature, a specified thermal resistance for the covering, and measured air and radiant temperatures to solve for skin surface temperature.

1.2Body water as input

What ifWhat if the model uses extracellular water fraction?
Claim language“heart rate and blood pressure related variables”

A multifrequency impedance instrument measures the electrical response through four skin electrodes and calculates the ratio of extracellular water to total body water. A regression model uses that ratio to estimate lower-leg skin thickness associated with edema, with ultrasound measurements as the training target.

1.2Glucose exposure as input

What ifWhat if the model uses glycated hemoglobin?
Claim language“lipid metabolism related variables”

A laboratory assay reports glycated hemoglobin as a percentage of total hemoglobin. A regression model fitted to paired blood and forearm measurements maps that percentage to an estimated skin autofluorescence reading at a fixed excitation wavelength.

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

Coat and skin assessment in dairy herds

A herd monitoring application links each animal's age, body condition score, and blood electrolyte concentrations to its ear tag identifier. Training records pair these inputs with technician scores for skin flaking and coat thinning at defined body sites. At each herd check, the model uses the latest inputs to estimate the two scores for each site and stores the results with the animal's record.

Component substitution

Nearest neighbors for skin hydration estimation

A distance-weighted k-nearest-neighbor regressor replaces a fitted linear regression model for estimating forearm skin hydration. The reference table pairs age, body fat percentage, and fasting glucose with forearm hydration readings from a capacitance probe. The estimator scales each input by its reference-table standard deviation, selects the 15 closest records by Euclidean distance, and averages their hydration readings with weights inversely proportional to distance plus a small positive constant.

Parameter or scale variation

Weekly estimates from daily body measurements

A home monitor records body mass once each morning and pulse intervals during a five-minute seated session. Every seven days, software computes median body mass and median daily heart rate variability over the latest 14 calendar days, with at least 10 recorded days required. A model trained on the same 14-day summaries and paired forearm hydration measurements produces one hydration estimate per week.

Combination with existing systems

Skin estimation in a dialysis record system

An electronic dialysis record system supplies serum urea, serum phosphate, and pre- and post-treatment body mass to a skin estimation service. The service groups observations by treatment session and uses a model trained on session records paired with shin skin hydration readings taken immediately after treatment. When a session closes, the service writes the estimated hydration value and model version to the session record in dedicated fields.

Automated or data-driven variant

Overnight sensor inputs for skin estimation

A wrist sensor records optical pulse waveforms and three-axis acceleration during sleep. Software selects five-minute segments with low motion and sufficient pulse signal quality, then computes median pulse rate and median variability of successive pulse intervals across those segments. A gradient-boosted regression model trained on these features and paired next-morning cheek hydration readings estimates cheek hydration after the overnight data upload.

Personal calibration using paired skin readings

A monitoring application collects body composition measurements and fatigue questionnaire scores at repeated visits and feeds them to a population model for forearm skin hydration. At calibration visits, a capacitance probe supplies a same-day forearm hydration reading, and the application records the difference between that reading and the model estimate. After three paired visits, the application adds the median difference to subsequent estimates and updates the offset whenever a new paired reading arrives.

Specific version of a part

Sleep duration as input

A wrist accelerometer records movement across seven nights, and an activity classifier derives the mean nightly sleep duration. A regression model fitted to paired sleep records and skin measurements uses that duration to estimate cheek hydration in instrument units.

Seated pulse and pressure

An upper-arm cuff records systolic pressure, diastolic pressure, and pulse rate after the subject rests seated for five minutes. The system averages two readings taken one minute apart and stores pressure in millimeters of mercury and pulse rate in beats per minute.

Daily fatigue score collection

An electronic form records a fatigue rating each evening on an integer scale from 0 for no fatigue to 10 for extreme fatigue. The system calculates the mean of the preceding seven daily ratings and stores it with the dates of the entries.

Regression model for skin elasticity

A regularized linear regression maps age, body fat percentage, and glycated hemoglobin to the ratio of immediate skin recoil to peak deformation measured with a suction probe. At estimation time, the software scales each input using the training-set mean and standard deviation, then applies the fitted coefficients and intercept.

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 2009/0131761 A1
Published
May 21, 2009
Filed
Jun 20, 2006
Class
A61B 5/145
Document BUS 11,311,239 B2
Published
Apr 26, 2022
Filed
Aug 12, 2014
Class
A61B 5/6833
Claim 1
Document A
Document B
1.1acquiring mind-body data relating to the body and/or mind of a subject of skin condition estimation; and
One such probe includes a multi-parameter physiological measurement system that non-invasively measures blood pressure as well as respiration, perfusion, blood oxygen, pulse rate, body temperature, etc. from within the ear canal.
A · US 2009/0131761 A1 · ¶ 2
The vital-signs patch of claim 1, wherein the physiological measurements of the patient include measurements of vital-signs comprising at least one of body temperature, cardiac puke rate, respiration rate, and blood pressure.
B · US 11,311,239 B2 · claim 2
1.2estimating the subject's skin condition using a skin model that describes a correlation between the mind-body data and the skin condition, the mind-body data including at least one of liver function related variables, muscle-bone related variables, heart rate and blood pressure related variables, blood oxidation related variables, blood count related variables, lipid metabolism related variables, autonomic function related variables, personal attribute related variables, renal function related variables, body composition related variables, glucose tolerance related variables, electrolyte related variables, cognitive function related variables, immunometabolism related variables, and depression-fatigue-drowsiness related variables.

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

Statements in these documents
However, in some instances it is not convenient for a clinician to have to view the parameters at the central monitoring station, which is located away from the patient.
A · US 2009/0131761 A1 · ¶ 3
One advantage resides in locally displaying physiological signals measured with an in-the-ear probe.
A · US 2009/0131761 A1 · ¶ 5
A typical interval is 4 hours, which leads to the undesirable requirement for a nurse to awaken a patient in the middle of the night to take vital sign measurements.
B · US 11,311,239 B2 · ¶ 7
Measuring certain vital signs is normally intrusive at best and difficult to do on a continuous basis.
B · US 11,311,239 B2 · ¶ 9
Cite aspatent.fyi, US 2026/0354745 A1, claim 1, first published 2026-11-19T03:31:31-05:00, https://patent.fyi/US20260354745/, SHA-256 1bc02ca00e6d1678a89a0612670ed44f1146ddf212c6a71f3f004fb5985e65d6
First published
Permanent addresshttps://patent.fyi/US20260354745/
Content fingerprint (SHA-256)1bc02ca00e6d1678a89a0612670ed44f1146ddf212c6a71f3f004fb5985e65d6
Methodv2026-11-18.2 · automated, not reviewed by a person
Correctionscorrections@patent.fyi