System and method for determining sleep analysis based on a body image

Patent metadata

Field	Value
Publication number	US-12548154-B2
Application number	US-202118266758-A
Country	US
Kind code	B2
Filing date	Dec 10, 2021
Priority date	Dec 11, 2020
Publication date	Feb 10, 2026
Grant date	Feb 10, 2026

Abstract

A system and method to determine a sleep disorder in a patient is disclosed. A storage device stores a digital image including a face and a neck of the patient. A database stores previously identified phenotypes and dimensions of facial and neck features. A sleep disorder analysis engine is coupled to the storage device and the database. The sleep disorder analysis engine is operable to identify features of the face and the neck from the image by determining landmarks on the image. The sleep disorder analysis engine classifies at least one phenotype from the image based on comparisons with the database. The sleep disorder analysis engine correlates the at least one phenotype and at least one feature with a sleep disorder. The sleep disorder analysis engine determines a risk score of the sleep disorder based on the correlation of the phenotype and the feature.

First claim

What is claimed is:

1 . A method to determine a sleep disorder in a patient, the method comprising:
capturing a digital image including a face and a neck of the patient by a camera; measuring features of the face and the neck from the digital image by determining landmarks on the digital image via a processor; classifying at least one phenotype from the image from previously identified phenotypes stored in a database via the processor; correlating the at least one phenotype and the measurements of at least one feature with a sleep disorder via the processor; determining a risk score of the sleep disorder based on the correlation of the phenotype and the measurements of the at least one feature via the processor, wherein the phenotype is coded by a color on the image, and wherein the color code on the phenotype represents a degree of correlation with the sleep disorder; and displaying the image and the color code on a display.

2 . The method of claim 1 , further comprising providing multiple images including the face and neck of the patient.

3 . The method of claim 1 , further comprising measuring a physiological reading from the patient, and wherein the risk score of the sleep disorder is determined based partly on the physiological reading.

4 . The method of claim 1 , wherein the correlation is performed with a machine learning model trained with a plurality of images from a patient population and a sleep disorder score of each of the patient population.

5 . The method of claim 4 , further comprising:
storing the image, classified phenotype, dimensions of the feature and sleep disorder score; and updating a database of the patient population with the stored classified phenotype, dimensions of the features, and sleep disorder score for the patient.

6 . The method of claim 1 , wherein the sleep disorder is one of Obstructive Sleep Apnea (OSA), a form of Sleep Disordered Breathing (SDB), Cheyne-Stokes Respiration (CSR), Obesity Hyperventilation Syndrome (OHS) and Chronic Obstructive Pulmonary Disease (COPD).

7 . The method of claim 1 , further comprising determining a risk score of a co-morbidity based on the at least one phenotype.

8 . The method of claim 1 , further comprising:
providing a video of the patient; determining dynamic movement of one of the features from the video, and wherein the risk score of the sleep disorder is determined with the dynamic movement.

9 . The method of claim 1 , wherein the at least one phenotype is selected from one of the group of obesity/neck circumference, inset jaw/mandibular, and crowded/narrow upper airway.

10 . The method of claim 1 , further comprising:
determining a severity of the sleep disorder based on the determined sleep disorder score; and determining a therapy based on the severity of the sleep disorder.

11 . The method of claim 1 , wherein the feature is a neck dimension, wherein the neck dimension is correlated to a tissue mass and a stiffness parameter, and wherein the sleep disorder correlation relates to the tissue mass and the stiffness parameter.

12 . The method of claim 1 , further comprising matching a treatment for the sleep disorder based on the determined phenotype.

13 . A non-transitory computer readable medium comprising instructions which, when executed by a computer, cause the computer to carry out;
capturing a digital image including a face and a neck of the patient from a camera; measuring features of the face and the neck from the image by determining landmarks on the image; classifying at least one phenotype from the image from previously identified phenotypes stored in a database; correlating the at least one phenotype and the measurements of at least one feature with a sleep disorder; determining a risk score of the sleep disorder based on the correlation of the phenotype and the measurements of the at least one feature, wherein the phenotype is coded by a color on the image, wherein the color code on the phenotype represents a degree of correlation with the sleep disorder; and displaying the image and the color code on a display.

14 . A system to determine a sleep disorder in a patient, the system comprising:
a camera configured to capture a digital image including a face and a neck of the patient; a database storing previously identified phenotypes and dimensions of facial and neck features; a display; a processor coupled to the camera, the display, and the database, the processor operable to: identify features of the face and the neck from the image by determining landmarks on the image; classify at least one phenotype from the image based on comparisons with the database; correlate the at least one phenotype and at least one feature with a sleep disorder; and determine a risk score of the sleep disorder based on the correlation of the phenotype and the feature, wherein the phenotype is coded by a color on the image, and wherein the color code on the phenotype represents a degree of correlation with the sleep disorder; and display the image and the color code on the display.

15 . The system of claim 14 , further comprising a sensor interface coupled to the processor and a sensor measuring a physiological reading from the patient, and wherein the risk score of sleep disorder is determined based partly on the physiological reading.

16 . The system of claim 14 , wherein the correlation is performed with a machine learning model trained with a plurality of images from a patient population and a sleep disorder score of each of the patient population stored in the database, and wherein the processor is further operable to:
store the image, classified phenotype, dimensions of the feature, and sleep disorder score in a storge device; and update the database with the stored classified phenotype, dimensions of the features, and sleep disorder score for the patient.

17 . The system of claim 14 , wherein the sleep disorder is one of Obstructive Sleep Apnea (OSA), a form of Sleep Disordered Breathing (SDB), Cheyne-Stokes Respiration (CSR), Obesity Hyperventilation Syndrome (OHS) and Chronic Obstructive Pulmonary Disease (COPD).

18 . The system of claim 14 , wherein the at least one phenotype is selected from one of the group of obesity/neck circumference, inset jaw/mandibular, and crowded/narrow upper airway.

19 . The system of claim 14 , wherein the feature is a neck dimension, wherein the neck dimension is correlated to a tissue mass and a stiffness parameter, and wherein the sleep disorder correlation relates to the tissue mass and the stiffness parameter.

20 . The system of claim 14 , further comprising a storage device storing a video of the patient, and wherein the processor is operable to determine dynamic movement of one of the features from the video, and wherein the risk score of sleep disorder is determined with the dynamic movement.

Assignees

• ResMed Pty Ltd

Inventors

• Gill Christopher Andrew Wakeley
• Holley Liam
• Wehbeh Jamie Graeme
• Furlong Rowan Ben
• Mcgann Sarah Terese
• Wagner Stewart Joseph
• Hogg Michael Christopher

Classifications

• G06T2207/30201

  Face · CPC title

• G06T2207/30004

  Biomedical image processing · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/10016

  Video; Image sequence · CPC title

• G16H50/30

  for calculating health indices; for individual health risk assessment · CPC title