[go: up one dir, main page]

WO2024180488A1 - Rule-based sleep apnea automatic detection - Google Patents

Rule-based sleep apnea automatic detection Download PDF

Info

Publication number
WO2024180488A1
WO2024180488A1 PCT/IB2024/051897 IB2024051897W WO2024180488A1 WO 2024180488 A1 WO2024180488 A1 WO 2024180488A1 IB 2024051897 W IB2024051897 W IB 2024051897W WO 2024180488 A1 WO2024180488 A1 WO 2024180488A1
Authority
WO
WIPO (PCT)
Prior art keywords
computer program
program product
cardiac output
value
executed
Prior art date
Application number
PCT/IB2024/051897
Other languages
French (fr)
Inventor
Riccardo Groppo
Massimo VIOLANTE
Luigi PUGLIESE
Original Assignee
Sleep Advice Technologies S.R.L.
Politecnico Di Torino
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Sleep Advice Technologies S.R.L., Politecnico Di Torino filed Critical Sleep Advice Technologies S.R.L.
Publication of WO2024180488A1 publication Critical patent/WO2024180488A1/en

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4806—Sleep evaluation
    • A61B5/4818—Sleep apnoea
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
    • A61B5/0077—Devices for viewing the surface of the body, e.g. camera, magnifying lens
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording for evaluating the cardiovascular system, e.g. pulse, heart rate, blood pressure or blood flow
    • A61B5/024—Measuring pulse rate or heart rate
    • A61B5/02405—Determining heart rate variability
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording for evaluating the cardiovascular system, e.g. pulse, heart rate, blood pressure or blood flow
    • A61B5/024—Measuring pulse rate or heart rate
    • A61B5/02416—Measuring pulse rate or heart rate using photoplethysmograph signals, e.g. generated by infrared radiation
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue
    • A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
    • A61B5/14551—Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value ; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4806—Sleep evaluation
    • A61B5/4812—Detecting sleep stages or cycles
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
    • G16H40/63—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for local operation
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4806—Sleep evaluation
    • A61B5/4815—Sleep quality
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
    • G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Definitions

  • the present invention generally relates to automatic detection of Obstructive Sleep Apnea Syndrome (OSAS) in a subject.
  • OSAS Obstructive Sleep Apnea Syndrome
  • the present invention relates to a rule-based algorithm configured to identify OSAS by mapping the behavior of oxygen saturation (SpO2) and the action of the Autonomic Nervous System (ANS) and its subsystems, which are Sympathetic Nervous System (SNV) and Parasympathetic Nervous System (PNS).
  • SpO2 behavior of oxygen saturation
  • ANS Autonomic Nervous System
  • SNV Sympathetic Nervous System
  • PNS Parasympathetic Nervous System
  • OSAS is a common sleep disorder characterized by repeated episodes of breathing cessation during sleep; in particular, OSAS affects the quality of life and can lead to severe health complications, in particular when left untreated.
  • OSA Obstructive Sleep Apnea
  • AASM American Academy of Sleep Medicine scoring criteria for Obstructive Sleep Hypopnea and Apnea is an airflow reduction of at least 30% and 90%, respectively, considering that the reduction must last at least 10 seconds.
  • PSG Polysomnographic
  • rule-based approaches employ heuristic rules to identify apnea events based on the presence of specific patterns in the signals. For instance, known systems such as the ApneaLinkTM device exploit nasal pressure and thoracic/abdominal respiratory effort to identify respiratory events, in particular applying rules based on the AASM guidelines to classify them as apneas or hypopneas.
  • rule -based approaches are generally limited by the complexity and variability of the signals and cannot provide enough generalized results.
  • data-driven approaches use machine learning algorithms to learn patterns and features directly from the signals and classify apnea events based on the learned features; typically, data-driven approaches are based on supervised learning algorithms, such as support vector machines (SVM), artificial neural networks (ANN), and random forests (RF), as well as unsupervised learning algorithms such as clustering and principal component analysis (PCA).
  • SVM support vector machines
  • ANN artificial neural networks
  • RF random forests
  • PCA principal component analysis
  • An object of the present invention is thus providing systems and methods that allow to overcome at least in part the disadvantages of the known prior art.
  • Figure 1 schematically shows an electronic system according to an embodiment of the present invention.
  • Figure 2 schematically shows a software according to the present invention and implementing a OSAS classification.
  • FIG. 3 shows a block diagram of the software according to the present invention.
  • FIGS 4 and 5 schematically show architectural mappings in an integrated and distributed manner according to the present invention.
  • the present invention aims at automatically identifying the presence of OSAS and to highly and accurately differentiate its severity level, specifically in Severe, Moderate or Low OSAS.
  • the present invention is based on monitoring and processing cardio-respiratory parameters (e.g.
  • Heart Rate Heart Rate
  • HRV Heart Rate Variability
  • SpO2 Oxygen Saturation
  • a wearable device e.g. smartwatch
  • a contactless sensor e.g. RADAR, camera, image Photoplethysmography (PPG) sensor, etc.
  • Figure 1 shows a block diagram of a system 1 comprising:
  • a sensing unit 2 configured to communicate with a sensory system, here comprising either a wearable sensor 3 (e.g. a smartwatch) and/or a contactless sensor 4 (e.g. a RADAR, a camera, an image PPG sensor), to receive biometric signals of a subject; and
  • a wearable sensor 3 e.g. a smartwatch
  • a contactless sensor 4 e.g. a RADAR, a camera, an image PPG sensor
  • - electronic computing resources 10 here comprising a processing unit 5, configured to communicate with the sensing unit 2 to receive the biometric signals and to store, load and execute, when in use, a computer program product, software or algorithm 6 therein to output data relative to a phase and/or a transition among Relaxation, Arousal and Desaturation phases of OSAS based on the biometric signals.
  • the software 6 is designed to cause, when executed, the electronic processing resources 10 to become configured to automatically detect Obstructive Sleep Apnea Syndrome, OSAS, severity in a subject.
  • the software 6 is designed to cause, when executed, the electronic processing resources 10 to become configured to:
  • the software 6 is designed to cause, when executed, the electronic processing resources 10 to become configured to:
  • the observation window is here an all-night record of a subject’s sleep; according to further aspects of the present invention, not described in further detail hereinafter, the observation window may be a reduced time frame to the one disclosed herein.
  • the software 6 is designed to cause, when executed, the electronic processing resources 10 to become configured to classify (block 29) the biometric signals into the one or different classes based on whether the plurality of physiological quantities fulfils the proprietary criterions.
  • the sensing unit 2 is configured to:
  • the plurality of physiological quantities comprises cardiac outputs, in particular heart rate HR and heart rate variability HRV, and oxygen saturation outputs SpCh.
  • the biometric signals are sampled at 1 Hz, without it being limiting to the present invention.
  • the software 6 is configured to receive physiological data and process it to determine a phase among Relaxation, Arousal and Desaturation phases of the subject, here based on three levels or classes labelled as OSA phases.
  • OSA phases a phase among Relaxation, Arousal and Desaturation phases of the subject.
  • the oxygen saturation output SpO2 decreases over time, for example according to a tunable value x .
  • the value x is comprised between 3% and 15%. It is noted that, according to an aspect of the present invention, the software 6 is designed to operate with one or a subset of the abovementioned physiological quantities.
  • the software 6 is designed to cause, when executed, the electronic processing resources 10 to become configured to determine (block 21-22) a plurality of threshold values on the basis of the plurality of physiological quantities. Furthermore, the electronic processing resources 10 are configured to determine (block 21-22) a plurality of indexes associated with the time frame in which the variation of the plurality of physiological quantities is observed.
  • the electronic processing resources 10 are configured to determine (block 21) a function T_ODI relative to the number of desaturations whose value is in particular higher or equal to 4% and whose duration is at least 10 seconds observed in an all-night record of the sleep of a subject. r c if ODI ⁇ m 1 c 2 if ODI > mand ODI ⁇ m 2
  • Oxygen Desaturation Index which is the number of desaturation episodes, here higher than 4%, per hour;
  • Ci values are comprised between 0.001 and 3.0;
  • - mi-m4 are the boundaries values for different ranges of ODI, namely the mi values are comprised between 5 and 30.
  • T_HR heart rate threshold value which is determined as the ratio between the standard deviation of the heart rate HR and the standard deviation of the oxygen saturation output SpO2 multiplied by the function T_ODI;
  • the electronic processing resources 10 are also configured to determine (block 22), in particular set, a first index OSA, initially set to zero, related to the number of iterations in which OSA is determined to be present in the considered time frame; and a second index i, the latter being a natural integer initially set to zero, related to the time instants in the time frame.
  • the software 6 is designed to cause, when executed, the electronic processing resources 10 to become configured to verify (block 23-28) that the plurality of physiological quantities fulfils proprietary criterions on the basis of the plurality of the threshold values in the observation time window.
  • the electronic processing resources 10 are configured to:
  • observation window here the time frame considered to determine the presence of OSA and, when present, OSAS severity
  • the electronic processing resources 10 are configured to:
  • a cardiac output here the heart rate HR
  • a third index j wherein j is natural integer, in particular a calibrated value establishing the distance from the i* value
  • j is natural integer, in particular a calibrated value establishing the distance from the i* value
  • the subject may be determined to be in the Relaxation phase; in addition, if the heart rate HR at the second time instant i is higher than the sum between the mean value of the cardiac output mean HRw and heart rate threshold value T_HR, the subject may be determined to be in the Arousal phase.
  • the electronic processing resources 10 are also configured to verify (block 25) that the difference between the maximum value of an oxygen saturation output maxSpCh and the value of the oxygen saturation output SpCh at the second time instant i is higher to the oxygen saturation threshold value T_SpO2.
  • the electronic processing resources are configured to update (block 28) the value of the first index OSA, as well as the value of the second index i, by one, so as to continue the observation of the subject’s condition in the observation window.
  • the software 6 is configured to cause, when executed, the electronic processing resources 10 to become configured to determine (block 29) that, if the plurality of physiological quantities fulfils the proprietary criterions, one or more phases among Relaxation, Arousal and Desaturation phases of OSA of a subject are determined to be present.
  • one or more phases of OSA are detected if the following conditions, listed at blocks 25-27, are valid:
  • the heart rate HR at the time instant i-j is lower than the difference between the mean value of the cardiac output mean HRw and heart rate threshold value T_HR;
  • the heart rate HR at the second time instant i is higher than the sum between the mean value of the cardiac output mean HRw and heart rate threshold value T_HR;
  • the electronic processing resources 10 are configured to update the value of the second index i even in the case where the conditions at either blocks 25-27 are not fulfilled; in this way, the observation of the subject is shifted to the next time instant, as no condition is determined to be met and, as such, OSA is determined to not have been observed in the considered time instant.
  • the values of the first index OSA are stored in a dedicated memory (not shown) in the electronic processing resources 10.
  • the software 6 is designed to cause, when executed, the electronic processing resources 10 to become configured to determine (block 29) that, if the conditions at blocks 25-27 are met and, thus, the first index OSA is different from zero, one or more phases of OSA are determined to be present.
  • the software 6 is designed to cause, when executed, the electronic processing resources 10 to become configured to determine (block 29) the OSAS severity, relating to the number of obstructive events in the all-night record, in detail based on the first index OSA and, thus, the biometric signals;
  • the one or different classes comprises:
  • the software 6 is designed to cause, when executed, the electronic computing resources 10 to become configured to determine (block 29) the index on the basis of the number of potential OSA events occurring in the all-night record.
  • the number of potential OSA events occurring in the all-night record being determined on the basis of the number of times in which in the observation window the electronic processing resources 10 determine that the conditions at blocks 25-27 are considered to be fulfilled, i.e.:
  • the heart rate HR at the time instant i-j is lower than the difference between the mean value of the cardiac output mean HRw and heart rate threshold value T_HR;
  • the heart rate HR at the second time instant i is higher than the sum between the mean value of the cardiac output mean HRw and heart rate threshold value T_HR;
  • the abovementioned sequence of steps performed by the electronic processing resources 10 is repeated for the entire length of the considered time frame; in other words, the abovementioned steps are performed at each time instant of the considered time frame, the latter being for example the duration of the night sleep of the subject, so as to monitor the behavior of the same subject.
  • the present invention can be implemented in different architectural structures, thereby expanding the possibility of using the present invention in different contexts and applications. Examples of architectural implementations of the present invention are shown in Figures 4 and 5 and they will be described briefly in the following.
  • an edge device 30 is configured to fully integrate different sensors, i.e. integrates the sensory system of system 1, and the processing unit 5 of the electronic processing resources 10; furthermore, in this case, the feedback outputted by the electronic processing resources 10 is locally generated.
  • sensors of a first device 40 are configured to locally communicate, e.g. wirelessly through Wi-Fi, Blueetooth, RF signals or through a wired connection, and to transmit data to the processing unit 5 which is housed in a second device 50; the processing unit 5 is also configured to generate the feedback.
  • the present invention allows to identify the presence and stage of OS AS, significantly enhance diagnostic accuracy, reduce costs and increase access to care thanks to the adoption of much simpler sensors, being either a wearable device or a contactless sensor.
  • the present invention allows to improve the sensitivity and speed of OSAS diagnosis, which can ultimately lead to better patient outcomes and more efficient use of healthcare resources.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Pathology (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Surgery (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Cardiology (AREA)
  • Primary Health Care (AREA)
  • Artificial Intelligence (AREA)
  • Epidemiology (AREA)
  • Physiology (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Signal Processing (AREA)
  • Mathematical Physics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Business, Economics & Management (AREA)
  • Psychiatry (AREA)
  • Evolutionary Computation (AREA)
  • Fuzzy Systems (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Business, Economics & Management (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Optics & Photonics (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

A computer program product (6) storable in, and executable by, electronic computing resources (10) and designed to cause, when executed, the electronic computing resources (10) to become configured to automatically detect Obstructive Sleep Apnea Syndrome, OSAS, in a subject. The computer program product (6) is designed to cause, when executed, the electronic computing resources (10) to become configured to: receive (20) a biometric signals of a subject; process (21-28) the received biometric signals to classify them into one of different classes associated with one or more phases among Relaxation, Arousal and Desaturation phases of OSAS of a subject; and detect (29) a phase among Relaxation, Arousal and Desaturation phases of the subject based on the classified biometric signals. In order to process (21-28) the received biometric signal, the computer program product (6) is designed to cause, when executed, the electronic computing resources (10) to become configured to: compute (21-22) a plurality of physiological quantities based on the received biometric signals; and verify (23-28) that the plurality of physiological quantities fulfils proprietary criterions related to the variation of the plurality of physiological quantities in an observation window. In order to detect (29) a phase, the computer program product (6) is designed to cause, when executed, the electronic computing resources (10) to become configured to classify (29) the biometric signals into the one or different classes based on whether the plurality of physiological quantities fulfils the proprietary criterions.

Description

RULE-BASED SLEEP APNEA AUTOMATIC DETECTION
DESCRIPTION
Cross-Reference to Related Applications
This Patent Application claims priority from European Patent Application No. 23159216.3 filed on February 28, 2023 and from Italian Patent Application No. 102024000003919 filed on February 23, 2024, the entire disclosure of which is incorporated herein by reference.
Technical Field of the Invention
The present invention generally relates to automatic detection of Obstructive Sleep Apnea Syndrome (OSAS) in a subject. In particular, the present invention relates to a rule-based algorithm configured to identify OSAS by mapping the behavior of oxygen saturation (SpO2) and the action of the Autonomic Nervous System (ANS) and its subsystems, which are Sympathetic Nervous System (SNV) and Parasympathetic Nervous System (PNS).
Background of the Invention
As is known, OSAS is a common sleep disorder characterized by repeated episodes of breathing cessation during sleep; in particular, OSAS affects the quality of life and can lead to severe health complications, in particular when left untreated. In further detail, two types of Obstructive Sleep Apnea (OSA) are identified, i.e. obstructive sleep hypopnea and obstructive sleep apnea. The American Academy of Sleep Medicine (AASM) scoring criteria for Obstructive Sleep Hypopnea and Apnea is an airflow reduction of at least 30% and 90%, respectively, considering that the reduction must last at least 10 seconds.
The defined gold standard for diagnosing OSA is overnight Polysomnographic (PSG), which involves measuring several physiological signals, including airflow, oxygen saturation and brain activity. However, PSG is expensive, time-consuming and requires specialized equipment and expertise.
Therefore, there is growing interest in developing automatic OSA identification methods and systems which can be a tool for a preliminary screening of OSAS that is cheaper, more widely available and less burdensome for patients.
Recent advances in machine learning and signal processing have led to the development of several automatic OSA identification algorithms, exploiting various physiological signals to detect respiratory events and classify sleep apnea. These methods can be broadly categorized into two main approaches, namely rule-based and data-driven.
In particular, rule-based approaches employ heuristic rules to identify apnea events based on the presence of specific patterns in the signals. For instance, known systems such as the ApneaLink™ device exploit nasal pressure and thoracic/abdominal respiratory effort to identify respiratory events, in particular applying rules based on the AASM guidelines to classify them as apneas or hypopneas. However, rule -based approaches are generally limited by the complexity and variability of the signals and cannot provide enough generalized results.
On the other hand, data-driven approaches use machine learning algorithms to learn patterns and features directly from the signals and classify apnea events based on the learned features; typically, data-driven approaches are based on supervised learning algorithms, such as support vector machines (SVM), artificial neural networks (ANN), and random forests (RF), as well as unsupervised learning algorithms such as clustering and principal component analysis (PCA). Data-driven approaches have shown promising results in identifying sleep apnea from physiological signals, including nasal pressure, thoracic/abdominal respiratory effort and oxygen saturation.
Ongoing studies in determining and monitoring OSAS are currently preoccupied with improving the diagnosis and management of OSA, increasing access to care for those who need it. Thus, continuous monitoring of Heart Rate Variability (HRV) and SpO2 can provide valuable insights into the presence and severity of sleep apnea.
Ob ject and Summary of the Invention
Despite the advances in automatic sleep apnea identification, the Applicant has noticed that there are still several challenges that have to be addressed, such as the need for more extensive and heterogeneous datasets for training and validation, the standardization in the definition and classification of apnea events, and the demand for real-time and continuous monitoring of sleep apnea.
An object of the present invention is thus providing systems and methods that allow to overcome at least in part the disadvantages of the known prior art.
According to the present invention, a computer program product or software and a related system for automatically detecting sleep apnea, in particular based on rule-based approaches, are provided, as claimed in the appended set of claims. Brief Description of the Drawings
Figure 1 schematically shows an electronic system according to an embodiment of the present invention.
Figure 2 schematically shows a software according to the present invention and implementing a OSAS classification.
Figure 3 shows a block diagram of the software according to the present invention.
Figures 4 and 5 schematically show architectural mappings in an integrated and distributed manner according to the present invention.
Description of Preferred Embodiments of the Invention
The present invention will now be described in detail with reference to the accompanying drawings in order to allow a skilled person to implement it and use it. Various modifications to the described embodiments will be readily apparent to those of skill in the art and the general principles described may be applied to other embodiments and applications without however departing from the protective scope of the present invention as defined in the appended claims. Therefore, the present invention should not be regarded as limited to the embodiments described and illustrated herein but should be allowed the broadest protection scope consistent with the features described and claimed herein.
Unless otherwise defined, all technical and scientific terms used herein have the same meaning commonly understood by one of ordinary skill in the art to which the invention belongs. In case of conflict, the present specification, including the definitions provided, will control. Furthermore, the examples are provided for illustrative purposes only and as such should not be considered limiting.
In particular, the block diagrams included in the attached figures and described below are not to be understood as a representation of the structural features, i.e. constructional limitations, but must be understood as a representation of functional features, i.e. intrinsic properties of the devices defined by the effects obtained, that is to say functional restrictions, which can be implemented in different ways, so as to protect the functionalities thereof (operational capability).
In order to facilitate the understanding of the embodiments described herein, reference will be made to some specific embodiments and a specific language will be used to describe the same. The terminology used herein is used for the purpose of describing particular embodiments only and is not intended to limit the scope of the present invention. In particular, as also described in further detail below, the present invention aims at automatically identifying the presence of OSAS and to highly and accurately differentiate its severity level, specifically in Severe, Moderate or Low OSAS. In further detail, the present invention is based on monitoring and processing cardio-respiratory parameters (e.g. Heart Rate (HR), Heart Rate Variability (HRV), Oxygen Saturation (SpO2), etc.), which allow the implementation of a related algorithm in a simple and cost-effective manner either through a wearable device (e.g. smartwatch) or a contactless sensor (e.g. RADAR, camera, image Photoplethysmography (PPG) sensor, etc.).
Figure 1 shows a block diagram of a system 1 comprising:
- a sensing unit 2 configured to communicate with a sensory system, here comprising either a wearable sensor 3 (e.g. a smartwatch) and/or a contactless sensor 4 (e.g. a RADAR, a camera, an image PPG sensor), to receive biometric signals of a subject; and
- electronic computing resources 10, here comprising a processing unit 5, configured to communicate with the sensing unit 2 to receive the biometric signals and to store, load and execute, when in use, a computer program product, software or algorithm 6 therein to output data relative to a phase and/or a transition among Relaxation, Arousal and Desaturation phases of OSAS based on the biometric signals.
In particular, the software 6 is designed to cause, when executed, the electronic processing resources 10 to become configured to automatically detect Obstructive Sleep Apnea Syndrome, OSAS, severity in a subject. In further detail, referring to Figure 3, the software 6 is designed to cause, when executed, the electronic processing resources 10 to become configured to:
- receive (block 20) biometric signals of a subject;
- process (block 21-28) the received biometric signals to classify them into one of different classes associated with one or more phases among Relaxation, Arousal and Desaturation phases of OSAS of a subject; and
- detect (block 29) a phase among Relaxation, Arousal and Desaturation phases of the subject based on the classified biometric signals.
In particular, in order to process (block 21-28) the received biometric signal, the software 6 is designed to cause, when executed, the electronic processing resources 10 to become configured to:
- compute (block 21-22) a plurality of physiological quantities based on the received biometric signals; and
- verify (block 23-28) that the plurality of physiological quantities fulfils proprietary criterions related to the variation of the plurality of physiological quantities in an observation window or time frame.
According to an aspect of the present invention, the observation window is here an all-night record of a subject’s sleep; according to further aspects of the present invention, not described in further detail hereinafter, the observation window may be a reduced time frame to the one disclosed herein.
Furthermore, in order to detect (block 29) a phase, the software 6 is designed to cause, when executed, the electronic processing resources 10 to become configured to classify (block 29) the biometric signals into the one or different classes based on whether the plurality of physiological quantities fulfils the proprietary criterions.
It is noted that, here, the sensing unit 2 is configured to:
- provide a physical interface between the sensors 3, 4 and the electronic computing resources 10;
- extract physiological data or variables thereof from the received biometric signals; and
- transfer the physiological data to the electronic processing resources 10, which then are configured to load and execute the software 6 to output data to be presented to an end user as local and/or remote feedback.
According to an aspect of the present invention, the plurality of physiological quantities comprises cardiac outputs, in particular heart rate HR and heart rate variability HRV, and oxygen saturation outputs SpCh. In further detail, according to an aspect of the present invention, the biometric signals are sampled at 1 Hz, without it being limiting to the present invention.
As it will be clear from the following paragraphs, with reference to Figure 2, the software 6 is configured to receive physiological data and process it to determine a phase among Relaxation, Arousal and Desaturation phases of the subject, here based on three levels or classes labelled as OSA phases. In particular:
1) in the Relaxation phase, the parasympathetic activity is higher than the sympathetic one and the heart rate variability HR decreasing over time;
2) in the Arousal or Autonomic Arousal phase, the sympathetic activity is higher than the parasympathetic one and the heart rate variability HR is increasing over time; and
3) in the Desaturation phase, the oxygen saturation output SpO2 decreases over time, for example according to a tunable value x .
In particular, the value x is comprised between 3% and 15%. It is noted that, according to an aspect of the present invention, the software 6 is designed to operate with one or a subset of the abovementioned physiological quantities.
In order to compute (block 21-22) the plurality of physiological quantities, the software 6 is designed to cause, when executed, the electronic processing resources 10 to become configured to determine (block 21-22) a plurality of threshold values on the basis of the plurality of physiological quantities. Furthermore, the electronic processing resources 10 are configured to determine (block 21-22) a plurality of indexes associated with the time frame in which the variation of the plurality of physiological quantities is observed.
In particular, the electronic processing resources 10 are configured to determine (block 21) a function T_ODI relative to the number of desaturations whose value is in particular higher or equal to 4% and whose duration is at least 10 seconds observed in an all-night record of the sleep of a subject. r c if ODI < m1 c2if ODI > mand ODI < m2
TODI — < c3if ODI > m2and ODI < m3 c4if ODI > m3and ODI < m4 c5if ODI > m4 where:
- ODI isthe Oxygen Desaturation Index which is the number of desaturation episodes, here higher than 4%, per hour;
- C1-C5 are the values that TODI could assume for different ranges of ODI, namely the Ci values are comprised between 0.001 and 3.0; and
- mi-m4 are the boundaries values for different ranges of ODI, namely the mi values are comprised between 5 and 30.
Following, the electronic processing resources 10 are then configured to determine (block 22):
- a cardiac output, here heart rate, threshold value T_HR which is determined as the ratio between the standard deviation of the heart rate HR and the standard deviation of the oxygen saturation output SpO2 multiplied by the function T_ODI; and
- a oxygen saturation threshold value T SpO which is set as the predetermined, tunable value x.
Furthermore, the electronic processing resources 10 are also configured to determine (block 22), in particular set, a first index OSA, initially set to zero, related to the number of iterations in which OSA is determined to be present in the considered time frame; and a second index i, the latter being a natural integer initially set to zero, related to the time instants in the time frame.
In order to verify (block 23-28) that the plurality of physiological quantities fulfils proprietary criterions, the software 6 is designed to cause, when executed, the electronic processing resources 10 to become configured to verify (block 23-28) that the plurality of physiological quantities fulfils proprietary criterions on the basis of the plurality of the threshold values in the observation time window.
In particular, the electronic processing resources 10 are configured to:
- determine (block 23) the observation window, here the time frame considered to determine the presence of OSA and, when present, OSAS severity; and
- verify (block 24) that the second index i is lower than the length of a vector containing the values of the heart rate HR in the observation window.
If the second index i is determined to be lower than the length of a vector containing the values of the heart rate HR in the observation window, the electronic processing resources 10 are configured to:
- verify (block 26) that a cardiac output, here the heart rate HR, at a time instant equal to the difference between the second index i and a third index j (wherein j is natural integer, in particular a calibrated value establishing the distance from the i* value) is lower than the difference between a mean value of the cardiac output mean (HRw) and the heart rate threshold value T_HR; and
- if it is verified that the heart rate HR at the time instant i-j is lower than the difference between the mean value of the cardiac output mean HRw and heart rate threshold value T_HR, verify (block 27) that a cardiac output, here the heart rate HR, at a second time instant equal to the second index i is higher than the sum between the mean value of the cardiac output mean HRw and the heart rate threshold value T_HR.
It is noted that, if the heart rate HR at the time instant i-j is lower than the difference between the mean value of the cardiac output mean HRw and heart rate variability threshold value T_HR, the subject may be determined to be in the Relaxation phase; in addition, if the heart rate HR at the second time instant i is higher than the sum between the mean value of the cardiac output mean HRw and heart rate threshold value T_HR, the subject may be determined to be in the Arousal phase.
Furthermore, the electronic processing resources 10 are also configured to verify (block 25) that the difference between the maximum value of an oxygen saturation output maxSpCh and the value of the oxygen saturation output SpCh at the second time instant i is higher to the oxygen saturation threshold value T_SpO2.
If the conditions at blocks 25 and 27 are also fulfilled, i.e. it is verified that the heart rate HR at the second time instant i is higher than the sum between the mean value of the cardiac output mean HRw and heart rate threshold value T_HR and that the difference between the maximum value of an oxygen saturation output maxSpCh and the value of the oxygen saturation output SpCh at the second time instant i is higher to the oxygen saturation threshold value T_SpO2, the electronic processing resources are configured to update (block 28) the value of the first index OSA, as well as the value of the second index i, by one, so as to continue the observation of the subject’s condition in the observation window.
Therefore, in order to detect (block 29) a phase among Relaxation, Arousal and Desaturation phases of the subject based on the classified biometric signals, the software 6 is configured to cause, when executed, the electronic processing resources 10 to become configured to determine (block 29) that, if the plurality of physiological quantities fulfils the proprietary criterions, one or more phases among Relaxation, Arousal and Desaturation phases of OSA of a subject are determined to be present. In other words, considering the disclosure above, one or more phases of OSA are detected if the following conditions, listed at blocks 25-27, are valid:
- the heart rate HR at the time instant i-j is lower than the difference between the mean value of the cardiac output mean HRw and heart rate threshold value T_HR;
- the heart rate HR at the second time instant i is higher than the sum between the mean value of the cardiac output mean HRw and heart rate threshold value T_HR; and
- the difference between the maximum value of an oxygen saturation output maxSpO and the value of the oxygen saturation output SpO2 at the second time instant i is higher to the oxygen saturation threshold value T_SpO2.
It is noted that the electronic processing resources 10 are configured to update the value of the second index i even in the case where the conditions at either blocks 25-27 are not fulfilled; in this way, the observation of the subject is shifted to the next time instant, as no condition is determined to be met and, as such, OSA is determined to not have been observed in the considered time instant.
It is also noted that the values of the first index OSA are stored in a dedicated memory (not shown) in the electronic processing resources 10.
If the second index i is determined to be higher than the length of a vector containing the values of the heart rate HR in the observation window, in order to detect (block 29) a phase among Relaxation, Arousal and Desaturation phases of the subject based on the classified biometric signals, the software 6 is designed to cause, when executed, the electronic processing resources 10 to become configured to determine (block 29) that, if the conditions at blocks 25-27 are met and, thus, the first index OSA is different from zero, one or more phases of OSA are determined to be present. In particular, the software 6 is designed to cause, when executed, the electronic processing resources 10 to become configured to determine (block 29) the OSAS severity, relating to the number of obstructive events in the all-night record, in detail based on the first index OSA and, thus, the biometric signals; in particular, the one or different classes comprises:
- a first class Ci indicative of healthy OSAS and wherein the value of the index OSA is lower than five;
- a second class C2 indicative of a mild OSAS and wherein the value of the index OSA is comprised between five and fifteen;
- a third class C3 indicative of a moderate OSAS and wherein the value of the index OSA is comprised between fifteen and thirty; and
- a fourth class C4 indicative of a severe OSAS and wherein the value of the index OSA is higher than thirty.
Therefore, considering the disclosure above, in order to determine (block 29) the index in the observation window, the software 6 is designed to cause, when executed, the electronic computing resources 10 to become configured to determine (block 29) the index on the basis of the number of potential OSA events occurring in the all-night record. In particular, the number of potential OSA events occurring in the all-night record being determined on the basis of the number of times in which in the observation window the electronic processing resources 10 determine that the conditions at blocks 25-27 are considered to be fulfilled, i.e.:
- the heart rate HR at the time instant i-j is lower than the difference between the mean value of the cardiac output mean HRw and heart rate threshold value T_HR;
- the heart rate HR at the second time instant i is higher than the sum between the mean value of the cardiac output mean HRw and heart rate threshold value T_HR; and
- the difference between the maximum value of an oxygen saturation output maxSpCh and the value of the oxygen saturation output SpCh at the second time instant i is higher to the oxygen saturation threshold value T_SpO2.
It is noted that the abovementioned sequence of steps performed by the electronic processing resources 10 is repeated for the entire length of the considered time frame; in other words, the abovementioned steps are performed at each time instant of the considered time frame, the latter being for example the duration of the night sleep of the subject, so as to monitor the behavior of the same subject.
The present invention can be implemented in different architectural structures, thereby expanding the possibility of using the present invention in different contexts and applications. Examples of architectural implementations of the present invention are shown in Figures 4 and 5 and they will be described briefly in the following.
From the architectural viewpoint, both integrated and distributed solutions can be implemented, as also shown in Figures 4-5. In particular, with reference to Figure 4, showing an integrated solution, an edge device 30 is configured to fully integrate different sensors, i.e. integrates the sensory system of system 1, and the processing unit 5 of the electronic processing resources 10; furthermore, in this case, the feedback outputted by the electronic processing resources 10 is locally generated. On the other hand, with reference to Figure 5, showing a distributed solution, sensors of a first device 40 are configured to locally communicate, e.g. wirelessly through Wi-Fi, Blueetooth, RF signals or through a wired connection, and to transmit data to the processing unit 5 which is housed in a second device 50; the processing unit 5 is also configured to generate the feedback.
From the disclosure above, the present invention has several advantages.
In particular, the present invention allows to identify the presence and stage of OS AS, significantly enhance diagnostic accuracy, reduce costs and increase access to care thanks to the adoption of much simpler sensors, being either a wearable device or a contactless sensor.
Furthermore, the present invention allows to improve the sensitivity and speed of OSAS diagnosis, which can ultimately lead to better patient outcomes and more efficient use of healthcare resources.
Finally, it is clear that modifications and variations may be made to the object of the present patent application described and illustrated herein without departing from the protective scope of the present invention as defined in the appended claims.

Claims

1. A computer program product (6) storable in, and executable by, electronic computing resources (10) and designed to cause, when executed, the electronic computing resources (10) to become configured to automatically detect Obstructive Sleep Apnea Syndrome, OS AS, in a subject; the computer program product (6) is designed to cause, when executed, the electronic computing resources (10) to become configured to:
- receive (20) a biometric signals of a subject;
- process (21-28) the received biometric signals to classify them into one of different classes associated with one or more phases among Relaxation, Arousal and Desaturation phases of OSAS of a subject; and
- detect (29) a phase among Relaxation, Arousal and Desaturation phases of the subject based on the classified biometric signals, characterised in that, in order to process (21-28) the received biometric signal, the computer program product (6) is designed to cause, when executed, the electronic computing resources (10) to become configured to:
- compute (21-22) a plurality of physiological quantities based on the received biometric signals; and
- verify (23-28) that the plurality of physiological quantities fulfils proprietary criterions related to the variation of the plurality of physiological quantities in an observation window, and wherein, in order to detect (29) a phase, the computer program product (6) is designed to cause, when executed, the electronic computing resources (10) to become configured to classify (29) the biometric signals into the one or different classes based on whether the plurality of physiological quantities fulfils the proprietary criterions.
2. The computer program product (6) according to claim 1, wherein, in order to compute (21-22) the plurality of physiological quantities, the computer program product (6) is designed to cause, when executed, the electronic computing resources (10) to become configured to determine (21-22) a plurality of threshold values on the basis of the plurality of physiological quantities, wherein, in order to verify (23-28) that the plurality of physiological quantities fulfils proprietary criterions, the computer program product (6) is designed to cause, when executed, the electronic processing resources (10) to become configured to verify (23-28) that the plurality of physiological quantities fulfils proprietary criterions on the basis of the plurality of the threshold values in the observation window, and wherein, in order to detect (block 29) a phase among Relaxation, Arousal and Desaturation phases of the subject based on the classified biometric signals, the computer program product (6) is configured to cause, when executed, the electronic processing resources (10) to become configured to determine (29) that, if the plurality of physiological quantities fulfils the proprietary criterions, one or more phases among Relaxation, Arousal and Desaturation phases of OSAS of a subject are determined to be present.
3. The computer program product (6) according to claim 2, wherein the plurality of physiological quantities comprise cardiac outputs, in particular heart rate (HR) and heart rate variability (HRV), and oxygen saturation outputs (SpCh), wherein, in order to compute (21-22) the plurality of physiological quantities, the computer program product (6) is designed to cause, when executed, the electronic computing resources (10) to become configured to determine (21):
- a function (T_ODI) relative to the number of desaturations observed in the observation window;
- a cardiac output, in particular heart rate, threshold value (T_HR) which is determined as the ratio between the standard deviation of the cardiac output (HR) and the standard deviation of the oxygen saturation output (SpCh) multiplied by the function (T_ODI); and
- a oxygen saturation threshold value (T_SpO2) which is set as predetermined, tunable value (x), wherein, in order to verify (23-28) that the plurality of physiological quantities fulfils the proprietary criterions, the computer program product (6) is configured to cause, when executed, the electronic processing resources (10) to become configured to:
- verify (26) that the cardiac output (HR) at a first time instant (i-j) is lower than the difference between a mean value of the cardiac output mean (HRw) and the cardiac output threshold value (T_HR); and
- if it is verified that the cardiac output (HR) at the first time instant (i-j) is lower than the difference between the mean value of the cardiac output mean (HRw) cardiac output threshold value (T_HR), verify (27) that the cardiac output (HR) at a second time instant (i) is higher than the sum between the mean value of the cardiac output mean (HRw) and the cardiac output threshold value (T_HR), the computer program product (6) being further configured to cause, when executed, the electronic processing resources (10) to become configured to verify (25) that the difference between the maximum value of an oxygen saturation output (maxSpCh) and the value of the oxygen saturation output (SpCh) at the second time instant (i) is higher to the oxygen saturation threshold value (T_SpO2).
4. The computer program product (6) according to claim 3, wherein the predetermined tunable value (x) is comprised between 3% and 15%.
5. The computer program product (6) according to any one of claims 3-4, wherein, in order to classify (29) the biometric signals into the one or different classes, the computer program product (6) is designed to cause, when executed, the electronic computing resources (10) to become configured to determine (block 29) that one or more phases among Relaxation, Arousal and Desaturation phases of OSAS of a subject are determined to be present if:
- the cardiac output (HR) at the first time instant (i-j) is lower than the difference between the mean value of the cardiac output mean (HRw) and cardiac output threshold value (T_HR);
- the cardiac output (HR) at the second time instant (i) is higher than the sum between the mean value of the cardiac output mean (HRw) and cardiac output threshold value (T_HR); and
- the difference between the maximum value of an oxygen saturation output (maxSpCh) and the value of the oxygen saturation output (SpCh) at the second time instant (i) is higher to the oxygen saturation threshold value (T_SpO2).
6. The computer program product (6) according to claim 5, wherein, in order to classify (26) the biometric signals into the one or different classes based on whether the plurality of physiological quantities fulfils the proprietary criterions, the computer program product (6) is designed to cause, when executed, the electronic computing resources (10) to become configured to determine (29) the OSAS severity based on an index (OSA) relating to the number of obstructive events in the observation window, the one or different classes comprising:
- a first class (Ci) indicative of healthy OSAS and wherein the value of the index (OSA) is lower than five;
- a second class (C2) indicative of a mild OSAS and wherein the value of the index (OSA) is comprised between five and fifteen;
- a third class (C3) indicative of a moderate OSAS and wherein the value of the index (OSA)is comprised between fifteen and thirty; and
- a fourth class (C4) indicative of a severe OSAS and wherein the value of the index (OSA)is higher than thirty.
7. The computer program product (6) according to claim 6, wherein, in order to determine (29) the index in the observation window, the computer program product (6) is designed to cause, when executed, the electronic computing resources (10) to become configured to determine (29) the index on the basis of the number of potential OSA events occurring in the observation window, wherein the number of potential OSA events occurring in the observation window being determined on the basis of the number of times in which in the observation window the electronic processing resources (10) determine that:
- the cardiac output (HR) at the first time instant (i-j) is lower than the difference between the mean value of the cardiac output mean (HRw) and cardiac output threshold value (T_HR);
- the cardiac output (HR) at the second time instant (i) is higher than the sum between the mean value of the cardiac output mean (HRw) and cardiac output threshold value (T_HR); and
- the difference between the maximum value of an oxygen saturation output (maxSpCh) and the value of the oxygen saturation output (SpCh) at the second time instant (i) is higher to the oxygen saturation threshold value (T_SpO2).
8. Electronic computing resources (10) configured to automatically detect Obstructive Sleep Apnea Syndrome, OSAS, in a subject; the electronic computing resources (10) being configured to store, load and execute a computer program product according to any one of the preceding claims to operate according any one of the preceding claims.
PCT/IB2024/051897 2023-02-28 2024-02-28 Rule-based sleep apnea automatic detection WO2024180488A1 (en)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
EP23159216.3 2023-02-28
EP23159216 2023-02-28
IT202400003919 2024-02-23
IT102024000003919 2024-02-23

Publications (1)

Publication Number Publication Date
WO2024180488A1 true WO2024180488A1 (en) 2024-09-06

Family

ID=90105268

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IB2024/051897 WO2024180488A1 (en) 2023-02-28 2024-02-28 Rule-based sleep apnea automatic detection

Country Status (1)

Country Link
WO (1) WO2024180488A1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070032733A1 (en) * 2004-01-16 2007-02-08 David Burton Method and apparatus for ECG-derived sleep disordered breathing monitoring, detection and classification
US20160120464A1 (en) * 2004-12-23 2016-05-05 Resmed Limited Discrimination of cheyne-stokes breathing patterns by use of oximetry signals
WO2017031489A1 (en) * 2015-08-20 2017-02-23 Serenium, Inc. System and method of diagnosing pediatric obstructive sleep apnea
EP3205267A1 (en) * 2009-07-16 2017-08-16 ResMed Ltd. Detection of sleep condition
US20200405222A1 (en) * 2018-03-07 2020-12-31 Koninklijke Philips N.V. Sleep apnea detection system and method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070032733A1 (en) * 2004-01-16 2007-02-08 David Burton Method and apparatus for ECG-derived sleep disordered breathing monitoring, detection and classification
US20160120464A1 (en) * 2004-12-23 2016-05-05 Resmed Limited Discrimination of cheyne-stokes breathing patterns by use of oximetry signals
EP3205267A1 (en) * 2009-07-16 2017-08-16 ResMed Ltd. Detection of sleep condition
WO2017031489A1 (en) * 2015-08-20 2017-02-23 Serenium, Inc. System and method of diagnosing pediatric obstructive sleep apnea
US20200405222A1 (en) * 2018-03-07 2020-12-31 Koninklijke Philips N.V. Sleep apnea detection system and method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
LAZAZZERA REMO ET AL: "Detection and Classification of Sleep Apnea and Hypopnea Using PPG and SpO$_2$ Signals", vol. 68, no. 5, 30 September 2020 (2020-09-30), pages 1496 - 1506, XP011850385, ISSN: 0018-9294, Retrieved from the Internet <URL:https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9210227> [retrieved on 20210420], DOI: 10.1109/TBME.2020.3028041 *

Similar Documents

Publication Publication Date Title
Choi et al. Real-time apnea-hypopnea event detection during sleep by convolutional neural networks
Zhou et al. Automatic detection of sleep apnea based on EEG detrended fluctuation analysis and support vector machine
Pathinarupothi et al. Single sensor techniques for sleep apnea diagnosis using deep learning
JP6199330B2 (en) Identification of Chain Stokes breathing patterns using oximetry signals
Fekr et al. Respiration disorders classification with informative features for m-health applications
US11288952B2 (en) System and method for processing multiple signals
Huang et al. A novel method to precisely detect apnea and hypopnea events by airflow and oximetry signals
US20220039742A1 (en) Systems and methods for analysis of sleep disordered breathing events
Aktaruzzaman et al. The addition of entropy-based regularity parameters improves sleep stage classification based on heart rate variability
Marcos et al. Utility of multilayer perceptron neural network classifiers in the diagnosis of the obstructive sleep apnoea syndrome from nocturnal oximetry
De Chazal et al. Multimodal detection of sleep apnoea using electrocardiogram and oximetry signals
US11813077B2 (en) Arrhythmic heartbeat resilient sleep apnea detection
Carrubba et al. Continuous EEG-based dynamic markers for sleep depth and phasic events
WO2024180488A1 (en) Rule-based sleep apnea automatic detection
KR20190110276A (en) Multi-sensor based noncontact sleep monitoring method and apparatus using ensemble of deep neural network and random forest
Schipper et al. A deep-learning approach to assess respiratory effort with a chest-worn accelerometer during sleep
CA3139034A1 (en) System and method for filtering time-varying data for physiological signal prediction
Parbat et al. Multiscale entropy analysis of single lead ECG and ECG derived respiration for ai based prediction of sleep apnea events
KR102488616B1 (en) Method for Emotion Evaluation using heart dynamics, and system adopting the method
Fallmann et al. Enhanced multi-source data analysis for personalized sleep-wake pattern recognition and sleep parameter extraction
Ghavami et al. Artificial neural network-enabled prognostics for patient health management
Venkatakiran et al. Real-Time Health Data Analytics in IoT-Connected Wearable Devices
Lewicke et al. Reliable determination of sleep versus wake from heart rate variability using neural networks
US20240206822A1 (en) Computer implemented method for adaptive physiology-based monitoring of a subject
Sannino et al. Use of machine learning algorithms to identify sleep phases starting from ECG signals

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24708564

Country of ref document: EP

Kind code of ref document: A1

DPE1 Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101)