WO2018234427A1 - Détection d'hypoxie - Google Patents

Détection d'hypoxie Download PDF

Info

Publication number
WO2018234427A1
WO2018234427A1 PCT/EP2018/066531 EP2018066531W WO2018234427A1 WO 2018234427 A1 WO2018234427 A1 WO 2018234427A1 EP 2018066531 W EP2018066531 W EP 2018066531W WO 2018234427 A1 WO2018234427 A1 WO 2018234427A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
hypoxia
user
plethysmography
electrocardiography
Prior art date
Application number
PCT/EP2018/066531
Other languages
English (en)
Inventor
Cristhian Mauricio POTES BLANDON
Mladen Milosevic
Saman Parvaneh
Erina GHOSH
Original Assignee
Koninklijke Philips N.V.
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 Koninklijke Philips N.V. filed Critical Koninklijke Philips N.V.
Publication of WO2018234427A1 publication Critical patent/WO2018234427A1/fr

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
    • A61B5/02416—Detecting, measuring or recording 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, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
    • A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
    • A61B5/14551—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, 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
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/332—Portable devices specially adapted therefor
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/346—Analysis of electrocardiograms
    • A61B5/349—Detecting specific parameters of the electrocardiograph cycle
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
    • A61B5/6802—Sensor mounted on worn items
    • A61B5/681—Wristwatch-type devices
    • 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
    • A61B5/7271—Specific aspects of physiological measurement analysis
    • A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
    • 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

Definitions

  • Embodiments described herein generally relate to systems and methods for detecting hypoxia and, more particularly but not exclusively, to systems and methods for detecting hypoxia through monitoring baroreflex sensitivity using wearable sensor devices.
  • hypoxia is a condition caused by inadequate supply of oxygen in tissues and organs. People may experience hypoxia by operating or otherwise being in environments with limited oxygen supply such as in poorly ventilated rooms or at higher altitudes. People may also experience hypoxia by engaging in strenuous activity. For example, first responders, soldiers, and athletes tend to be at higher risk of hypoxia than others.
  • Symptoms of hypoxia may include light-headedness, fatigue, and nausea. More extreme instances of hypoxia may be accompanied by symptoms such as disorientation, tachycardia, myocardial infarction, stroke, low blood pressure, and even death.
  • Existing techniques for detecting hypoxia at the systemic level generally involve some type of body-invasive measurements. For example, one existing technique is to extract a blood sample from a user to determine lactate levels. However, these invasive measurements for measuring hypoxia are impractical for real-time monitoring and detection of hypoxia.
  • inventions relate to a hypoxia detection system.
  • the system includes an electrocardiography sensor configured to gather electrocardiography data of a user; a plethysmography sensor configured to gather plethysmography data of the user; a features extraction module executing instructions stored on a memory to generate at least one baroreflex sensitivity feature based on the electrocardiography data and the plethysmography data; a hypoxia detection module executing instructions stored on the memory to compute a hypoxia index in real time based on the at least one baroreflex sensitivity feature; and a communications interface in operable communication with the hypoxia detection module and configured to present a notification to the user upon the hypoxia index indicating the user is at risk of hypoxia.
  • the at least one baroreflex sensitivity feature includes at least one of QRS amplitude, plethysmography amplitude, ratio of QRS amplitude to plethysmography amplitude, heart rate variability, average time interval between heart beats, Sp0 2 , total spectral power, spectral power in different frequency bands, and pulse transit time.
  • the system further includes a pre-processing module configured to perform at least one of filtering the electrocardiography and plethysmography data, and calculating a signal quality index based on the electrocardiography data and the plethysmography data, wherein a signal quality index exceeding a predetermined threshold indicates that a hypoxia index should be computed.
  • a pre-processing module configured to perform at least one of filtering the electrocardiography and plethysmography data, and calculating a signal quality index based on the electrocardiography data and the plethysmography data, wherein a signal quality index exceeding a predetermined threshold indicates that a hypoxia index should be computed.
  • the system further includes an acceleration sensor configured to gather acceleration data of the user, wherein the hypoxia index is additionally based on the acceleration data.
  • the system further includes a context inference module to infer the user's context from at least the acceleration data and to adjust the hypoxia index based on the user's context.
  • the system further includes a sensor providing altitude information to the context inference module.
  • the electrocardiography data and the plethysmography data are gathered over individual temporal segments, and a hypoxia index is computed for each individual temporal segment.
  • the system further includes at least one database module configured to store the electrocardiography data, the plethysmography data, and previously computed hypoxia indices.
  • the system further includes a beat detection module extracting heartbeat data from the electrocardiography data and the plethysmography data and providing the extracted heartbeat data as an input to the features extraction module.
  • a hypoxia index exceeding a predetermined threshold indicates the user is at risk of hypoxia.
  • embodiments relate to a method of detecting hypoxia based on baroreflex sensitivity.
  • the method includes receiving electrocardiography data of a user; receiving plethysmography data of the user; generating, using a features extraction module executing instructions stored on a memory, at least one baroreflex sensitivity feature based on the electrocardiography data and the plethysmography data; computing, using a hypoxia detection module executing instructions stored on the memory, a hypoxia index in real time based on the at least one baroreflex sensitivity feature; and presenting, using a communications interface, a notification to the user upon the hypoxia index indicating the user is at risk of hypoxia.
  • the at least one baroreflex sensitivity feature includes at least one of QRS amplitude, plethysmography amplitude, ratio of QRS amplitude to plethysmography amplitude, average time interval between heart beats, heart rate variability, Sp0 2 , total spectral power, spectral power in different frequency bands, and pulse transit time.
  • the method further includes performing, using a pre-processing module, at least one of filtering the electrocardiography and plethysmography data, and calculating a signal quality index based on the electrocardiography data and the plethysmography data, wherein a signal quality index exceeding a predetermined threshold indicates that a hypoxia index should be calculated.
  • the method further includes receiving acceleration data of the user, wherein the hypoxia index is additionally based on the acceleration data.
  • the method further includes determining the user's context from at least the acceleration data using a context inference module; and adjusting, using the context inference module, the hypoxia index based on the user's context. In some embodiments, the method further includes determining the user's context from at least altitude information using the context inference module. [0020] In some embodiments, the electrocardiography data and the plethysmography data are gathered over individual temporal segments, and a hypoxia index is computed for each individual temporal segment.
  • the method further includes storing, using at least one database module, electrocardiography data, the plethysmography data, and previously computed hypoxia indices.
  • the method further includes extracting heartbeat data from the electrocardiography data and the plethysmography data using a beat detection module and providing the extracted heartbeat data as an input to the features extraction module.
  • the hypoxia index exceeding a predetermined threshold indicates the user is at risk of hypoxia.
  • embodiments relate to a computer readable medium containing computer-executable instructions for detecting hypoxia based on baroreflex sensitivity, the medium comprising computer-executable instructions for receiving electrocardiography data of a user; computer-executable instructions for receiving plethysmography data of the user; computer-executable instructions for generating, using a features extraction module executing instructions stored on a memory, at least one baroreflex sensitivity feature based on the electrocardiography data and the plethysmography data; computer-executable instructions for computing, using a hypoxia detection module executing instructions stored on the memory, a hypoxia index in real time based on the at least one baroreflex sensitivity feature; and computer- executable instructions for presenting, using a communications interface, a notification to the user upon the hypoxia index indicating the user is at risk of hypoxia.
  • FIG. 1 illustrates a system for hypoxia detection in accordance with one embodiment
  • FIG. 2 illustrates wearable devices for detecting hypoxia in accordance with one embodiment
  • FIG. 3 depicts a flowchart of a method for detecting hypoxia in accordance with one embodiment
  • FIG. 4 illustrates an exemplary hardware device for implementing the methods described herein in accordance with one embodiment.
  • the present disclosure also relates to an apparatus for performing the operations herein.
  • This apparatus may be specially constructed for the required purposes, or it may comprise a general-purpose computer selectively activated or reconfigured by a computer program stored in the computer.
  • a computer program may be stored in a computer readable storage medium, such as, but is not limited to, any type of disk including floppy disks, optical disks, CD-ROMs, magnetic-optical disks, read-only memories (ROMs), random access memories (RAMs), EPROMs, EEPROMs, magnetic or optical cards, application specific integrated circuits (ASICs), or any type of media suitable for storing electronic instructions, and each may be coupled to a computer system bus.
  • the computers referred to in the specification may include a single processor or may be architectures employing multiple processor designs for increased computing capability.
  • Airway neuroepithelial bodies sense changes in inspired oxygen and carotid bodies sense arterial oxygen levels. Both respond to the decreased oxygen supply by, for example, increasing lung ventilation, enhancing oxygen extraction efficiency, and increasing cardiac output and tissue perfusion.
  • BRS baroreflex sensitivity
  • BRS is a reflex mechanism that uses baroreceptors to regulate blood pressure by detecting blood pressure changes. Activation of baroreceptors (e.g., due to an increase in blood pressure) leads to a decrease in the discharge of sympathetic neurons to the heart and the peripheral bloods vessels. On the other hand, a decrease in systemic blood pressure causes the deactivation of baroreceptors and the subsequent enhancement of the sympathetic activity and vagal inhibition. This may lead to tachycardia, an increase in cardiac contractility and peripheral resistance, and venous return.
  • ECG electrocardiography
  • PPG plethysmography
  • the ECG data and PPG data may be gathered by devices worn by a user. These wearable devices may include, for example, the Phillips VitalPatch and the Philips Health Watch. Wearable devices therefore can detect hypoxia without requiring invasive techniques such as those discussed previously. Accordingly, the proposed system and methods continuously monitor hypoxia using noninvasive sensors that can be implemented in wearable devices and used during physical activity.
  • FIG. 1 illustrates the architecture of a hypoxia detection system 100 in accordance with one embodiment.
  • the system 100 may include a sensing module 102, a pre-processing module 104, a beat detector module 106, a features extraction module 108, one or more databases 110, a BRS sensitivity estimation module 112, a context inference module 114, a hypoxia detection module 116, and a communication user interface 118.
  • the sensing module 102 may include or interface with sensor devices to gather data regarding the user. Specifically, this data may include physiological and kinematic data.
  • the sensing module 102 may include wearable sensor devices to gather ECG data and PPG data.
  • the sensing module 102 may also include acceleration sensor devices to gather acceleration data of a user, pressure gauges (e.g., to detect pressure on a user), and GPS-based sensor devices to gather location and altitude data.
  • Data gathered by the sensing module 102 may be communicated to the pre-processing module 104.
  • the pre-processing module 104 may be any hardware device capable of executing instructions stored on memory to process the data gathered by the sensing module 102.
  • the pre-processing module 104 may be a microprocessor, a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), or a similar type of device.
  • FPGA field programmable gate array
  • ASIC application-specific integrated circuit
  • the functionality described as being provided in part via software may instead be configured into the design of the ASICs and, as such, the associated software may be omitted.
  • the pre-processing module 104 may be configured to denoise, detrend, and/ or filter the data gathered by the sensing module 102. This may additionally serve as a calibration step for the data gathered by sensing module 102.
  • the pre-processing module 104 may filter out or otherwise only extract data that is above and/or below a certain level. Additionally or alternatively, the preprocessing module 104 may calculate an initial signal quality index for a particular temporal segment that may be used to decide whether a hypoxia index should be calculated for that segment. [0048] In other words, the pre-processing module 104 may be configured to consider an initial set of ECG and PPG data to determine if the data indicates a user may be at risk of hypoxia. For example, if there are several ECG and PPG readings that are abnormal, the hypoxia index may suggest that further analysis is recommended. On the other hand, if repeated ECG and PGG readings are normal and give no cause for concern, it may not be necessary or worthwhile to conduct further analysis.
  • the pre-processing module 104 may be configured to, upon receiving the data from the sensing module 102, calculate various derivatives of the measured user data, including but not limited to simple averages (i.e., a mean(s)), weighted averages, standard deviations, etc.
  • Output from the pre-processing module 104 may be communicated to the beat detection module 106.
  • the beat detection module 106 may be configured to detect user heartbeats from the pre-processed ECG and PPG data. Additionally, the beat detection module 106 may be configured to detect ECG and PPG peaks to calculate amplitude -based and time-based features. This information may then be used by the features extraction module 108, discussed below.
  • Output from the pre-processing module 104 and/or the beat detection module 106 may be communicated to the features extraction module 108.
  • the features extraction module 108 may be any hardware device capable of executing instructions stored on a memory to process the data from the sensing module 102, the pre-processing module 104, and/or the beat detection module 106.
  • the features extraction module 108 may be a microprocessor, a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), or a similar type of device.
  • FPGA field programmable gate array
  • ASIC application-specific integrated circuit
  • the functionality described as being provided in part via software may instead be configured into the design of the ASICs and, as such, the associated software may be omitted.
  • the features extraction module 108 may be configured to generate at least one baroreflex sensitivity feature based on the ECG and PPG data.
  • the at least one baroreflex sensitivity feature may be then used to estimate the baroreflex sensitivity of a user.
  • the generated baroreflex sensitivity features may include at least one of QRS amplitude, sympathetic/parasympathetic tone, cycle length variability, plethysmography amplitude, ratio of the QRS amplitude to the plethysmography amplitude, heart rate variability, average time interval between heart beats, Sp0 2 , total spectral power, spectral power in different frequency bands, cardio-respiratory coupling (pulse transit time), and envelopes of the gathered data signals.
  • the gathered data may be sorted into individual temporal segments. These segments may be, for example, 1 minute in length, 30 seconds in length, 10 seconds in length, or some other time interval.
  • the generated barorefiex sensitivity feature(s) may be communicated to one or databases 110 for storage and/or to the BRS sensitivity estimation module 112 for analysis.
  • the database(s) 110 may store sensed data regarding the user including all extracted features, learned contextual parameters, previously calculated hypoxia indices, BRS sensitivity, and other parameters learned from the hypoxia detection system 100 related to one or more users.
  • the BRS sensitivity estimation module 112 may estimate BRS sensitivity of a user based on the barorefiex sensitivity features generated by the features extraction module 108.
  • the BRS sensitivity estimation module may be structured similarly to the features extraction module 108 described above.
  • the output of the BRS sensitivity estimation module 112 may be a value that represents how likely it is that a user has hypoxia or is at least at risk of hypoxia.
  • the output value may be a normalized value between 0 and 1, for example.
  • the context inference module 114 may analyze data that maybe indicative of the user's context. For example, if acceleration data gathered by an acceleration sensor indicates the user is moving quickly, the context inference module 114 may infer the user is engaging in strenuous activity such as exercise and that the user is at a higher risk of hypoxia. Similarly, if altitude data suggests the user is at a high altitude, the context inference module 114 may infer the user is at an increased risk of hypoxia.
  • the hypoxia detection module 116 may execute a trained hypoxia model to calculate a hypoxia index.
  • the hypoxia index may be based on the generated barorefiex sensitivity feature(s) as well as labeled data from the one or more database(s) 110.
  • the hypoxia detection module 116 may implement a machine learning approach that relies on deep neural network or logistic regression techniques. Additionally, the hypoxia detection module 116 may consider input from the context inference module 114 to consider the user's context when calculating the hypoxia index and account for any increased context-based risk.
  • the hypoxia detection module 116 may combine the received data from the various sources using an ensemble learning method such as boosting or stacking. This in turn produces a hypoxia index that is adjusted for the risk associated with the user's environmental context.
  • the communications user interface 118 may deliver relevant information to the user as well as to other interested parties. This information may include whether or not the user, based on the processed data and the calculated hypoxia index, is at least at risk of hypoxia. This information may be presented in the form of a textual message, visual message, audio message, haptic-based message, or some combination thereof.
  • FIG. 2 illustrates exemplary user interfaces 202 and 204 that may present indicia 206 and 208, respectively, that informs a user 210 about their hypoxia risk.
  • interface 202 is configured as a watch device and interface 204 is configured as a smartphone device executing a web page or a smartphone application.
  • FIG. 2 also shows wearable sensor devices 212 and 214 for gathering ECG and PPG data, respectively.
  • the patch sensor 212 and the smart watch 214 are merely exemplary.
  • the systems and methods according to various embodiments may leverage any other types of sensor device(s) that measure ECG and PPG.
  • the interfaces 202 and 204 may also present data regarding specific features of the user's health.
  • the interfaces 202 and 204 may display measurements related to the user's cardiovascular system such as heart rate, RR (cycle length) variability, BRS, and Sp0 2 .
  • hypoxia index and other data regarding a user may be communicated to other interested parties.
  • interested parties may include, for example, medical personnel, an accompanying first-responder and/or a supervisor or anyone else with access to a suitable interface.
  • FIG. 3 depicts a flowchart of a method 300 for detecting hypoxia in accordance with one embodiment.
  • Step 302 involves receiving ECG data of a user.
  • the ECG data may be gathered by a wearable device such as a smartwatch or other type of wearable sensor device.
  • Step 304 involves receiving PPG data of the user.
  • the PPG data may be gathered by a a smartwatch or other type of wearable sensor device.
  • Step 306 involves generating at least one baroreflex sensitivity feature. This step may be performed by the features extraction module 108 of FIG. 1, for example.
  • Generated baroreflex sensitivity features may include at least one of QRS amplitude, sympathetic/parasympathetic tone, cycle length variability, plethysmography amplitude, ratio of the QRS amplitude to the plethysmography amplitude, heart rate variability, average time interval between heart beats, Sp0 2 , total spectral power, spectral power in different frequency bands, cardio-respiratory coupling (pulse transit time), and envelopes of the gathered data signals.
  • Step 308 involves computing a hypoxia index. This step may be performed by the hypoxia detection module 116 of FIG. 1 , for example.
  • the hypoxia detection module 116 may compute a hypoxia index for each interval in which ECG data and PPG data are gathered. For example, if an ECG and PPG reading are gathered once every ten seconds, then a hypoxia index may be computed once every ten seconds. Effectively, the method 300 of FIG. 3 may be repeated multiple times over multiple time intervals.
  • Step 310 involves presenting a notification.
  • This notification may be presented by a communications user interface such as the interfaces 202 and 204 of FIG. 2.
  • the notification may be made by any suitable technique (e.g., auditory, visual, etc.), and may be presented if a hypoxia index exceeds a predetermined threshold thereby indicating a user at risk of hypoxia. Or, in other embodiments, a notification may be presented only if the hypoxia index exceeds a threshold after a certain number of consecutive readings. In yet other embodiments, machine learning techniques may be applied to recognize readings that are abnormal for a particular user and may be indicative of hypoxia for that user.
  • FIG. 4 illustrates an exemplary hardware device 400 for detecting hypoxia in accordance with one embodiment.
  • the device 400 includes a processor 420, memory 430, user interface 440, network interface 450, and storage 460 interconnected via one or more system buses 410. It will be understood that FIG. 4 constitutes, in some respects, an abstraction and that the actual organization of the components of the device 400 may be more complex than illustrated.
  • the processor 420 may be any hardware device capable of executing instructions stored in memory 430 or storage 460 or otherwise capable of processing data.
  • the processor 420 may include a microprocessor, field programmable gate array (FPGA), application-specific integrated circuit (ASIC), or other similar devices.
  • the memory 430 may include various memories such as, for example LI, L2, or L3 cache or system memory. As such, the memory 430 may include static random access memory (SRAM), dynamic RAM (DRAM), flash memory, read only memory (ROM), or other similar memory devices.
  • SRAM static random access memory
  • DRAM dynamic RAM
  • ROM read only memory
  • the user interface 440 may include one or more devices for enabling communication with a user.
  • the user interface 440 may include a display, a mouse, and a keyboard for receiving user commands.
  • the user interface 440 may include a command line interface or graphical user interface that may be presented to a remote terminal via the network interface 450.
  • the network interface 450 may include one or more devices for enabling communication with other hardware devices.
  • the network interface 450 may include a network interface card (NIC) configured to communicate according to the Ethernet protocol.
  • the network interface 450 may implement a TCP/IP stack for communication according to the TCP/IP protocols.
  • NIC network interface card
  • TCP/IP stack for communication according to the TCP/IP protocols.
  • the storage 460 may include one or more machine-readable storage media such as read-only memory (ROM), random-access memory (RAM), magnetic disk storage media, optical storage media, flash-memory devices, or similar storage media.
  • ROM read-only memory
  • RAM random-access memory
  • magnetic disk storage media such as magnetic tape, magnetic disks, optical disks, flash-memory devices, or similar storage media.
  • the storage 460 may store instructions for execution by the processor 420 or data upon with the processor 420 may operate.
  • the storage 460 may include an operating system 461 that includes: a sensing module 462 for at least gathering ECG and PPG data of a user; a pre-processing module 463 for denoising, filtering, or detrending the gathered data; a beat detection module 464 for, among other things, detecting ECG and PPG peaks; a feature extraction module 465 for generating at least one baroreflex sensitivity feature; a BRS sensitivity module 466 for detecting BRS sensitivity; a context inference module 467 for inferring the context of a user; and a hypoxia detection module 468 for calculating hypoxia indices.
  • an operating system 461 that includes: a sensing module 462 for at least gathering ECG and PPG data of a user; a pre-processing module 463 for denoising, filtering, or detrending the gathered data; a beat detection module 464 for, among other things, detecting ECG and PPG peaks; a feature extraction module 465 for generating at least one
  • Embodiments of the present disclosure are described above with reference to block diagrams and/or operational illustrations of methods, systems, and computer program products according to embodiments of the present disclosure.
  • the functions/acts noted in the blocks may occur out of the order as shown in any flowchart.
  • two blocks shown in succession may in fact be executed substantially concurrent or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
  • not all of the blocks shown in any flowchart need to be performed and/or executed. For example, if a given flowchart has five blocks containing functions/acts, it may be the case that only three of the five blocks are performed and/or executed. In this example, any of the three of the five blocks may be performed and/or executed.
  • a statement that a value exceeds (or is more than) a first threshold value is equivalent to a statement that the value meets or exceeds a second threshold value that is slightly greater than the first threshold value, e.g., the second threshold value being one value higher than the first threshold value in the resolution of a relevant system.
  • a statement that a value is less than (or is within) a first threshold value is equivalent to a statement that the value is less than or equal to a second threshold value that is slightly lower than the first threshold value, e.g., the second threshold value being one value lower than the first threshold value in the resolution of the relevant system.

Landscapes

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

Abstract

L'invention concerne des procédés et des systèmes de détection d'hypoxie basés sur la sensibilité du baroréflexe (BRS). Le système selon divers modes de réalisation de l'invention peut comprendre des dispositifs de capteur pouvant être portés pour recueillir des données d'électrocardiographie et des données de pléthysmographie d'un utilisateur. Le système peut ensuite générer une ou plusieurs caractéristiques de sensibilité du baroréflexe sur la base des données recueillies. Un module de détection d'hypoxie peut considérer les caractéristiques de sensibilité du baroréflexe générées et le contexte de l'utilisateur pour déterminer si l'utilisateur est à risque d'hypoxie.
PCT/EP2018/066531 2017-06-22 2018-06-21 Détection d'hypoxie WO2018234427A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US201762523486P 2017-06-22 2017-06-22
US62/523,486 2017-06-22

Publications (1)

Publication Number Publication Date
WO2018234427A1 true WO2018234427A1 (fr) 2018-12-27

Family

ID=63012973

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2018/066531 WO2018234427A1 (fr) 2017-06-22 2018-06-21 Détection d'hypoxie

Country Status (1)

Country Link
WO (1) WO2018234427A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2598215A (en) * 2020-08-19 2022-02-23 Halare Inc Systems, methods and apparatuses for monitoring hypoxic events

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030216658A1 (en) * 2002-05-15 2003-11-20 Colin Corporation Fetal-pulse-wave-velocity-related-information obtaining apparatus and childbirth monitoring apparatus
US20110301436A1 (en) * 2009-04-22 2011-12-08 Teixeira Rodrigo E Apparatus for processing physiological sensor data using a physiological model and method of operation therefor
US20140123980A1 (en) * 2012-11-06 2014-05-08 Clarkson University Automated Hypoxia Recovery System
US20160113838A1 (en) * 2013-05-07 2016-04-28 President And Fellows Of Havard College Systems and methods for inhibiting apneic and hypoxic events
US20170049336A1 (en) * 2014-05-01 2017-02-23 Reveal Biosensors, Inc. Physiological sensors, systems, kits and methods therefor

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030216658A1 (en) * 2002-05-15 2003-11-20 Colin Corporation Fetal-pulse-wave-velocity-related-information obtaining apparatus and childbirth monitoring apparatus
US20110301436A1 (en) * 2009-04-22 2011-12-08 Teixeira Rodrigo E Apparatus for processing physiological sensor data using a physiological model and method of operation therefor
US20140123980A1 (en) * 2012-11-06 2014-05-08 Clarkson University Automated Hypoxia Recovery System
US20160113838A1 (en) * 2013-05-07 2016-04-28 President And Fellows Of Havard College Systems and methods for inhibiting apneic and hypoxic events
US20170049336A1 (en) * 2014-05-01 2017-02-23 Reveal Biosensors, Inc. Physiological sensors, systems, kits and methods therefor

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2598215A (en) * 2020-08-19 2022-02-23 Halare Inc Systems, methods and apparatuses for monitoring hypoxic events

Similar Documents

Publication Publication Date Title
US10750960B2 (en) Passive arrythmias detection based on photoplethysmogram (PPG) inter-beat intervals and morphology
EP3600018B1 (fr) Détermination de l'emplacement d'une artère à l'aide d'une détection basée sur une caméra
EP2944251B1 (fr) Procédé, dispositif et support lisible par ordinateur de détermination de niveau de confiance hr ambulatoire basé sur un algorithme classificateur de rythme à trois voies
EP2931120B1 (fr) Système et procédé pour détecter des événements arythmiques importants à l'aide d'un photopléthysmographe (ppg) et d'un accéléromètre
EP2829223B1 (fr) Surveillance de paramètres physiologiques
US20200138306A1 (en) Feature selection for cardiac arrhythmia classification and screening
US11006874B2 (en) Real-time stress determination of an individual
WO2017040331A1 (fr) Détermination de phases de sommeil et d'événements de sommeil à l'aide de données de capteur
JP2005021450A (ja) 生体状態分析装置及び生体状態分析方法
US11412978B2 (en) Information processing system and program
US11432778B2 (en) Methods and systems for patient monitoring
CN104434312B (zh) 监护设备及其生理参数处理方法与系统
US11617545B2 (en) Methods and systems for adaptable presentation of sensor data
CN109674474B (zh) 睡眠呼吸暂停识别方法、设备及计算机可读介质
US20240099665A1 (en) Electrocardiogram data processing server, electrocardiogram data processing method of extracting analysis required section while segmenting electrocardiogram signal into signal segments with variable window sizes, and computer program
US20220183608A1 (en) Non-invasive continuous heart rhythm monitoring based on wearable sensors
CN114159038A (zh) 血压测量方法、装置、电子设备和可读存储介质
CN110200620A (zh) 多模态心脏数据检测方法、装置、存储介质及终端设备
WO2022087651A1 (fr) Surveillance de sujet
WO2018234427A1 (fr) Détection d'hypoxie
US20220270751A1 (en) An event-driven spiking neutral network system for detection of physiological conditions
US20240057925A1 (en) Health Monitoring and Management System Using Ectopic Beats as Early Cardiac Health Marker
EP3821798A1 (fr) Procédé de génération de modèle formé, système de génération de modèle formé, programme et appareil d'estimation
Gonzalez et al. Signal quality for rr interval prediction on wearable sensors
US11399775B2 (en) Systems and methods to detect cardiac events

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: 18745497

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18745497

Country of ref document: EP

Kind code of ref document: A1