System and method for estimating respiratory rate of a subject wearing an instant heart rate monitor

Abstract

A method and system are provided for estimating the respiratory rate of a subject using a wearable real-time heart rate monitor. The method includes receiving heart rate data indicating the subject from the real-time heart rate monitor; determining a heartbeat annotation of the heart rate based on the received data; filtering the heartbeat annotation to remove outliers from the heart rate; determining an IBI sequence based on the filtered heartbeat annotation; determining the power spectral density of the determined IBI sequence; inputting the power spectral density, a lower limit estimate of the respiratory rate, and an upper limit estimate of the respiratory rate into a respiratory rate estimation algorithm; using the respiratory rate estimation algorithm to determine the peak energy and maximum frequency energy of the power spectral density; and outputting an estimated respiratory rate by fusing the peak energy and maximum frequency energy using the respiratory rate estimation algorithm.

Description

Government Licensing Rights Statement

[0001] This invention was made with government support under contract numbers HQ0034209PT04 and HDTRA121C0006 granted by the Defense Threat Reduction Agency (DTRA) of the Department of Defense. The government holds certain rights to this invention. Background Technology

[0002] Breathing has been shown to be an important factor in infection prediction algorithms used to predict the presence and spread of infectious diseases such as COVID and hospital-acquired infections, as well as for respiratory disease detection in chronic respiratory diseases such as asthma and chronic obstructive pulmonary disease (COPD) and acute respiratory disorders (ARDS). Breathing is also considered in chemical exposure algorithms.

[0003] Specifically, for medical diagnosis, there are various methods to measure respiratory rate. However, accurate respiratory measurement involves large and expensive monitors, requiring the patient to be largely immobile. Routine respiratory monitoring methods include flow-based monitoring from a ventilator or non-invasive nasal cannula for carbon dioxide recording, and monitoring of impedance changes due to respiration from a medical-grade multi-lead electrocardiogram (ECG). Wearable monitors would be preferred, but robustly measuring respiratory rate using wearable monitors remains challenging. Summary of the Invention

[0004] According to a representative embodiment, a method is provided for estimating the respiratory rate of a subject wearing a wearable real-time heart rate monitor. The method includes: receiving heart rate data indicating the subject from the wearable real-time heart rate monitor; determining a heartbeat annotation of the heart rate based on the received data; filtering the heartbeat annotation to remove outlier real-time heart rates from the received data; determining an inter-beat interval (IBI) time series based on the filtered heartbeat annotation; determining the power spectral density of the determined IBI time series; determining the peak energy and maximum frequency energy of the power spectral density within a lower and upper bound estimate of the respiratory rate using a respiratory rate estimation algorithm; determining an estimated respiratory rate by fusing the peak energy and maximum frequency energy using the respiratory rate estimation algorithm; and generating the patient's respiratory rate for display based on the estimated respiratory rate.

[0005] According to another representative embodiment, a system for estimating the respiratory rate of a subject is provided. The system includes: a wearable real-time heart rate monitor configured to collect data indicating the heart rate of a subject; a processing unit configured to receive data from the wearable real-time heart rate monitor; and a memory storing a respiratory rate estimation algorithm and instructions. When executed by the processing unit, the instructions cause the processing unit to determine a heartbeat annotation of the heart rate based on the received data; filter the heartbeat annotation to remove outlier real-time heart rates from the received data; determine an IBI time series based on the filtered heartbeat annotation; determine the power spectral density of the determined IBI time series; and execute the respiratory rate estimation algorithm. The respiratory rate estimation algorithm is configured to take the power spectral density, a lower bound estimate of the respiratory rate, and an upper bound estimate of the respiratory rate as inputs; determine the peak energy and maximum frequency energy of the power spectral density within the lower bound estimate and the upper bound estimate using the respiratory rate estimation algorithm; and output an estimated respiratory rate by fusing the peak energy and the maximum frequency energy using the respiratory rate estimation algorithm; and generate the patient's respiratory rate based on the estimated respiratory rate.

[0006] According to another representative embodiment, a non-transient computer-readable medium stores instructions for estimating the respiratory rate of an object. When executed by one or more processors, the one or more processors cause the processors to: receive data from a wearable real-time heart rate monitor, wherein the wearable real-time heart rate monitor is worn by the object and configured to collect data indicating the object's heart rate; receive heartbeat annotations of the heart rate in the received data; filter the heartbeat annotations to remove outlier real-time heart rates from the received data; determine an IBI sequence based on the filtered heartbeat annotations; determine the power spectral density of the determined IBI sequence; determine the peak energy and maximum frequency energy of the power spectral density within a lower and upper bound estimate of the respiratory rate using a respiratory rate estimation algorithm; determine an estimated respiratory rate by fusing the peak energy and maximum frequency energy using the respiratory rate estimation algorithm; and generate the patient's respiratory rate based on the estimated respiratory rate. Attached Figure Description

[0007] When combined with attachment Figure 1 When reading this, the exemplary embodiments are best understood in light of the following specific implementation. It should be emphasized that the various features are not necessarily drawn to scale. In fact, dimensions may be increased or decreased arbitrarily for clarity of discussion. Similar reference numerals refer to similar elements, provided they are applicable and practical.

[0008] Figure 1 This is a simplified block diagram of a system for estimating the respiratory rate of an object wearing a wearable real-time heart rate monitor, according to a representative embodiment.

[0009] Figure 2A representative IBI time series and a representative power spectral density calculated from the IBI time series are shown according to a representative embodiment.

[0010] Figure 3 This illustrates a representative embodiment from the following: Figure 2 A graph of the representative respiratory rate of the object derived from the power spectral density calculated by IBI time series.

[0011] Figure 4 This is a flowchart of a method for estimating the respiratory rate of an object wearing a wearable real-time heart rate monitor, according to a representative embodiment. Detailed Implementation

[0012] In the following detailed description, representative embodiments with specific details disclosed are set forth for purposes of explanation and not limitation, in order to provide a thorough understanding of embodiments according to this teaching. Descriptions of known systems, devices, materials, methods of operation, and methods of manufacture may be omitted to avoid obscuring the description of representative embodiments. Nevertheless, systems, devices, materials, and methods within the knowledge of those skilled in the art are also within the scope of this teaching and may be used according to representative embodiments. It should be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. The defined terminology is supplementary to its technical and scientific meaning as commonly understood and accepted in the art field of this teaching.

[0013] It will be understood that although the terms first, second, third, etc., may be used herein to describe various elements or components, these elements or components should not be limited by these terms. These terms are used only to distinguish one element or component from another. Therefore, without departing from the teachings of the inventive concept, the first element or component discussed below may be referred to as the second element or component.

[0014] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used in the specification and claims, the singular terms “a,” “an,” and “the” are intended to include both the singular and plural forms unless the context expressly specifies otherwise. Furthermore, when used herein, the terms “comprising” and / or “including” and / or similar terms specify the presence of stated features, elements, and / or components, but do not exclude the presence or addition of one or more other features, elements, components, and / or groups thereof. As used herein, the term “and / or” includes any and all combinations of one or more of the associated listed items.

[0015] Unless otherwise stated, when an element or component is considered "connected to," "coupled to," or "proximity to" another element or component, it is understood that the element or component may be directly connected to or coupled to the other element or component, or that there may be intermediate elements or components. That is, these and similar terms cover situations where one or more intermediate elements or components may be used to connect two elements or components. However, when an element or component is considered "directly connected to" another element or component, this only covers situations where two elements or components are connected to each other without any intermediate or intermediary elements or components.

[0016] As used in the specification and appended claims, and in addition to their ordinary meaning, the terms "about" and "approximately" mean with an acceptable limitation or extent. For example, "about 2 MHz" means that a person skilled in the art would consider the signal to be 2 MHz within a reasonable measure. Furthermore, as used in the specification and appended claims, in addition to their ordinary meaning, the term "substantially" means within an acceptable limitation or extent. For example, the term "substantially simultaneously" means that a person skilled in the art would consider it to occur simultaneously.

[0017] In view of the foregoing, this disclosure is intended to present one or more of the advantages specifically pointed out below through its various aspects, embodiments, and / or specific features or sub-components. Example embodiments with specific details disclosed are set forth for purposes of explanation and not limitation in order to provide a thorough understanding of embodiments based on this teaching. However, other embodiments consistent with this disclosure that depart from the specific details disclosed herein remain within the scope of the claims. Furthermore, descriptions of well-known apparatuses and methods may be omitted so as not to obscure the description of the example embodiments. Such methods and apparatuses are within the scope of this disclosure.

[0018] Typically, various embodiments provide a process for estimating a subject's respiratory rate without using data from a respiratory monitor. Instead, the process relies on heart rate data received from a real-time heart rate monitor worn by the subject to generate an estimated respiratory rate. Therefore, various embodiments provide technical improvements to real-time heart rate monitoring systems to include respiratory rate determination.

[0019] Figure 1 This is a simplified block diagram of a system for estimating the respiratory rate of an object, according to a representative embodiment.

[0020] refer to Figure 1System 100 includes a workstation 105 for implementing and / or managing the process described herein for estimating the respiratory rate of a subject (patient) 150 using heart rate data from a wearable real-time heart rate monitor 140. The real-time heart rate monitor 140 may be, for example, an electrocardiogram (ECG) or photoplethysmography (PPG) monitoring device, but may include other types of cardiac monitoring devices capable of providing accurate heart rate data of the subject 150 via the wearable monitor without departing from the scope of this teaching. Other examples of the real-time heart rate monitor 140 include ePatch, available from Philips Koninklijke Philips NV. TM The Empatica Health Monitoring Platform is available from Empatica, the Oura Ring is available from Oura Health Oy, and the Zephyr® Chest Belt is available from Pulmonx.

[0021] Workstation 105 includes processor 120, memory 130, user interface 122, and display 124. Processor 120 communicates with real-time heart rate monitor 140 via a known monitor interface (not shown), which may include a wired or wireless connection (e.g., Wi-Fi, Bluetooth) for data transfer. Memory 130 stores instructions executable by processor 120. When executed, the instructions cause processor 120 to perform one or more procedures for estimating the respiratory rate of subject 150 using heart rate data acquired by wearable real-time heart rate monitor 140. In the context of this application, for example, the real-time heart rate data provided from real-time heart rate monitor 140 may be real-time or near real-time during the intervention procedure. For illustrative purposes, memory 130 is shown as including software modules, each software module including a set of instructions executable by processor 120 corresponding to an associated capability of system 100.

[0022] Processor 120 represents one or more processing devices and may be implemented using any combination of hardware, software, firmware, hardwired logic circuitry, or a general-purpose computer, central processing unit (CPU), digital signal processor (DSP), graphics processing unit (GPU), tensor processing unit (TPU), computer processor, microprocessor, state machine, programmable logic device, field-programmable gate array (FPGA), application-specific integrated circuit (ASIC), or other combinations thereof, employing hardware, software, firmware, hardwired logic circuitry, or other combinations thereof. Any processor or processing unit herein may include multiple processors, parallel processors, or both. Multiple processors may be included in or coupled to a single device or multiple devices. As used herein, the term "processor" encompasses an electronic component capable of executing a program or machine-executable instructions. A processor may also refer to a collection of processors within a single computer system or distributed across multiple computer systems, such as in cloud-based or other multi-site applications. A program has software instructions that are executed by one or more processors, which may be within a single computing device or distributed across multiple computing devices.

[0023] Memory 130 represents one or more memories and may include main memory and / or static memory, wherein such memories can communicate with each other and with processor 120 via one or more buses. Memory 130 may be implemented by, for example, any number, type, and combination of random access memory (RAM) and read-only memory (ROM), and may store various types of information, such as software algorithms, artificial intelligence (AI) models, machine learning models, and computer programs, all of which can be executed by processor 120. Various types of ROM and RAM may include any number, type, and combination of computer-readable storage media, such as disk drives, flash memory, electrically programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, removable disks, magnetic tapes, optical disc read-only memory (CD-ROM), digital universal disk (DVD), floppy disks, Blu-ray discs, universal serial bus (USB) drives, or any other form of storage media. Memory 130 is a tangible storage medium for storing data and executable software instructions, and is non-transient during the time the software instructions are stored therein. As used herein, the term "non-transient" should not be interpreted as a permanent property of a state, but rather as a property of a state that will last for a period of time. The term "non-transient" explicitly negates transient properties, such as carrier waves or signals, or other forms of properties that exist only temporarily at any time and place. Memory 130 may store software instructions and / or computer-readable code that enable the performance of various functions. Memory 130 may be secure and / or encrypted, or insecure and / or unencrypted.

[0024] System 100 may also include a database 112 for storing information that can be used by various software modules of memory 130. For example, database 112 may include heart rate data and associated respiratory data from previous monitoring of object 150 and / or from other similar locations with wearable real-time heart rate monitors. The stored data can be used to train machine learning models (algorithms), such as neural networks. Database 112 may be implemented using, for example, any number, type, and combination of RAM and ROM. Various types of ROM and RAM may include any number, type, and combination of computer-readable storage media, such as disk drives, flash memory, EPROM, EEPROM, registers, hard disks, removable disks, magnetic tape, CD-ROMs, DVDs, floppy disks, Blu-ray discs, USB drives, or any other form of storage media known in the art. Database 112 includes one or more tangible storage media for storing data and / or executable software instructions, and is non-transient during the time the data and software instructions are stored therein. Database 112 may be secure and / or encrypted, or insecure and / or unencrypted. For illustrative purposes, database 112 is shown as a separate storage medium, but it should be understood that it may be combined with and / or included in memory 130 without departing from the scope of this teaching.

[0025] Processor 120 may include or have access to an artificial intelligence (AI) engine, which may be implemented as software to provide artificial intelligence (e.g., machine learning models) and apply the machine learning described herein. For example, the AI ​​engine may reside in any component other than or different from processor 120, such as memory 130, an external server, and / or the cloud. When the AI ​​engine is implemented in the cloud (not shown) (e.g., at a data center), for example, the AI ​​engine may be connected to processor 120 via the Internet or other communication networks using one or more wired and / or wireless connections.

[0026] User interface 122 is configured to provide a user with information and data output from processor 120, memory 130, and / or real-time heart rate monitor 140, and / or to receive information and data input by the user. That is, user interface 122 enables the user to input data and control or manipulate aspects of the processes described herein, and also enables processor 120 to indicate the effect of the user's input. All or part of user interface 122 may be implemented by a graphical user interface (GUI) (such as GUI 128 viewable on display 124), as described below. User interface 122 may include one or more interface devices, such as a mouse, keyboard, trackball, joystick, microphone, camera, touchpad, touchscreen, or voice or gesture recognition captured by a microphone or camera.

[0027] For example, display 124 can be a monitor, such as a computer monitor, television, liquid crystal display (LCD), organic light-emitting diode (OLED), flat panel display, solid-state display, or cathode ray tube (CRT) display or electronic whiteboard. Display 124 includes screen 126 for viewing information about object 150, including visualizations of heart rate, such as ECG or PPG traces from real-time heart rate monitor 140, and various features described herein to convey estimated respiratory rate to the user, as well as predicted ailments that may be associated with cardiac monitoring and recommendations for subsequent movement types. Screen 126 also enables viewing of GUI 128 to allow the user to interact with the displayed images and features.

[0028] Reference memory 130, in which various modules store data and instruction sets executable by processor 120 to determine estimates of respiration, as described above. Cardiac data module 131 is configured to receive and process data indicating, for example, the heart rate of subject 150 collected over a period of time. The heart rate data can be non-invasively acquired by wearable real-time heart rate monitor 140 as discussed herein, and can be received in real-time or near real-time during active monitoring or during simultaneous intervention with subject 150. Indications of heart rate (e.g., traces, graphs, numbers) can be displayed on display 124 based on the heart rate data.

[0029] The heartbeat annotation module 132 is configured to determine heartbeat annotations for the received heart rate data. Heartbeat annotations are labels assigned to data indicating heart rate, describing an event at a specific location in the data, such as an R-peak in an ECG signal. Locations can be automatically identified, for example, using a peak detector, or manually identified by the user via user interface 122. The heartbeat annotations themselves can be added automatically, for example, by the device vendor or by known heartbeat annotation software. For example, when the heart rate data includes ECG or PPG signals, heartbeat annotations can be added to indicate the location and / or time of the event and the type of individual heartbeat. For example, when the heart rate data includes signals from an Oura ring, annotations indicating the location and / or time of the event and the type of heartbeat are already included in the heartbeat file and can therefore be extracted from the heartbeat file rather than added.

[0030] The heartbeat annotation module 132 can also filter heartbeat annotations for quality control to remove outliers or unreliable instantaneous heart rates in humans. Filtering is based on minimum and maximum physiologically feasible instantaneous heart rates that are previously set or can be customized to lower and upper thresholds, respectively, to identify and remove outlier instantaneous heart rates. The lower and upper thresholds can be adjusted in practical settings suitable for the intended use case and population. For example, the lower threshold could be 45 bpm, and the upper threshold could be 115 bpm.

[0031] IBI module 133 is configured to determine an IBI time series based on filtered heartbeat annotations provided by heartbeat annotation module 132. The IBI sequence provides timing between heartbeats and can be determined by accumulating filtered heartbeat annotations over a predetermined time period. The unit of the IBI time series can be seconds. IBI module 133 is also configured to determine the power spectral density of the determined IBI time series. In a separate embodiment, the power spectral density can be calculated by applying a Lomb-Scargle periodogram to, for example, the IBI time series over a predetermined time period. The application of the Lomb-Scargle periodogram allows for irregularly sampled data. Other techniques (e.g., dictionary learning techniques with Fourier or wavelet dictionaries) can be applied without departing from the scope of this teaching to calculate the power spectral density from the IBI time series, and optimization can be used to estimate the power spectral density, as will be apparent to those skilled in the art. Such determination of the power spectral density cannot be performed in the human mind. The power spectral density indicates the peak and maximum frequencies in the frequency band corresponding to the breathing modulation from the IBI time series.

[0032] Figure 2 A representative IBI time series 210, determined by IBI module 133 according to a representative embodiment, and a representative power spectral density 220 calculated from IBI time series 210 are illustrated. Crossovers in IBI time series 210 indicate the instantaneous heart rate at which a peak is detected within a one-minute time interval. Power spectral density 220 shows the frequency in Hz at a time interval (a “slice”) of IBI time series 210 within the same time interval. Box 225 indicates the frequency corresponding to the respiratory modulation of the subject, wherein box 225 is defined by lower and upper bound estimates of the respiratory rate. In the depicted example, the lower bound estimate of the respiratory rate is approximately 0.20 Hz, and the upper bound estimate of the respiratory rate is approximately 0.40 Hz, which corresponds to a lower bound estimate of approximately 12 respiratory rates per minute and an upper bound estimate of approximately 24 respiratory rates per minute. Of course, without departing from the scope of this teaching, the lower and upper bound estimates can be adjusted by the user to a specific population. The lower and upper bound estimates can be determined based on physically feasible respiratory rates and population variance. For example, statistically, children have a higher respiratory rate than adults. In the depicted example, the peak frequency is at approximately 0.32 Hz, as indicated by the brighter portion of the power spectral density. It is worth noting that the peak energy may differ from the maximum frequency energy discussed below. Similar power spectral densities were determined at other times in the IBI time series 210 to provide a complete representation of the power spectral density.

[0033] The respiratory rate (RR) estimation module 134 is configured to apply a respiratory rate algorithm to estimate the respiratory rate of the object 150 based on the power spectral density. For example, the respiratory rate algorithm could be a signal processing algorithm. The respiratory rate algorithm receives the power spectral density, a lower bound estimate of the respiratory rate, and an upper bound estimate of the respiratory rate, and automatically determines both the peak energy and the maximum frequency energy of the power spectral density within the lower and upper bound estimates of the respiratory rate at each time interval or slice. For example, the peak energy can be determined by a peak-finding algorithm that uses the second derivative of the power spectral density curve to determine the peak location (peak frequency). Other peak-finding algorithms can be applied without departing from the scope of this teaching. The maximum frequency energy can be determined by finding a local maximum of the power spectral density.

[0034] The respiratory rate algorithm automatically fuses peak energy and maximum frequency energy at each time interval or slice to output an estimated respiratory rate. Fusing peak energy and maximum frequency energy may include determining whether the maximum frequency energy is above either the lower or upper bound estimate of the respiratory rate. If not, the maximum frequency energy is used as the estimated respiratory rate for that time interval or slice. When the maximum frequency energy is above either the lower or upper bound estimate of the respiratory rate, the peak energy is used as the estimated respiratory rate for that time interval or slice. Alternatively, the peak energy and maximum frequency energy may be weighted to arrive at an estimated respiratory rate that is a weighted combination of the two values. At least the above aspects of the respiratory rate algorithm cannot be practically performed in the human mind. The estimated respiratory rate corresponds to the respiratory rate of subject 150. Typically, the respiratory rate is about two to three times slower than the heart rate.

[0035] For example, the breathing rate algorithm also generates the breathing rate of object 150 by multiplying the estimated breathing frequency by 60 for display on display 124. Figure 3 Instructions according to a representative embodiment are shown from... Figure 2 A graph 330 shows the representative respiratory rate of the subject estimated by the power spectral density 220 calculated from the IBI time series. The respiratory rate is shown as respiratory counts per minute over a time span of 1050 seconds. In the depicted example, the respiratory rate ranges between an upper limit of approximately 24.7 respiratory counts per minute (brpm) and a lower limit of approximately 13.0 brpm. Unlike conventional respiratory rate determination techniques that rely on monitor values, the estimated respiratory rate according to the representative embodiment can be determined using only a wearable real-time heart rate monitor without a respiratory monitor, achieving reliable results.

[0036] Figure 4 This is a flowchart of a method for estimating the respiratory rate of a subject wearing a wearable real-time heart rate monitor, according to a representative embodiment. Figure 4This can be implemented at least in part by the processor 120 of the workstation 105, which, for example, executes instructions stored in the memory 130.

[0037] refer to Figure 4 In box S411, heart rate data of the indicated subject is received from the wearable real-time heart rate monitor. The wearable real-time heart rate monitor can be any device that can be attached to the subject and is capable of collecting heart rate data of the indicated subject, such as an ECG monitor or PPG monitor. Data can be received via a wireless or wired interface with the wearable real-time heart rate monitor. Other examples of wearable heart rate monitors include ePatch as described above. TM Empatica health monitoring platform, Oura ring, and Zephyr® chest strap.

[0038] In box S412, a heartbeat annotation is determined based on the received data. For example, when the data includes ECG or PPG signals, a heartbeat annotation can be added to indicate the location and / or time of the event and the type of individual heartbeat. The location can be automatically identified, for example, using a peak detector, or manually identified by the user via a user interface. For example, when the data includes Oura ring signals, the annotation can be extracted from the heartbeat file received along with data from the Oura ring.

[0039] In block S413, the heartbeat annotations are filtered to remove outliers or unreliable instantaneous heart rates from humans, thereby improving quality. Filtering involves receiving the minimum and maximum physiologically feasible instantaneous heart rates as lower and upper thresholds, respectively, and removing instantaneous heart rates exceeding these thresholds.

[0040] In box S414, the IBI time series is determined based on the filtered heartbeat annotations. The IBI series provides timing between heartbeats and can be determined by accumulating heartbeat annotations over a predetermined time period.

[0041] In box S415, the power spectral density of the determined IBI time series is calculated. The power spectral density can be calculated by applying a Lomb-Scargle periodogram to the IBI time series, for example, over a predetermined time period. Other techniques can be used to calculate the power spectral density, such as dictionary learning using Fourier or wavelet dictionaries and using optimization to estimate the power spectral density.

[0042] In box S416, the peak energy and maximum frequency energy of the power spectral density are automatically determined within the lower and upper bound estimates of the respiratory rate at each time point in the IBI time series using a respiratory rate estimation algorithm. As mentioned above, the peak energy can be determined by detecting the peak frequency of the second derivative of the power spectral density curve, and the maximum frequency energy can be determined by finding the local maxima of the power spectral density.

[0043] In block S417, a respiratory rate estimation algorithm automatically fuses peak energy and maximum frequency energy at each time step to output an estimated respiratory rate. Peak energy and maximum frequency energy correspond to the object's respiratory rate. Fusing peak energy and maximum frequency energy may include: using the maximum frequency energy as the estimated respiratory rate at each time step where the maximum frequency energy is not at either the lower or upper bound estimate, and using the peak energy as the estimated respiratory rate at each time step where the maximum frequency energy is at either the lower or upper bound estimate. Alternatively, fusing peak energy and maximum frequency energy may include weighting the values ​​of peak energy and maximum frequency energy at each time step and combining the weighted values ​​to form the estimated respiratory rate.

[0044] In box S418, the patient's respiratory rate is generated for display. The respiratory rate can be generated by multiplying the estimated respiratory rate by 60.

[0045] Although this specification describes components and functions that may be implemented in specific embodiments with reference to particular standards and protocols, this disclosure is not limited to such standards and protocols. Such standards are periodically replaced by more effective equivalents with substantially the same functionality. Therefore, alternative standards and protocols with the same or similar functionality are considered their equivalents.

[0046] The illustrations of the embodiments described herein are intended to provide a general understanding of the structure of the various embodiments. These illustrations are not intended to be a complete description of all elements and features of the disclosure described herein. Many other embodiments will be apparent to those skilled in the art upon viewing this disclosure. Other embodiments can be utilized and derived from this disclosure, allowing structural and logical substitutions and changes to be made without departing from the scope of this disclosure. Furthermore, the illustrations are merely representative and may not be drawn to scale. Some scales within the illustrations may be exaggerated, while others may be minimized. Therefore, this disclosure and the accompanying drawings should be considered illustrative rather than restrictive.

[0047] One or more embodiments of this disclosure may be referred to individually and / or collectively by the term "invention" herein, merely for convenience and not intended to voluntarily limit the scope of this application to any particular invention or inventive concept. Furthermore, although specific embodiments have been illustrated and described herein, it should be appreciated that any subsequent arrangements designed to achieve the same or similar purpose may replace the specific embodiments shown. This disclosure is intended to cover any and all subsequent modifications or variations of the various embodiments. After reviewing this specification, combinations of the above embodiments and other embodiments not specifically described herein will be apparent to those skilled in the art.

[0048] This abstract of disclosure is provided in accordance with 37 C. FR § 1.72(b) and is submitted with the understanding that it is not intended to interpret or limit the scope or meaning of the claims. Furthermore, in the foregoing detailed description, various features may be grouped together or described in a single embodiment for the purpose of simplifying this disclosure. This disclosure should not be construed as reflecting an intention that the claimed embodiments require more features than expressly recited in each claim. Rather, as reflected in the following claims, the inventive subject matter may relate to fewer features than all of any of the disclosed embodiments. Therefore, the following claims are incorporated into the detailed description, each claim serving as itself to define a separately claimed subject matter.

[0049] The prior description of the disclosed embodiments is provided to enable any person skilled in the art to practice the concepts described in this disclosure. Thus, the subject matter of the above disclosure should be considered illustrative rather than restrictive, and the claims are intended to cover all such modifications, enhancements, and other embodiments falling within the true spirit and scope of this disclosure. Therefore, to the maximum extent permitted by law, the scope of this disclosure shall be determined by the broadest permissible interpretation of the claims and their equivalents, and should not be construed as limited or restricted by the foregoing detailed description.

Claims

1. A method for estimating the respiratory rate of a subject wearing a wearable real-time heart rate monitor, the method comprising: Receive data indicating the object's heart rate from the wearable real-time heart rate monitor; The heart rate annotation is determined based on the received data; The heartbeat annotations are filtered to remove outliers, i.e., heart rates, from the received data; The inter-heartbeat interval (IBI) sequence was determined based on the filtered heartbeat annotations; Determine the power spectral density of the determined IBI sequence; The peak energy and maximum frequency energy of the power spectral density are determined using a respiratory rate estimation algorithm within the lower and upper bound estimates of the respiratory rate. The estimated respiratory rate is determined by fusing the peak energy and the maximum frequency energy using the respiratory rate estimation algorithm. and The patient's respiratory rate is generated based on the estimated respiratory rate for display.

2. The method of claim 1, wherein, Generating the patient's respiratory rate involves multiplying the estimated respiratory rate by 60.

3. The method of claim 1, wherein, When the real-time heart rate monitor is an electrocardiogram (ECG) device or a photoplethysmography (PPG) device, the heartbeat annotation is determined to include annotating the received data based on the ECG waveform or the PPG waveform, respectively.

4. The method according to claim 1, wherein, Filtering the heartbeat annotations includes: Input the minimum physiologically feasible instantaneous heart rate and the maximum physiologically feasible instantaneous heart rate; and Remove instantaneous heart rates that are below the minimum physiologically feasible instantaneous heart rate and above the maximum physiologically feasible instantaneous heart rate.

5. The method according to claim 4, further comprising: Adjust at least one of the minimum physiologically feasible instantaneous heart rate and the maximum physiologically feasible instantaneous heart rate for filtering the heart, based on the intended use case and / or patient population.

6. The method according to claim 1, wherein, The IBI sequence is determined based on the filtered heartbeat annotations, including: The heartbeat annotations within the predetermined time period are accumulated.

7. The method according to claim 1, further comprising: The lower limit estimate or the upper limit estimate is adjusted based on the patient population.

8. A system for estimating the respiratory rate of a subject, the system comprising: A wearable real-time heart rate monitor, configured to collect data indicating the heart rate of the subject; A processing unit configured to receive the data from the wearable real-time heart rate monitor; as well as A memory storing a respiratory rate estimation algorithm and instructions, the instructions causing the processing unit, when executed by the processing unit, to: The heart rate annotation is determined based on the received data; The heartbeat annotations are filtered to remove outliers, i.e., heart rates, from the received data; The inter-heartbeat interval (IBI) sequence was determined based on the filtered heartbeat annotations; Determine the power spectral density of the determined IBI sequence; Input the lower limit estimate of the respiratory rate and the upper limit estimate of the respiratory rate; The peak energy and maximum frequency energy of the power spectral density are determined within the lower limit estimate and the upper limit estimate of the respiratory rate using a respiratory rate estimation algorithm. The estimated respiratory rate is determined by fusing the peak energy and the maximum frequency energy using the respiratory rate estimation algorithm. and The patient's respiratory rate is generated based on the estimated respiratory rate.

9. The system according to claim 8, further comprising: A user interface is configured to allow a user to input the lower bound estimate of the respiratory rate and the upper bound estimate of the respiratory rate into the processing unit for application to the respiratory rate estimation algorithm.

10. The system according to claim 8, wherein, When the wearable real-time heart rate monitor includes an electrocardiogram (ECG) device, and wherein the instructions cause the processing unit to determine the heartbeat annotation by annotating the received data based on an ECG waveform provided by the ECG device.

11. The system according to claim 8, wherein, When the wearable real-time heart rate monitor includes an optical volumetric plethysmography (PPG) device, and wherein the instructions cause the processing unit to determine the heartbeat annotation by annotating the received data based on a PPG waveform provided by the PPG device.

12. The system according to claim 8, wherein, The instruction causes the processing unit to determine the IBI sequence based on the filtered heartbeat annotations by accumulating the heartbeat annotations over a predetermined time period.

13. The system according to claim 8, wherein, The instructions cause the processing unit to determine the power spectral density by applying a Lomb-Scargle periodogram to the IBI sequence.

14. The system according to claim 8, wherein, The instruction causes the processing unit to filter the heartbeat annotations by performing the following operations: Receive the minimum physiologically feasible instantaneous heart rate and the maximum physiologically feasible instantaneous heart rate; and Remove instantaneous heart rates that are below the minimum physiologically feasible instantaneous heart rate and above the maximum physiologically feasible instantaneous heart rate.

15. A non-transient computer-readable medium storing instructions for estimating the respiratory rate of an object, the instructions causing the one or more processors, when executed by one or more processors, to: Data is received from a wearable real-time heart rate monitor, among which... The wearable real-time heart rate monitor is worn by the subject and configured to collect data indicating the subject's heart rate; The heart rate annotation received from the received data; The heartbeat annotations are filtered to remove outliers, i.e., heart rates, from the received data; The inter-heartbeat interval (IBI) sequence was determined based on the filtered heartbeat annotations; Determine the power spectral density of the determined IBI sequence; The peak energy and maximum frequency energy of the power spectral density are determined using a respiratory rate estimation algorithm within the lower and upper bound estimates of the respiratory rate. The estimated respiratory rate is determined by fusing the peak energy and the maximum frequency energy using the respiratory rate estimation algorithm. and The patient's respiratory rate is generated based on the estimated respiratory rate.

Images