System and method for estimating respiration rate of subject wearing instant heart rate monitor

Abstract

A method and system are provided for estimating the respiration rate of a subject using a wearable instant heart rate monitor. The method includes receiving data indicating heart rates of the subject from the instant heart rate monitor; determining beat annotations of the heart rates from the received data; filtering the beat annotations to remove outlier instant heart rates from the heart rate; determining an IBI series from filtered beat annotations; determining power spectrum density of the determined IBI series; inputting the power spectrum density, a lower bound estimation of the respiration rate and an upper bound estimation of the respiration rate to a respiratory rate estimation algorithm; determining peak energy and maximum frequency energy of the power spectrum density using the respiratory rate estimation algorithm; and outputting an estimated respiration frequency by fusing the peak energy and the maximum frequency energy using the respiratory rate estimation algorithm.

Description

[0001] SYSTEM AND METHOD FOR ESTIMATING RESPIRATION RATE OF

[0002] SUBJECT WEARING INSTANT HEART RATE MONITOR

[0003] GOVERNMENT LICENSE RIGHTS

[0004] This invention was made with government support under Contracts No. HQ0034209PT04 and HDTRA121C0006 awarded by the Defense Threat Reduction Agency (DTRA) of the Department of Defense. The government has certain rights in the invention.

[0005] BACKGROUND OF THE INVENTION

[0006] Respiration 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 respiratory disease detection of chronic respiratory diseases, such as asthma and chronic obstructive pulmonary disease (COPD), and acute respiratory diseases (ARDS). Respiration also factors into chemical exposure algorithms.

[0007] For medical diagnosis, in particular, there are multiple ways to measure respiratory rate. However, accurate respiration measurements involve bulky and expensive monitors that require the patient to be substantially immobile. Conventional respiratory monitoring methods include flow-based monitoring from ventilators or non-invasive Capnography nasal cannula, and impedance change monitoring due to breathing from medical grade multi-leads electrocardiogram (ECG) monitoring. Wearable monitors would be preferable, but measuring respiratory rates robustly using wearable monitors remains a challenge.

[0008] SUMMARY OF THE INVENTION

[0009] According to a representative embodiment, a method is provided for estimating respiration rate of a subject wearing a wearable instant heart rate monitor. The method includes receiving data indicating heart rates of the subject from the wearable instant heart rate monitor; determining beat annotations of the heart rates from the received data; filtering the beat annotations to remove outlier instant heart rates from the received data; determining an interbeat interval (IB I) time series from filtered beat annotations; determining power spectrum density of the determined IBI time series; determining peak energy and maximum frequency energy of the power spectrum density within a lower bound estimation and an upper bound estimation of the respiration rate using a respiratory rate estimation algorithm; determining an estimated respiration frequency by fusing the peak energy and the maximum frequency energy using the respiratory rate estimation algorithm; and generating a respiration rate of the patient based on the estimated respiration frequency for display.

[0010] According to another representative embodiment, a system is provided for estimating respiration rate of a subject. The system includes a wearable instant heart rate monitor configured to collect data indicating heart rates of the subject; a processing unit configured to receive the data from the wearable instant 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 beat annotations of the heart rates from the received data; filter the beat annotations to remove outlier instant heart rates from the received data; determine an IBI time series from filtered beat annotations; determine power spectrum density of the determined IBI time series; execute the respiratory rate estimation algorithm. The respiratory rate estimation algorithm is configured to input the power spectrum density, a lower bound estimation of the respiration rate and an upper bound estimation of the respiration rate; determine peak energy and maximum frequency energy of the power spectrum density within the lower and upper bound estimations using the respiratory rate estimation algorithm; and output an estimated respiration frequency by fusing the peak energy and the maximum frequency energy using the respiratory rate estimation algorithm; and generate a respiration rate of the patient based on the estimated respiration frequency.

[0011] According to another representative embodiment, a non-transient computer readable medium stores instructions for estimating a respiration rate of a subject. When executed by one or more processors, cause the one or more processors to receive data from a wearable instant heart rate monitor, where the wearable instant heart rate monitor is worn by the subject and configured to collect data indicating a heart rate of the subject; receive beat annotations of the heart rates of the received data; filter the beat annotations to remove outlier instant heart rates from the received data; determine an IBI series from filtered beat annotations; determine power spectrum density of the determined IBI series; determine peak energy and maximum frequency energy of the power spectrum density within a lower bound estimation and an upper bound estimation of the respiration rate using a respiratory rate estimation algorithm; determine an estimated respiration frequency by fusing the peak energy and the maximum frequency energy using the respiratory rate estimation algorithm; and generate the respiration rate of the patient based on the estimated respiration frequency. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The example embodiments are best understood from the following detailed description when read with the accompanying drawing figures. It is emphasized that the various features are not necessarily drawn to scale. In fact, the dimensions may be arbitrarily increased or decreased for clarity of discussion. Wherever applicable and practical, like reference numerals refer to like elements.

[0013] Fig. l is a simplified block diagram of a system for estimating respiration rate of a subject wearing a wearable instant heart rate monitor, according to a representative embodiment.

[0014] Fig. 2 shows a representative IBI time series and a representative power spectrum density calculated from the IBI time series, according to a representative embodiment.

[0015] Fig. 3 is a graph showing a representative respiratory rate of a subject derived from the power spectrum density calculated from the IBI time series in Fig. 2, according to a representative embodiment.

[0016] Fig. 4 is a flow diagram of a method of estimating respiration rate of a subject wearing a wearable instant heart rate monitor, according to a representative embodiment.

[0017] DETAILED DESCRIPTION OF EMBODIMENTS

[0018] In the following detailed description, for purposes of explanation and not limitation, representative embodiments disclosing specific details are set forth in order to provide a thorough understanding of an embodiment according to the present teachings. Descriptions of known systems, devices, materials, methods of operation and methods of manufacture may be omitted so as to avoid obscuring the description of the representative embodiments. Nonetheless, systems, devices, materials and methods that are within the purview of one of ordinary skill in the art are within the scope of the present teachings and may be used in accordance with the representative embodiments. It is to be understood that the terminology used herein is for purposes of describing particular embodiments only, and is not intended to be limiting. The defined terms are in addition to the technical and scientific meanings of the defined terms as commonly understood and accepted in the technical field of the present teachings.

[0019] 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 only used to distinguish one element or component from another element or component. Thus, a first element or component discussed below could be termed a second element or component without departing from the teachings of the inventive concept. The terminology used herein is for purposes of describing particular embodiments only, and is not intended to be limiting. As used in the specification and appended claims, the singular forms of terms “a,” “an” and “the” are intended to include both singular and plural forms, unless the context clearly dictates otherwise. Additionally, the terms “comprises,” and / or “comprising,” and / or similar terms when used in this specification, specify the presence of stated features, elements, and / or components, but do not preclude 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.

[0020] Unless otherwise noted, when an element or component is said to be “connected to,” “coupled to,” or “adjacent to” another element or component, it will be understood that the element or component can be directly connected or coupled to the other element or component, or intervening elements or components may be present. That is, these and similar te-rms encompass cases where one or more intermediate elements or components may be employed to connect two elements or components. However, when an element or component is said to be “directly connected” to another element or component, this encompasses only cases where the two elements or components are connected to each other without any intermediate or intervening elements or components.

[0021] As used in the specification and appended claims, and in addition to their ordinary meanings, the term “about” and “approximately” mean to with acceptable limits or degree. For example, “approximately 2 MHz” means one of ordinary skill in the art would consider the signal to be 2 MHz within reasonable measure. Also, as used in the specification and appended claims, in addition to its ordinary meaning, the term “substantially” means within acceptable limits or degree. For example, the term “substantially simultaneously” means one of ordinary skill in the art would consider occurrence at the same time.

[0022] In view of the foregoing, the present disclosure, through one or more of its various aspects, embodiments and / or specific features or sub-components, is thus intended to bring out one or more of the advantages as specifically noted below. For purposes of explanation and not limitation, example embodiments disclosing specific details are set forth in order to provide a thorough understanding of an embodiment according to the present teachings. However, other embodiments consistent with the present disclosure that depart from specific details disclosed herein remain within the scope of the appended claims. Moreover, descriptions of well-known apparatuses and methods may be omitted so as to not obscure the description of the example embodiments. Such methods and apparatuses are within the scope of the present disclosure. Generally, the various embodiments provide a process that can estimate the respiration rate of a subject without using data from a respiration monitor. Rather, the process relies on heart rate data received from an instant heart rate monitor worn by the subject to generate an estimated respiration rate of the subject. The various embodiments thus provide technical improvements to instant heart rate monitoring systems to include respiration rate determination.

[0023] Fig. l is a simplified block diagram of a system for estimating respiration rate of a subject, according to a representative embodiment.

[0024] Referring to Fig. 1, system 100 includes a workstation 105 for implementing and / or managing the processes described herein with regard to estimating a respiration rate of a subject (patient) 150 using a data from a wearable instant heart rate monitor 140 that indicates the heart rate of the subject 150. The instant heart rate monitor 140 may be an electrocardiogram (ECG) or a photoplethysmogram (PPG) monitoring device, for example, although other types of heart monitoring devices capable of providing an accurate heart rate of the subject 150 via a wearable monitor may be incorporated without departing from the scope of the present teachings. Other examples of the instant heart rate monitor 140 include ePatch™ available from Philips Koninklijke Philips N.V, Empatica Health Monitoring Platform available from Empatica, Inc., Oura Ring available from Oura Health Oy, and Zephyr® chest band available from Pulmonx Corporation.

[0025] The workstation 105 includes processor 120, memory 130, a user interface 122 and a display 124. The processor 120 communicates with the instant heart rate monitor 140 through a known monitor interface (not shown), which may include a wired connection or a wireless connection (e.g., Wifi, Bluetooth) for communicating the data. The memory 130 stores instructions executable by the processor 120. When executed, the instructions cause the processor 120 to implement one or more processes for estimating the respiration rate of the subject 150 using the heart rate data acquired by the wearable instant heart rate monitor 140. In the context of this application, the instant heart rate data which may be provided from the instant heart rate monitor 140 are real-time or near real-time during an interventional procedure, for example. For purposes of illustration, the memory 130 is shown to include software modules, each of which includes sets of instructions, executable by the processor 120, corresponding to an associated capability of the system 100.

[0026] The processor 120 is representative of one or more processing devices, and may be implemented by a general purpose computer, a central processing unit (CPU), a digital signal processor (DSP), a graphical processing unit (GPU), a tensor processing unit (TPU), a computer processor, a microprocessor, a state machine, programmable logic device, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), or combinations thereof, using any combination of hardware, software, firmware, hard-wired logic circuits, or 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. The term “processor” as used herein encompasses an electronic component able to execute a program or machine executable instruction. A processor may also refer to a collection of processors within a single computer system or distributed among multiple computer systems, such as in a cloud-based or other multi-site application. Programs have software instructions performed by one or multiple processors that may be within the same computing device or which may be distributed across multiple computing devices.

[0027] The memory 130 is representative of one or more memories, and may include main memory and / or static memory, where such memories may communicate with each other and the processor 120 via one or more buses. The memory 130 may be implemented by any number, type and combination of random access memory (RAM) and read-only memory (ROM), for example, and may store various types of information, such as software algorithms, artificial intelligence (Al) models, machine learning models, and computer programs, all of which are executable by the processor 120. The various types of ROM and RAM may include any number, type and combination of computer readable storage media, such as a disk drive, flash memory, an electrically programmable read-only memory (EPROM), an electrically erasable and programmable read only memory (EEPROM), registers, a hard disk, a removable disk, tape, compact disk read only memory (CD-ROM), digital versatile disk (DVD), floppy disk, Blu-ray disk, a universal serial bus (USB) drive, or any other form of storage medium. The memory 130 is a tangible storage medium for storing data and executable software instructions, and is non-transitory during the time software instructions are stored therein. As used herein, the term “non-transitory” is to be interpreted not as an eternal characteristic of a state, but as a characteristic of a state that will last for a period. The term “non-transitory” specifically disavows fleeting characteristics such as characteristics of a carrier wave or signal or other forms that exist only transitorily in any place at any time. The memory 130 may store software instructions and / or computer readable code that enable performance of various functions. The memory 130 may be secure and / or encrypted, or unsecure and / or unencrypted.

[0028] The system 100 may also include database 112 for storing information that may be used by the various software modules of the memory 130. For example, the database 112 may include heart rate data and associated respiration data from previous monitoring of the subject 150 and / or from other similarly situated subjects having wearable instant heart rate monitors. The stored data may be used for training a machine learning model (algorithm), such as a neural network, for example. The database 112 may be implemented by any number, type and combination of RAM and ROM, for example. The various types of ROM and RAM may include any number, type and combination of computer readable storage media, such as a disk drive, flash memory, EPROM, EEPROM, registers, a hard disk, a removable disk, tape, CD-ROM, DVD, floppy disk, Blu-ray disk, USB drive, or any other form of storage medium known in the art. The database 112 comprises one or more tangible storage mediums for storing data and / or executable software instructions and is non-transitory during the time data and software instructions are stored therein. The database 112 may be secure and / or encrypted, or unsecure and / or unencrypted. For purposes of illustration, the database 112 is shown as a separate storage medium, although it is understood that it may be combined with and / or included in the memory 130, without departing from the scope of the present teachings.

[0029] The processor 120 may include or have access to an artificial intelligence (Al) engine, which may be implemented as software that provides artificial intelligence (e.g., machine learning models) and applies machine learning described herein. The Al engine may reside in any of various components in addition to or other than the processor 120, such as the memory 130, an external server, and / or the cloud, for example. When the Al engine is implemented in a cloud (not shown), such as at a data center, for example, the Al engine may be connected to the processor 120 via the internet or other communication network using one or more wired and / or wireless connection(s).

[0030] The user interface 122 is configured to provide information and data output by the processor 120, the memory 130 and / or the instant heart rate monitor 140 to the user and / or for receiving information and data input by the user. That is, the user interface 122 enables the user to enter data and to control or manipulate aspects of the processes described herein, and also enables the processor 120 to indicate the effects of the user’s input. All or a portion of the user interface 122 may be implemented by a graphical user interface (GUI), such as GUI 128 viewable on the display 124, discussed below. The user interface 122 may include one or more interface devices, such as a mouse, a keyboard, a trackball, a joystick, a microphone, a video camera, a touchpad, a touchscreen, voice or gesture recognition captured by a microphone or video camera, for example.

[0031] The display 124 may be a monitor such as a computer monitor, a television, a liquid crystal display (LCD), an organic light emitting diode (OLED), a flat panel display, a solid-state display, or a cathode ray tube (CRT) display, or an electronic whiteboard, for example. The display 124 includes a screen 126 for viewing information regarding the subject 150, including visualization of the heart rate, e.g., ECG or PPG traces from the instant heart rate monitor 140, along with various features described herein to communicate to the user estimated respiratory rates, together with predicted ailments that may be associated with the heart monitoring and recommendations of types of follow-up actions. The screen 126 further enables viewing of the GUI 128 to enable the user to interact with the displayed images and features.

[0032] Referring to the memory 130, the various modules therein store sets of data and instructions executable by the processor 120 to determine estimation of respiration, as mentioned above. Heart data module 131 is configured to receive and process data indicating heart rates of the subject 150, e.g., collected over a period of time. The heart rate data may be acquired non- invasively by the wearable instant heart rate monitor 140, as discussed above, and may be received in real-time or near real-time during active monitoring or during a contemporaneous intervention of the subject 150. Indications (e.g., traces, graphs, numbers) of the heart rates may be displayed on the display 124 based on the heart rate data.

[0033] Beat annotations module 132 is configured to determine beat annotations of the heart rates from the received heart rate data. Beat annotations are labels assigned to the data indicating the heart rates that describe events at specific locations in the data, such as R-peaks in an ECG signal, for example. The locations may be identified automatically, for example, using a peak detector, or identified manually by the user via the user interface 122. The beat annotations themselves may be added automatically, e.g., by device vendors or by known beat annotation software. When the heart rate data includes ECG or PPG signals, for example, the beat annotations may be added to indicate the locations and / or times of occurrence of the events, as well as types of individual heart beats. When the heart rate data includes signals from an Oura Ring, for example, the annotations indicating locations and / or times of occurrence and the types of heart beats are already included in beat files, and therefore may be extracted from the beat files as opposed to being added.

[0034] The beat annotations module 132 may also filter the beat annotations for quality control in order to remove outlier or implausible instant heart rates for humans. The filtering is based on minimum and maximum physiologically feasible instant heart rates that are previously set or customizable as lower and upper thresholds, respectively, in order to identify and remove the outlier instant heart rates. The lower and upper thresholds may be adjusted in practical settings adapted to intended use cases and populations. For example, the lower threshold may be 45 bpm and the upper threshold may be 115 bpm. IBI module 133 is configured to determine an IBI time series from the filtered beat annotations provided by the beat annotations module 132. The IBI series provides timing between heart beats, and may be determined by cumulating the filtered beat annotations over a predetermined period of time. The unit of the IBI time series may be in seconds. The IBI module 133 is further configured to determine power spectrum density of the determined IBI time series. In a separate embodiment, the power spectrum density may be calculated by applying a Lomb- Scargle periodogram to the IBI time series, for example, over the predetermined period of time. Application of the Lomb-Scargle periodogram allows irregularly sampled data. Other techniques may be applied for calculating the power spectrum density from the IBI time series without departing from the scope of the present teachings, such as dictionary learning technique with Fourier or wavelet dictionary and estimating the power spectrum density using optimization, as would be apparent to one skilled in the art. Such determinations of power spectrum density cannot practically be performed in the human mind. The power spectrum density indicates the peak and the maximum frequency in a frequency band that corresponds to respiration modulation from the IBI time series.

[0035] Fig. 2 shows a representative IBI time series 210, e.g., determined by the IBI module 133, and a representative power spectrum density 220 calculated from the IBI time series 310, according to a representative embodiment. The crosses in the IBI time series 210 indicate instant heart rates where peaks are detected over a time period of one minute. The power spectrum density 220 shows the frequencies in Hz at one interval of time (one “slice”) of the IBI time series 210 in the same time period. Box 225 indicates frequencies that correspond to respiration modulation of the subject, where box 225 is defined by lower and upper bound estimations of the respiration rate. In the depicted example, the lower bound estimation of the respiration rate is about 0.20 Hz and the upper bound estimation of the respiration rate is about 0.40 Hz, which correspond to a lower bound estimation of about 12 breaths per minute and an upper bound estimation of about 24 breaths per minute. Of course, the lower and upper bound estimations may be adjusted by the user to specific populations without departing from the scope of the present teachings. The lower and upper bound estimations may be determined based on physically feasible respiratory rates, as well as population variance. For example, kids have higher respiratory rates than adults, statistically speaking. The peak frequency is at about 0.32 Hz in the depicted example, as indicated by a brighter portion of the power spectrum density. Notably, the peak energy may be different from the maximum frequency energy, discussed below. Similar power spectrum densities are determined at other times of the IBI time series 210 to provide a complete power spectrum density representation. Respiration rate (RR) estimation module 134 is configured to apply a respiratory rate algorithm to estimate the respiration rate of the subject 150 based on the power spectrum density. The respiratory rate algorithm may be a signal processing algorithm, for example. The respiratory rate algorithm receives the power spectrum density, the lower bound estimation of the respiration rate and the upper bound estimation of the respiration rate, and automatically determines both peak energy and maximum frequency energy of the power spectrum density within the lower and upper bound estimations of the respiration rate at each time interval or slice. The peak energy may be determined by a peak-finding algorithm that uses the second derivative of the curve of the power spectrum density to determine the peak location (peak frequency), for example. Other peak-finding algorithms may be applied without departing from the scope of the present teachings. The maximum frequency energy may be determined by finding a local maximum of the power spectrum density.

[0036] The respiratory rate algorithm automatically fuses the peak energy and the maximum frequency energy at each time interval or slice to output an estimated respiration frequency. Fusing the peak energy and the maximum frequency energy may include determining whether the maximum frequency energy is on either of the lower or upper bound estimations of the respiration rate. If not, the maximum frequency energy is used as the estimated respiration frequency for that time interval or slice. When the maximum frequency energy is on either of the lower or upper bound estimations of the respiration rate, the peak energy is used as the estimated respiration frequency for that time interval or slice. Alternatively, the peak energy and maximum frequency energy may be weighted to arrive at an estimated respiration frequency that is a weighted combination of both values. At least the above aspects of the respiratory rate algorithm cannot practically be performed in the human mind. The estimated respiration frequency corresponds to the breathing rate of the subject 150. Generally, the respiratory rate is about two to three times slower than the heart rate.

[0037] The respiratory rate algorithm also generates the respiration rate of the subject 150 for display on the display 124 by multiplying the estimated respiration frequency by 60, for example. Fig. 3 shows a graph 330 indicating a representative breathing rate of a subject estimated from the power spectrum density 220 calculated from the IBI time series in Fig. 2, according to a representative embodiment. The breathing rate is shown in breaths per minute over a time of 1050 seconds. In the depicted example, the breathing rates range between a high of about 24.7 breaths per minute (brpm) and a low of about 13.0 brpm. Unlike conventional breathing rate determination techniques, which rely on monitor numerics, the estimated breathing rate according to the representative embodiments may be determined in the absence of breathing monitors, using only wearable instant heart rate monitors to achieve a reliable result.

[0038] Fig. 4 is a flow diagram of a method of estimating a respiration rate of a subject wearing a wearable instant heart rate monitor, according to a representative embodiment Fig. 4 may be implemented at least in part by the processor 120 of the workstation 105, executing instructions stored in the memory 130, for example.

[0039] Referring to Fig. 4, data indicating heart rates of the subject is received in block S411 from a wearable instant heart rate monitor. The wearable instant heart rate monitor may be any device attachable to the subject and capable of collecting data indicating the subject’s heart rate, such as an ECG monitor or a PPG monitor, for example. The data may be received through a wireless or wired interface with the wearable instant heart rate monitor. Other examples of wear heart rate monitors include ePatch™, Empatica Health Monitoring Platform, Oura Ring, and Zephyr® chest band, mentioned above.

[0040] In block S412, beat annotations of the heart rates are determined from the received data. When the data includes ECG or PPG signals, for example, the beat annotations may be added to indicate the locations and / or times of occurrence of the events, as well as types of individual heart beats. The locations may be identified automatically, for example, using a peak detector, or identified manually by the user via the user interface. When the data includes Oura Ring signals, for example, the annotations may be extracted from beat files received with the data from the Oura Ring.

[0041] In block S413, the beat annotations are filtered to remove outlier or implausible instant heart rates for humans, improving quality. The filtering includes receiving minimum and maximum physiologically feasible instant heart rates as lower and upper thresholds, respectively, and removing instant heart rates exceeding these thresholds.

[0042] In block S414, an IBI time series is determined from the filtered beat annotations. The IBI series provides the timing between heart beats, and may be determined by cumulating the beat annotations over a predetermined period of time.

[0043] In block S415, power spectrum density of the determined IBI time series is calculated. The power spectrum density may be calculated by applying a Lomb-Scargle periodogram to the IBI time series, for example, over the predetermined time period. The power spectrum density may be calculated using other techniques, such as dictionary learning with Fourier or wavelet dictionary and estimating the power spectrum density using optimization, for example. In block S416, peak energy and maximum frequency energy of the power spectrum density are automatically determined within a lower bound estimation and an upper bound estimation of the respiration rate at each time in the IBI times series using a respiratory rate estimation algorithm. The peak energy may be determined by detecting the peak frequency of the second derivative of the power spectrum density curve, and the maximum frequency energy may be determined by finding a local maximum of the power spectrum density, as discussed above.

[0044] In block S417, the peak energy and the maximum frequency energy are automatically fused at each time by the respiratory rate estimation algorithm to output an estimated respiration frequency. The peak energy and the maximum frequency energy correspond to the breathing rate of the subject. Fusing the peak energy and the maximum frequency energy may include using the maximum frequency energy as the estimated respiration frequency at each time where the maximum frequency energy is not on either of the lower or upper bound estimations, and using the peak energy as the estimated respiration frequency at each time where the maximum frequency energy is on either of the lower or upper bound estimations. Alternatively, fusing the peak energy and the maximum frequency energy may include weighting the values of the peak energy and maximum frequency energy at each time, and combining the weighted values as the estimated respiration frequency.

[0045] In block S418, a respiration rate of the patient is generated for display. The respiration rate may be generated by multiplying the estimated respiration frequency by 60.

[0046] Although the present specification describes components and functions that may be implemented in particular embodiments with reference to particular standards and protocols, the disclosure is not limited to such standards and protocols. Such standards are periodically superseded by more efficient equivalents having essentially the same functions. Accordingly, replacement standards and protocols having the same or similar functions are considered equivalents thereof.

[0047] The illustrations of the embodiments described herein are intended to provide a general understanding of the structure of the various embodiments. The illustrations are not intended to serve as a complete description of all of the elements and features of the disclosure described herein. Many other embodiments may be apparent to those of skill in the art upon reviewing the disclosure. Other embodiments may be utilized and derived from the disclosure, such that structural and logical substitutions and changes may be made without departing from the scope of the disclosure. Additionally, the illustrations are merely representational and may not be drawn to scale. Certain proportions within the illustrations may be exaggerated, while other proportions may be minimized. Accordingly, the disclosure and the figures are to be regarded as illustrative rather than restrictive.

[0048] One or more embodiments of the disclosure may be referred to herein, individually and / or collectively, by the term “invention” merely for convenience and without intending to voluntarily limit the scope of this application to any particular invention or inventive concept. Moreover, although specific embodiments have been illustrated and described herein, it should be appreciated that any subsequent arrangement designed to achieve the same or similar purpose may be substituted for the specific embodiments shown. This disclosure is intended to cover any and all subsequent adaptations or variations of various embodiments. Combinations of the above embodiments, and other embodiments not specifically described herein, will be apparent to those of skill in the art upon reviewing the description.

[0049] The Abstract of the Disclosure is provided to comply with 37 C.F.R. § 1.72(b) and is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. In addition, in the foregoing Detailed Description, various features may be grouped together or described in a single embodiment for the purpose of streamlining the disclosure. This disclosure is not to be interpreted as reflecting an intention that the claimed embodiments require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive subject matter may be directed to less than all of the features of any of the disclosed embodiments. Thus, the following claims are incorporated into the Detailed Description, with each claim standing on its own as defining separately claimed subject matter.

[0050] The preceding description of the disclosed embodiments is provided to enable any person skilled in the art to practice the concepts described in the present disclosure. As such, the above disclosed subject matter is to be considered illustrative, and not restrictive, and the appended claims are intended to cover all such modifications, enhancements, and other embodiments which fall within the true spirit and scope of the present disclosure. Thus, to the maximum extent allowed by law, the scope of the present disclosure is to be determined by the broadest permissible interpretation of the following claims and their equivalents, and shall not be restricted or limited by the foregoing detailed description.

Claims

CLAIMS:

1. A method of estimating a respiration rate of a subject wearing a wearable instant heart rate monitor, the method comprising: receiving data indicating heart rates of the subject from the wearable instant heart rate monitor; determining beat annotations of the heart rates from the received data; filtering the beat annotations to remove outlier instant heart rates from the received data; determining an interbeat interval (IB I) series from filtered beat annotations; determining power spectrum density of the determined IBI series; determining peak energy and maximum frequency energy of the power spectrum density within a lower bound estimation and an upper bound estimation of the respiration rate using a respiratory rate estimation algorithm; determining an estimated respiration frequency by fusing the peak energy and the maximum frequency energy using the respiratory rate estimation algorithm; and generating a respiration rate of the patient based on the estimated respiration frequency for display.

2. The method of claim 1, wherein generating the respiration rate of the patient comprises multiplying the estimated respiration frequency by 60.

3. The method of claim 1, wherein when the instant heart rate monitor is an electrocardiogram (ECG) device or a photoplethysmography (PPG) device, determining the beat annotations comprises annotating the received data from an ECG waveform or a PPG waveform, respectively.

4. The method of claim 1, wherein filtering the beat annotations comprises: inputting a minimum physiologically feasible instant heart rate and a maximum physiologically feasible instant heart rate; andremoving instantaneous heart rates below the minimum physiologically feasible instant heart rate and above the maximum physiologically feasible instant heart rate.

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

6. The method of claim 1, wherein determining the IBI series from the filtered beat annotations comprises: cumulating the beat annotations over a predetermined period of time.

7. The method of claim 1, further comprising: adjusting at least one of the lower bound estimation or the upper bound estimation based on patient population.

8. A system for estimating a respiration rate of a subject, the system comprising: a wearable instant heart rate monitor configured to collect data indicating a heart rate of the subject; a processing unit configured to receive the data from the wearable instant heart rate monitor; and a memory storing a respiratory rate estimation algorithm and instructions that, when executed by the processing unit, cause the processing unit to: determine beat annotations of the heart rates from the received data; filter the beat annotations to remove outlier instant heart rates from the received data; determine an interbeat interval (IBI) series from filtered beat annotations; determine power spectrum density of the determined IBI series; input a lower bound estimation of the respiration rate and an upper bound estimation of the respiration rate; determine peak energy and maximum frequency energy of the power spectrum density within the lower and upper bound estimations of the respiration rate using a respiratory rate estimation algorithm;determine an estimated respiration frequency by fusing the peak energy and the maximum frequency energy using the respiratory rate estimation algorithm; and generate the respiration rate of the patient based on the estimated respiration frequency.

9. The system of claim 8, further comprising: a user interface configured to enable a user to input the lower bound estimation of the respiration rate and the upper bound estimation of the respiration rate to the processing unit to be applied to the respiratory rate estimation algorithm.

10. The system of claim 8, wherein when the wearable instant heart rate monitor comprises an electrocardiogram (ECG) device, and wherein the instructions cause the processing unit to determine the beat annotations by annotating the received data from an ECG waveform provided by the ECG device.

11. The system of claim 8, wherein when the wearable instant heart rate monitor comprises a photoplethysmography (PPG) device, and wherein the instructions cause the processing unit to determine the beat annotations by annotating the received data from a PPG waveform provided by the PPG device.

12. The system of claim 8, wherein the instructions cause the processing unit to determine the IBI series from the filtered beat annotations by cumulating the beat annotations over a predetermined period of time.

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

14. The system of claim 8, wherein the instructions cause the processing unit to filter the beat annotations by: receiving a minimum physiologically feasible instant heart rate and a maximum physiologically feasible instant heart rate; and removing instantaneous heart rates below the minimum physiologically feasible instant heart rate and above the maximum physiologically feasible instant heart rate.

15. A non-transient computer readable medium storing instructions for estimating a respiration rate of a subject, that when executed by one or more processors, cause the one or more processors to: receive data from a wearable instant heart rate monitor, wherein the wearable instant heart rate monitor is worn by the subject and configured to collect data indicating a heart rate of the subject; receive beat annotations of the heart rates of the received data; filter the beat annotations to remove outlier instant heart rates from the received data; determine an interbeat interval (IB I) series from filtered beat annotations; determine power spectrum density of the determined IBI series; determine peak energy and maximum frequency energy of the power spectrum density within a lower bound estimation and an upper bound estimation of the respiration rate using a respiratory rate estimation algorithm; determine an estimated respiration frequency by fusing the peak energy and the maximum frequency energy using the respiratory rate estimation algorithm; and generate the respiration rate of the patient based on the estimated respiration frequency.

Images