Device, system and method for measuring physiological phenomena and physical activity in a subject

Through the combined heuristics of periodic transformation and partial circulation measurement, the inaccuracy problem of wearable devices when monitoring respiration rates and other activities is solved, and accurate measurement of respiration rates and activities and reliable calculation of signal quality index is achieved, which enhances the The clinical application value of the equipment.

CN113727647BActive Publication Date: 2024-11-05KONINKLIJKE PHILIPS NV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202080030744.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2019-04-23
Filing Date
2020-04-20
Publication Date
2024-11-05
Estimated Expiration
2040-04-20

AI Technical Summary

Technical Problem

Existing wearable devices have problems with inaccuracy and insufficient measurement of signal quality index when monitoring respiration rates, resulting in the inability to accurately detect dominant activities, especially in resting states or in the presence of overlapping activities.

Method used

Using periodic transformation (PT) and partial cycle measurement (PCM) combined with heuristics, the dominant activity is identified and the signal quality index (SQI) is calculated through accelerometer and gyroscope data to eliminate harmonics and sub-period information to determine the most likely activity type.

Benefits of technology

Accurate measurement of respiration rates and other activities is achieved, the reliability of the signal quality index is improved, and the ability to accurately detect dominant activities in resting and moving states is enhanced, which is enhanced for clinical application reliability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113727647B_ABST
    Figure CN113727647B_ABST
Patent Text Reader

Abstract

Systems, devices, and methods for determining the dominant activity observed from a body-worn sensor and accurately characterizing the activity. Various embodiments may include using period transform (PT) and partial cycle measurement (PCM) calculations to detect the dominant activity associated with a data interval from one or more data channels. For example, in a body-worn sensor (e.g., chest-worn, limb-worn, etc.), there may be conflicting signals that overlap in time, frequency, amplitude, etc., and the overlapping data may convey specific dominant information in a mixed manner. Various embodiments described herein attempt to determine the dominant information source from any channel by using fractional cycles and period transforms. For example, period transforms according to various embodiments may provide a specific transformation method that can be implemented in real time, and identify dominant cycle periods when used with heuristics to eliminate harmonic / sub-periodic information. Therefore, various embodiments described herein may determine the dominant activity occurring in or with a patient and a reliability measure (e.g., signal quality index) for a specific measurement interval.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to devices, systems and methods for measuring physiological phenomena and physical activities associated with a subject. In particular, the present disclosure relates to determining the dominant activity observed from a body-worn sensor and accurately characterizing the activity. Background Art

[0002] The healthcare industry is experiencing the emergence of wireless technologies that can replace traditional health monitoring devices with wearable devices. These wearable devices can monitor physiological data related to the patient's health. Therefore, these wearable devices can greatly improve disease prevention, clinical care, and quality of life.

[0003] However, obtaining clinically accurate data from these wearable devices has proven to be quite difficult. For example, wearable medical devices may attempt to separate useful physiological information from data collected via a device worn on the body. To achieve this goal, the device may employ several components, including, for example, an accelerometer, a gyroscope or gyroscope, a magnetometer, and / or a barometer. Physiological information may include, for example, pulse rate, blood pressure, respiratory rate, and / or temperature. Among this physiological information, respiratory rate is typically not recorded or is inaccurate, and therefore, is unavailable for adverse event detection.

[0004] For example, when based on periodic and non-periodic chest wall movement and vibration, respiratory rate measurement may contain inaccuracies. At any particular time, the mechanical movement seen from periodic and non-periodic chest wall movement and vibration can be defined as the detection of dominant visible activity. And, for patients at rest, the sensor can indicate baseline respiratory activity and non-periodic sensor noise. When the patient gets up to a standing or sitting position or otherwise changes posture, sudden non-periodic changes may appear in the sensor data. And, when the patient moves, such as when the patient is walking, a group of periodic oscillations can be seen. At any point in time, the ratio of dominant activity to other activities can determine the signal quality index (SQI) measurement result. And, in order to utilize measurements such as respiratory rate or other types of activities, it may be necessary to accept measurements that can be used reliably via quality assurance of the quality index. The current model for respiratory rate does not provide high-quality SQI measurements, and therefore does not provide clinically accurate respiratory rate measurements. For example, when the dominant activity is not correctly determined, an accurate respiratory rate cannot be calculated.

[0005] However, activity levels cannot often be accurately determined. For example, medical quality algorithms may use measurements and / or background information that require assurance or quality indices to obtain acceptable measurements that can be used reliably. Furthermore, current models do not employ accurate or near accurate signal quality indices to use with each measurement.

[0006] Other challenges with existing methods include problems associated with overlapping activities involving, for example, breathing, slow walking cycles, posture changes, and / or other motion-related artifacts. These challenges are evidenced by the inability to provide a one-to-one relationship that associates frequency domain information with specific physiological phenomena.

[0007] In addition to these, the problem is the fact that respiratory rate is often not recorded even when the patient's main problem is respiratory status. This is despite the fact that abnormal respiratory rate may be an important predictor of serious events such as cardiac arrest or admission to an intensive care unit (ICU). In fact, higher respiratory rates in patients may be associated with increased mortality. There are these and other disadvantages.

[0008] Advantageously, the present invention seeks to address these outstanding issues by measuring physiological phenomena and physical activities occurring at any point in a subject's body. Summary of the invention

[0009] According to various embodiments, the present disclosure relates to systems, devices, and methods for determining a dominant activity observed from a body-worn sensor and accurately characterizing the activity. Various embodiments may include using period transform (PT) and partial cycle measurement (PCM) calculations to detect a dominant activity associated with a data interval from one or more data channels.

[0010] For example, in body worn sensors (e.g., chest worn, limb worn, etc.), there may be conflicting signals that overlap in time, frequency, amplitude, etc., and this overlapping data may convey specific dominant information in a mixed manner. Various embodiments described herein attempt to determine the dominant source of information from any channel by using fractional cycles and period transformations. For example, period transformations according to various embodiments may provide specific transformation methods that can be implemented in real time and identify dominant cycle periods when used with heuristics to eliminate harmonic / sub-periodic information. Therefore, various embodiments described herein can determine the dominant activity occurring in or with a patient and a reliability measure (e.g., a signal quality index) for a particular measurement interval.

[0011] As an example, a respiration rate measurement, such as a measurement of various mechanical motions seen from periodic and non-periodic chest wall movements and vibrations, can be defined as the detection of the dominant visible activity at any particular time. For a patient at rest, the sensor can indicate baseline respiratory activity as well as non-periodic sensor noise. When the patient stands up or changes posture or turns, sudden non-periodic changes appear in the sensor data. Again, when the patient undergoes routine slow or fast walking, a set of periodic oscillations can be seen. At any moment in time, the ratio of the dominant activity to the remaining activity can determine a signal quality index (SQI) metric.

[0012] Various embodiments of the present disclosure may include a device having: an accelerometer configured to receive accelerometer data; a gyroscope configured to receive gyroscope data; and a microprocessor configured to: perform a partial cycle analysis based on at least one of the accelerometer data and the gyroscope data to determine at least three top cycles; perform a period transformation (PT) based selection of at least one top cycle observed from the partial cycle analysis; and use a heuristic to determine the most likely activity of the at least one top cycle. In various embodiments, the most likely activity may include at least one of: sudden motion, sustained motion, slow chest wall motion, deep chest wall motion, and severe vibration.

[0013] According to various embodiments, the PT-based selection may be performed by: (a) assuming a threshold (T); (b) obtaining a signal X of length N via at least one of the accelerometer data and the gyroscope data; (c) locating a fractional cycle marker for each of the at least top three cycles; (d) approximating a cycle length (CL) for each cycle. i ) and amplitude (A i ), where i is a cycle; (e) approximate the expected period for each cycle; (f) relate the expected period to the fractional cycle label for each cycle; (g) set the expected period equal to one; (h) remove the linear DC component by removing the projection onto the first expected period equal to one; (i) set the expected period equal to CL1; (j) determine whether A1 contains at least T% of the energy in X; (k) if A1 contains at least T% of the energy in X, accept A1 and CL1 as possible cycles; (l) for each CL i and A i Repeat steps (i)-(k); and (m) based on each cycle length (CL i ) and the amplitude of each cycle (A i ) to estimate the most likely cycle length.

[0014] According to various embodiments, partial cycle estimation may occur simultaneously with or separately from period transform estimation.

[0015] In various embodiments, if adjacent cycles show dominant characteristics due to variability within the measurement interval, a periodic band is formed and the center cycle within the band is designated as the most likely cycle length. Also, in various embodiments, the heuristic may be based on at least one of: a specific amplitude range, a specific cycle length, data indicating continuity, data indicating the duration of continuity, data indicating the nature of the period, data indicating in what channel of the sensor the signal is dominant, and a degree of correlation with measurements made in a silent interval. According to various embodiments, the heuristic may include at least one of: a maximum power cycle length associated with the accelerometer data, a maximum power cycle length associated with the gyroscope data, an average power cycle length associated with the accelerometer data, an average power cycle length associated with the gyroscope data, a maximum significant estimated cycle length associated with the accelerometer data, a maximum significant estimated cycle length associated with the gyroscope data.

[0016] In addition, according to various embodiments, the microprocessor can use the presence or absence of period information associated with the partial cycle analysis to measure a signal quality index (SQI) of an incoming signal associated with at least one of the accelerometer data and the gyroscope data. According to various embodiments, a sudden change in the SQI for a duration less than a first SQI threshold can indicate a change in attitude.

[0017] In various embodiments, the accelerometer and gyroscope may be housed in a wearable device that may be worn on the patient's chest, in the upper chest or lower chest region. The user may include the patient. In various embodiments, the accelerometer data and / or gyroscope data may be received on demand and / or continuously. In various embodiments, the sensor data may be pushed from the wearable device and / or pulled from the wearable device.

[0018] According to various embodiments, the microprocessor may determine a signal quality index (SQI) associated with the most likely activity.

[0019] In various embodiments, partial cycle analysis can be performed by mapping the cycles to regions of maximum amplitude, minimum amplitude, and zero crossing intervals and their cycles. The mapping can be continuous. Also, in various embodiments, the cycles can be selected to be at least the top three cycles based on amplitude thresholds and repeatability of the cycles. Additionally, in various embodiments, a baseline measurement noise amplitude can be calculated and subtracted from the amplitude measurement results associated with at least one of the accelerometer data and the gyroscope data.

[0020] Various embodiments may include: receiving accelerometer data via an accelerometer of a wearable device; receiving gyroscope data via a gyroscope of the wearable device; performing a partial cycle analysis to determine at least top three cycles based on at least one of the accelerometer data and the gyroscope data; performing a period transformation (PT) based selection of at least one top cycle observed from the partial cycle analysis; and using a heuristic to determine the most likely activity of the at least one top cycle. Various embodiments may include the most likely top cycle of respiratory activity and respiratory rate. In addition, various embodiments may conclude that the most likely activity includes at least one of the following: sudden movement, sustained movement, slow chest wall movement, deep chest wall movement, and severe vibration.

[0021] Various embodiments may include performing the PT-based selection by: (a) assuming a threshold (T); (b) obtaining a signal X of length N via at least one of the accelerometer data and the gyroscope data; (c) locating a fractional cycle marker for each of the at least top three cycles; (d) approximating a cycle length (CL) for each cycle. i ) and amplitude (A i ), where i is a cycle; (e) approximate the expected period for each cycle; (f) associate the expected period with the fractional cycle label for each cycle; (g) set the expected period equal to one; (h) remove the linear DC component by removing the projection onto the first expected period equal to one; (i) set the expected period equal to CL1; (j) determine whether A1 contains at least T% of the energy in X; (k) if A1 contains at least T% of the energy in X, accept A1 and CL1 as possible cycles; (l) for each CL i and A i Repeat steps (i)-(k); and (m) based on each cycle length (CL i ) and the amplitude of each cycle (A i ) to estimate the most likely cycle length.

[0022] In various embodiments, implementation of any method or device-based algorithm may be in the form of hardware and / or firmware. For example, a low pass filter associated with a particular signal may filter or pass one or more signals having a frequency below a predefined threshold frequency. Advantageously, by placing the filter in hardware, the filter may be robust.

[0023] Various embodiments of the present disclosure provide devices, systems, and methods for measuring physiological phenomena and physical activities associated with a subject. In various embodiments: BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Various embodiments of the present disclosure, together with other objects and advantages, may be best understood by reference to the following description taken in conjunction with the accompanying drawings, in which like reference numerals identify like elements throughout the several views, and in which:

[0025] Figure 1 An example embodiment of a system including a device for measuring physiological phenomena and physical activity associated with a subject is depicted;

[0026] Figure 2 An example embodiment of a system including a device for measuring physiological phenomena and physical activity associated with a subject is depicted;

[0027] Figure 3 An example embodiment of a system including a device for measuring physiological phenomena and physical activity associated with a subject is depicted;

[0028] Figure 4 depicts a flow chart illustrating an example method of measuring physiological phenomena and physical activity associated with a subject in accordance with an embodiment of the present invention;

[0029] Figure 5 Depicting exemplary device-containing techniques for measuring physiological phenomena and physical activity associated with a subject in accordance with embodiments of the present invention; and

[0030] Figure 6 Depicted are exemplary device-containing techniques for measuring physiological phenomena and physical activity associated with a subject in accordance with embodiments of the present invention. DETAILED DESCRIPTION

[0031] The following description is intended to convey a thorough understanding of the described embodiments by providing multiple specific exemplary embodiments and details relating to devices, systems and methods for measuring physiological phenomena and physical activities associated with a subject (e.g., measuring signal data, determining a signal quality index and / or determining the most likely activity associated with sensor data). However, it should be appreciated that the present disclosure is not limited to these specific embodiments and details which are merely exemplary. It should also be appreciated that, in view of known systems and methods, those skilled in the art will appreciate the use of the present invention for its intended purposes and benefits in any number of alternative embodiments, depending on the specific design and other requirements.

[0032] Figure 1 An exemplary system 100 is depicted for use with devices, systems, and methods for measuring physiological phenomena and physical activities associated with a subject (e.g., measuring signal data, determining a signal quality index, and / or determining the most likely activity associated with sensor data). Figure 1As shown, example system 100 may include one or more wearable devices 120 , one or more monitoring systems 140 , and / or one or more mobile devices 150 connected via one or more networks 110 .

[0033] For example, network 110 may be one or more of a wireless network, a wired network, or any combination of a wireless network and a wired network. For example, network 110 may include one or more of the following: a fiber optic network, a passive optical network, a cable network, an Internet network, a satellite network, a wireless LAN, a global system for mobile communications ("GSM"), a personal communication service ("PCS"), a personal area network ("PAN"), a wireless application protocol (WAP), a multimedia messaging service (MMS), an enhanced messaging service (EMS), a short message service (SMS), a time division multiplexing (TDM)-based system, a code division multiple access (CDMA)-based system, D-AMPS, Wi-Fi, fixed wireless data, IEEE 802.11b, 802.15.1, 802.11n, and 802.11g, a Bluetooth network, or any other wired or wireless network for sending and receiving data signals.

[0034] In addition, the network 110 may include, but is not limited to, telephone lines, optical fibers, IEEE Ethernet 902.3, a wide area network ("WAN"), a local area network ("LAN"), a wireless personal area network ("WPAN"), a wireless body area network ("WBAN"), or a global network such as the Internet. In addition, the network 110 may support an Internet network, a wireless communication network, a cellular network, the like, or any combination thereof. The network 110 may also include one network or any number of networks of the above-described example types, operating as independent networks or in cooperation with one another. The network 110 may utilize one or more protocols of one or more network elements to which they are communicatively coupled. The network 110 may convert other protocols to or from one or more protocols of a network device. Although the network 110 is depicted as a single network, it should be understood that, according to one or more embodiments, the network 110 may include multiple interconnected networks, such as the Internet, a service provider's network, a cable television network, a corporate network, and a home network.

[0035] The wearable device 120 may include, for example, one or more accelerometers 122, one or more gyroscopes 123, one or more photoplethysmography (PPG) sensors 124, one or more electrocardiogram (ECG) sensors 125, one or more temperature sensors 126, one or more humidity sensors 127, position detection technology 128, and / or one or more microprocessors 129. The wearable device may also include other sensors 130, such as any magnetometer or barometer.

[0036] The wearable device 120 may, for example, receive signals and / or data indicative of vital signs (e.g., heart rate, respiratory rate, temperature, blood pressure, blood glucose level, pulse oximetry, etc.), pain measurements, stress measurements (e.g., via vital signs, skin conductance data, etc.), activity measurements (e.g., number of steps taken, number of floors climbed, type of activity, distance the user has moved, gait characteristics, gait speed, etc.). The wearable device 120 may be a limb-worn device (e.g., wrist, arm, ankle, leg, etc.), a chest-worn device, and / or a multi-position-worn device. In various embodiments, the ECG device 110 and / or the wearable device 120 may include a wireless patch, a wired patch, a limb-worn device, and / or an implantable device. For example, the wearable device may be a Figure 5 and Figure 6 For example, a chest-worn patch 502, 602 may be worn on a user / patient 500 / 600, as shown. The chest-worn patch 502, 602 may have any shape and / or may be placed on the chest in any manner.

[0037] Monitoring system 140 may include input / output interface 142, processor 144, and / or data storage device 146. Although monitoring system 140 is depicted as a standalone system, monitoring system 140 may be incorporated into wearable device 120 and / or mobile device 150, for example.

[0038] Monitoring system 140 and / or mobile device 150 may include, for example, one or more mobile devices such as a personal digital assistant (PDA), a tablet computer, and / or an electronic reader (e.g., Kindle Playbook, touchpad, etc.), wearable devices (e.g. Glasses, Apple etc.), telephone equipment, smart phones, cameras, music playing devices (e.g. etc.), televisions, patient monitoring equipment (such as Philips Philips Philips etc.), set-top box equipment, etc.

[0039] The monitoring system 140 and / or the mobile device 150 may also include a network-enabled computer system and / or device. As mentioned herein, a network-enabled computer system and / or device may include, but is not limited to, for example, any computer device or communication device, including, for example, a server, a network device, a personal computer (PC), a workstation, a mobile device, a phone, a handheld PC, a personal digital assistant (PDA), a thin client, a fat client, an Internet browser, or other device. A network-enabled computer system may execute one or more software applications to, for example, receive data as input from an entity accessing the network-enabled computer system, process the received data, send data over a network, and receive data over a network.

[0040] Monitoring system 140 and / or mobile device 150 may include at least one central processing unit (CPU), which may be configured to execute computer program instructions to perform various processes and / or methods. The processes and / or methods as described herein may be understood to refer to computer executable software, firmware, hardware and / or various combinations thereof. Note that in the case where the processes and / or methods include software and / or firmware components, the software and / or firmware are configured to affect the hardware elements of the associated system. It should also be noted that the processes and / or methods shown and described herein are intended to be examples. The processes and / or methods may be combined, integrated, separated or replicated to support various applications. In addition, the functions described herein as being performed at a specific process and / or method may be performed during one or more other processes and / or methods, and may be performed by one or more other devices, rather than or in addition to the functions performed as described. In addition, the processes and / or methods may be implemented across multiple devices or other components that are local or remote to each other. In addition, the processes and / or methods may be moved from one device and added to another device, or may be included in two devices.

[0041] The monitoring system 140 and / or the mobile device 150 may include input / output interfaces 142, 152. The input / output interfaces 142, 152 may also include antennas, network interfaces that may provide or enable wireless and / or wired digital and / or analog interfaces to one or more networks (such as the network 110) through one or more network connections, power supplies that provide appropriate alternating current (AC) or direct current (DC) to power one or more components of the system 100, and buses that allow communication between the various components of the system 100. The input / output interfaces 142, 152 may include a display, which may include, for example, output devices such as printers, display screens (e.g., monitors, televisions, etc.), speakers, projectors, etc. Although not shown, the input / output interfaces 142, 152 may include one or more encoders and / or decoders, one or more interleavers, one or more circular buffers, one or more multiplexers and / or demultiplexers, one or more permuters and / or depermutators, one or more encryption and / or decryption units, one or more modulation and / or demodulation units, one or more arithmetic logic units, and / or components thereof, etc.

[0042] The input / output interface 142, 152 may include a Bluetooth module or chipset with a Bluetooth transceiver, a chip, and an antenna. The transceiver may send and receive information via the antenna and the interface. The chip may include a microprocessor that stores and processes information specific to the micro-net and provides device control functions. The device control functions may include connection creation, frequency hopping sequence selection and timing, power control, security control, polling, packet processing, etc. The Bluetooth API provided by the platform associated with the monitoring system 140 and / or the mobile device 150 may be used to support device control functions and other Bluetooth-related functions. Using the Bluetooth API, applications stored on the monitoring system 140 and / or the mobile device 150 may be able to scan other Bluetooth devices, query local Bluetooth adapters to find paired Bluetooth devices, establish RFCOMM channels, connect to other devices through service discovery, transmit data to and from other devices, and manage multiple connections. The Bluetooth APIs used in the methods, systems, and devices described herein may include an API for Bluetooth Low Energy (BLE) to provide significantly lower power consumption and allow the monitoring system 140 and / or the mobile device 150 to communicate with BLE devices (e.g., the wearable device 120) having low power requirements.

[0043] The input / output interfaces 142, 152 may also include an NFC antenna and a secure element (SE). In one embodiment, the SE may be used for digital and physical secure storage of sensitive data. The SE may include a computer processor or other computing hardware or software.

[0044] The input / output interfaces 142, 152 can implement industry standard NFC transmissions. For example, the input / output interfaces 142, 152 can enable two loop antennas to form an air core transformer when placed close to each other using magnetic induction. The input / output interfaces 142, 152 can operate at 13.56MHz or any other acceptable frequency. In addition, the input / output interfaces 142, 152 can provide a passive communication mode, in which the initiator device provides a carrier field, allowing the target device to respond via modulation of the existing field. Additionally, the input / output interfaces 142, 152 can also provide an active communication mode by allowing alternating field generation of the initiator and target devices.

[0045] The input / output interfaces 142, 152 may deactivate electromagnetic fields used for wireless broadcasting and / or communication during specific (e.g., predefined and / or otherwise specified) intervals. For example, the input / output interfaces 142, 152 may deactivate the RF field while waiting for data. Such deactivation may use Miller-type encoding with varying modulation (including 100% modulation). Deactivation may also use Manchester encoding with varying modulation, including a 10% modulation ratio. Additionally, the input / output interfaces 142, 152 may be able to receive and transmit data simultaneously, as well as check for potential conflicts when the transmit and receive signal frequencies are different.

[0046] The input / output interfaces 142, 152 can utilize standardized transmission protocols. In addition, the input / output modules 142, 152 may be able to utilize transmission protocols and methods developed in the future using other frequencies or transmission modes. The input / output modules 142, 152 may also be backward compatible with existing technologies (e.g., RFID).

[0047] The monitoring system 140 and / or the mobile device 150 may include data storage devices 146, 156, including, for example, random access memory (RAM) and read-only memory (ROM), which may be configured to access and store data and information as well as computer program instructions. The data storage devices 146, 156 may also include storage media or other suitable types of memory (e.g., such as RAM, ROM, programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disks, optical disks, floppy disks, hard disks, removable cassettes, flash drives, any type of tangible and non-transitory storage media) in which files including operating systems, applications (including, for example, web browser applications, email applications, and / or other applications), and data files may be stored. The data storage devices 146, 156 may include electronic information, files, and documents stored in a variety of ways, including, for example, flat files, indexed files, hierarchical databases, relational databases, such as from, for example, The company's software creates and maintains databases, Excel files, Access file or any other storage mechanism.

[0048] Monitoring system 140 and / or mobile device 150 may also include, for example, processors 144, 154, which may be several processors, a single processor, or a single device with multiple processors. Processors 144, 154 may include any range of processing, such as, for example, a single-chip microprocessor or a multi-chip processing unit. In various embodiments, processor 144 and / or processor 154 may execute multiple instructions and / or modules.

[0049] Monitoring system 140 and / or mobile device 150 may include running Any mobile device running the iOS operating system (e.g., iPhone, iPad, Apple Watch, etc.) and / or running Google Any device running an operating system, including, for example Smartphones and other wearable mobile devices such as Glasses or Samsung Galaxy Smartwatches running Microsoft any device running a mobile operating system and / or any other smartphone or similar device.

[0050] Although not shown, the mobile device 150, monitoring system 140, ECG device 110 and / or wearable device 120 may be connected via the network 110 to a system associated with a general practitioner and / or specialist to transmit any received data and / or measurements associated with the monitoring described herein.

[0051] Figure 2 Depicted are exemplary systems that may be used for patient monitoring as described herein. Figure 2 The example system 200 in can enable medical facilities to provide networked services and solutions to patients, such as vital sign monitoring and analysis as described herein. Figure 2 As shown, system 200 may include user device 202 (e.g., wearable device, implantable device, etc. as described herein), network 204, front-end controlled domain 206, back-end controlled domain 212, and back-end 218. Front-end controlled domain 206 may include one or more load balancers 208 and one or more network servers 210. Back-end controlled domain 212 may include one or more load balancers 214 and one or more application servers 216.

[0052] The user device 202 may include some form of network-enabled computing device. As mentioned herein, a network-enabled computing device may include, but is not limited to, for example, any computer device or communication device, including, for example, a wearable device, an implantable device, a thin client, a fat client, an Internet browser, or other device. One or more network-enabled computing devices of the example system 200 may execute one or more software applications to implement, for example, network communications.

[0053] The computing device may include any computer device or communication device, including, for example, a server, a network device, a personal computer (PC), a workstation, a mobile device, a phone, a handheld PC, a personal digital assistant (PDA), a thin client, a fat client, an Internet browser, or other device. These devices may include monitoring devices that receive data from wearable and / or implantable devices. One or more network-enabled computers of the example system 200 may execute one or more software applications to implement, for example, network communications.

[0054] User device 202 may also be a mobile device. For example, a mobile device may include iPhone, iPod, iPad or any other mobile device running Apple's iOS operating system, running Google's Any device running Microsoft's Any device running a mobile operating system and / or any other smartphone or similar wearable mobile device.

[0055] The network 204 may be one or more of a wireless network, a wired network, or any combination of a wireless network and a wired network. For example, the network 204 may include one or more of the following: a fiber optic network, a passive optical network, a cable network, an Internet network, a satellite network, a wireless LAN, a body area network (BAN), a wide area network (WAN), a global system for mobile communications (GSM), a personal communications service (PCS), a personal area network (PAN), D-AMPS, Wi-Fi, fixed wireless data, IEEE 802.11b, 802.15.1, 802.11n, and 802.11g, or any other wired or wireless network for sending and receiving data signals.

[0056] In addition, the network 204 may include, but is not limited to, telephone lines, optical fibers, IEEE Ethernet 902.3, wide area networks (WANs), local area networks (LANs), body area networks (BANs), or global networks such as the Internet. In addition, the network 204 may support an Internet network, a wireless communication network, a cellular network, or the like, or any combination thereof. The network 204 may also include a network or any number of networks of the above-mentioned example types, operating as independent networks or in collaboration with each other. The network 204 may utilize one or more protocols of one or more network elements to which they are communicatively coupled. The network 204 may convert other protocols to one or more protocols of a network device or from other protocols to one or more protocols of a network device. Although the network 204 is depicted as a single network, it should be understood that, according to one or more embodiments, the network 204 may include multiple interconnected networks, such as the Internet, a service provider's network, a cable television network, a corporate network, and a home network.

[0057] A front-end controlled domain 206 may be implemented to provide security for the back-end 218. (One or more) load balancers 208 may distribute the workload across multiple computing resources (e.g., computers, computer clusters, network links, central processing units, or disk drives). In various embodiments, (one or more) load balancers 210 may distribute the workload across, for example, (one or more) network servers 216 and / or back-end 218 systems. Load balancing is intended to optimize resource usage, maximize throughput, minimize response time, and avoid overloading any one resource. Using multiple components with load balancing rather than a single component can increase reliability through redundancy. Load balancing is typically provided by dedicated software or hardware, such as a multilayer switch or a domain name system (DNS) server process.

[0058] The load balancer(s) 208 may include software that monitors ports, such as where external clients (e.g., user devices 202) connect to access various services and / or devices of the medical facility. The load balancer(s) 208 may forward the request to one of the application servers 216 and / or backend 218 servers, which may then reply to the load balancer 208. This may allow the load balancer(s) 208 to reply to the user device 202 without the user device 202 being aware of the internal separation of functions. It may also prevent the user device from contacting the backend servers directly, which may have security benefits by, for example, hiding the structure of the internal network and preventing attacks on the backend 218 or unrelated services running on other ports.

[0059] The load balancer(s) 208 may use various scheduling algorithms to determine which backend server to send a request to. Simple algorithms may include, for example, random selection or round-robin. The load balancer 208 may also consider additional factors, such as the server's reported load, recent response time, up / down status (determined by some monitoring polling), number of active connections, geographic location, capacity, or how much traffic it has been assigned recently.

[0060] The load balancer 208 may be implemented in hardware and / or software. The load balancer(s) 208 may implement many features, including but not limited to: asymmetric loading; priority activation: SSL offloading and acceleration; distributed denial of service (DDoS) attack protection; HTTP / HTTPS compression; TCP offloading; TCP buffering; direct server return; health checking; HTTP / HTTPS caching; content filtering; HTTP / HTTPS security; priority queuing; rate shaping; content-aware switching; client authentication; programmatic traffic manipulation; firewall; intrusion prevention system.

[0061] Web server(s) 210 may include hardware (e.g., one or more computers) and / or software (e.g., one or more applications) that delivers web content that may be accessed, for example, by a client device (e.g., user device 202) over a network (e.g., network 204) such as the Internet. Web server(s) 210 may use, for example, the Hypertext Transfer Protocol (HTTP / HTTPS or sHTTP) to communicate with user device 202. Web pages delivered to client devices may include, for example, HTML documents that may include, in addition to text content, images, style sheets, and scripts.

[0062] A user agent (such as, for example, a web browser, a web crawler, or a native mobile application) may initiate communication by making a request for a particular resource using HTTP / HTTPS, and the web server 210 may respond with the content of the resource or with an error message if unable to do so. The resource may be, for example, a file stored on the back end 218. The web server(s) 210 may also enable or facilitate receiving content from the cardholder device 202, so the cardholder device 202 may be able to, for example, submit a web form, including uploading a file.

[0063] (One or more) web servers can also support server-side scripting using, for example, Active Server Pages (ASP), PHP, or other scripting languages. Thus, the behavior of (one or more) web servers 210 can be scripted in separate files, while the actual server software remains unchanged.

[0064] Load balancer 214 may be similar to load balancer 208 as described above.

[0065] Application server(s) 216 may include hardware and / or software dedicated to efficiently executing processes (e.g., programs, routines, scripts) for applications supporting its applications. Application server(s) 216 may include one or more application server frameworks, including, for example, a Java application server (e.g., Java Platform, Enterprise Edition (Java EE), The company's .NET framework, PHP application server, etc.). Various application server frameworks can include a comprehensive service layer model. In addition, (one or more) application servers 216 can act as a set of components accessible to entities that implement the system 200 through an API defined by the platform itself. For network applications, these components can be executed in, for example, the same operating environment as (one or more) network servers 210, and the application server 216 can support the construction of dynamic pages. (One or more) application servers 216 can also implement services such as clustering, failover, and load balancing. In various embodiments, where the (one or more) application servers 216 are Java application servers, the (one or more) network servers 216 can behave like extended virtual machines for running applications, transparently handling connections to a database associated with the back end 218 on one side, and handling connections to network clients (e.g., client devices 202) on the other side.

[0066] The back end 218 may include hardware and / or software that implements back end services for, for example, a medical facility and / or medical provider or other entity that maintains a distributed system similar to the system 200. The back end 218 may be associated with various databases, including databases that maintain, for example, medical information (e.g., patient data, vital sign data, classifier data, etc.). The back end 218 may also be associated with one or more servers that implement various services provided by the system 200. The back end 218 may enable the medical facility and / or medical provider to implement various functions as shown and described herein.

[0067] refer to Figure 3 , a monitoring system and / or mobile device 300 may be provided, which may be similar (in whole or in part) to monitoring system 140 and / or mobile device 150. For example, Figure 3 The diagram illustrates an example architecture (eg, hardware and software) for an example mobile device and / or monitoring system 300. It should be understood by those skilled in the art that, in the context of the present disclosure, Figure 3The architecture of the mobile device and / or monitoring system 300 depicted in is merely an example, and in some embodiments, additional, fewer, and / or different components may be used to implement similar and / or additional functionality. The mobile device and / or monitoring system 300 may be embodied as a smart phone, a tablet, a mobile computing device, a patient monitoring system, etc. Also, in some embodiments, other types of devices may be used, including workstations, laptops, notebook computers, etc. In some embodiments, the mobile device and / or monitoring system 300 may be used to receive data from a wearable device (e.g., wearable device 120), further process the data received from the wearable device (e.g., wearable device 120), generate alerts and / or report data based on the data received from the wearable device (e.g., wearable device 120), and / or send wearable device data and / or alerts / reports based on the wearable device data.

[0068] The mobile device and / or monitoring system 300 may include at least two different processors, such as a baseband processor (BBP) 304 and an application processor (APP) 308. The baseband processor 304 may primarily handle tasks related to baseband communications. The application processor 308 may handle input and output and / or all applications other than those directly related to baseband processing. The baseband processor 304 may include a dedicated processor for deploying functions associated with a protocol stack (for example, but not limited to a GSM (Global System for Mobile Communications) protocol stack) and other functions. The application processor 308 may include a multi-core processor for running applications (including all or part of the application software). The baseband processor 304 and the application processor 308 may have corresponding associated memories (including random access memory (RAM), flash memory, etc.), peripheral devices, and operating clocks. The memories may also be referred to herein as non-transitory computer-readable media. Note that although depicted as residing in the memory 310, all or part of the application software may be stored in the memory 310, distributed between memories, or reside in other memories.

[0069] The baseband processor 304 may deploy the functionality of a protocol stack to enable the mobile device and / or monitoring system 300 to access one or more wireless network technologies, including WCDMA (Wideband Code Division Multiple Access), CDMA (Code Division Multiple Access), EDGE (Enhanced Data Rates for GSM Evolution), GPRS (General Packet Radio Service), Zigbee (e.g., based on IEEE 802.15.4), Bluetooth, Wi-Fi (Wireless Fidelity, e.g., based on IEEE 802.11) and / or LTE (Long Term Evolution), and variations thereof and / or other telecommunication protocols, standards and / or specifications. The baseband processor 304 may manage radio communications and control functions, including signal modulation, radio frequency shifting and encoding. The baseband processor 304 may include or may be coupled to a radio (e.g., RF front end) 302 and / or a GSM (or other communication standard) modem, as well as analog and digital baseband circuits (ABB, DBB, receive ground). The radio device 302 may include one or more antennas, transceivers, and power amplifiers to enable reception and transmission of multiple signals of different frequencies, thereby enabling access to a cellular (and / or wireless) network. The analog baseband circuit may be coupled to the radio 302 and provide an interface between the analog domain and the digital domain of the GSM modem. The analog baseband circuit may include circuitry including an analog-to-digital converter (ADC) and a digital-to-analog converter (DAC), as well as control and power management / distribution components and an audio codec to process analog and / or digital signals received indirectly via the application processor 308 or directly from a user interface (UI) 318 (e.g., a microphone, headphones, alarm tones, vibrator circuits, touch screens, etc.). The ADC may digitize any analog signal for processing by the digital baseband circuitry.

[0070] The digital baseband circuit may deploy the functionality of one or more levels (e.g., layer 1, layer 2, etc.) of the GSM protocol stack and may include a microcontroller (e.g., a microcontroller unit or MCU, also referred to herein as a processor) and a digital signal processor (DSP, also referred to herein as a processor) that communicate via a shared memory interface (the memory includes data and control information and parameters indicating actions taken on data processed by the application processor 308). The MCU may be embodied as a RISC (Reduced Instruction Set Computer) machine running a real-time operating system (RTIOS), wherein the core has a plurality of peripheral devices (e.g., circuits packaged as integrated circuits), such as RTC (Real Time Clock), SPI (Serial Peripheral Interface), I2C (Inter-Integrated Circuit), UART (Universal Asynchronous Receiver / Transmitter), IrDA (Infrared Data Association) based devices, SD / MMC (Secure Digital / Multimedia Card) card controllers, keyboard scan controllers and USB devices, GPRS encryption modules, TDMA (Time Division Multiple Access), smart card reader interfaces (e.g., Universal Digital / Multimedia Card). For the receive side function, the MCU can instruct the DSP to receive, for example, in-phase / quadrature (I / Q) samples from the analog baseband circuit, and perform detection, demodulation, and decoding, and report back to the MCU. For the transmit side function, the MCU presents the transmittable data and auxiliary information to the DSP, which encodes the data and provides it to the analog baseband circuit (for example, converted to an analog signal by a DAC).

[0071] The application processor 308 may operate under the control of an operating system (OS) that enables a plurality of user applications, including, for example, application software supporting vital sign calculations, alerts, and / or reporting. The application processor 308 may be embodied as a system on a chip (SOC) and support a plurality of multimedia related features, including Internet / cloud-based access functionality for accessing one or more computing devices of (one or more) clouds coupled to the Internet. For example, the application processor 308 may execute communication functionality of application software (e.g., middleware that may include a browser having one or more application program interfaces (APIs) or operable in association with one or more application program interfaces (APIs)) to enable access to a cloud computing framework or other network to provide remote data access / storage / processing, and, through collaboration with an embedded operating system, access to calendars, location services, user data, public data, vital sign data, contact data, etc.

[0072] For example, in some embodiments, vital sign calculations, alarms, and / or reporting may be operated using cloud computing services, wherein processing of raw and / or derived parameter data received indirectly or directly from a wearable device (e.g., wearable device 120) at the mobile device and / or monitoring system 300 may be implemented by one or more devices of the cloud(s), and a trigger signal (to trigger feedback) may be communicated from the cloud(s) (or other devices) to the mobile device and / or monitoring system 300, which in turn may activate feedback within the mobile device and / or monitoring system 300 or relay the trigger signal to other devices.

[0073] The application processor 308 may include a processor core (Advanced RISC Machine or ARM), and may also include or may be coupled to a multimedia module (for decoding / encoding pictures, video and / or audio), a graphics processing unit (GPU), a communication interface 328, and a device interface. The communication interface 328 may include a wireless interface, including a Bluetooth (BT) (and / or in some embodiments, Zigbee and others) module to enable wireless communication with any system component.

[0074] The communication interface 328 may include a Wi-Fi module for interfacing with a local 802.11 network according to corresponding communication software in the application software. The application processor 308 may include or be coupled to a global navigation satellite system (GNSS) receiver 330, which is used to enable access to a satellite network to (for example) provide location coordinates. In some embodiments, the GNSS receiver 330 associated with the GNSS function in the application software can collect context data (time and location data, including location coordinates and altitude) to determine location data associated with the mobile device and / or monitoring system 300. Note that although described as a GNSS receiver 330, other indoor / outdoor positioning systems may be used, including those based on triangulation of cellular network signals and / or Wi-Fi.

[0075] The device interface coupled to the application processor 308 may include a user interface 318, such as a display screen. The display screen may be embodied in one of several available technologies, including an LCD or liquid crystal display (or variants thereof, such as a thin film transistor (TFT) LCD, a plane switching (IPS) LCD), a light emitting diode (LED)-based technology (such as an organic LED (OLED), an active matrix OLED (AMOLED)), a retina-based or tactile technology, or a virtual / augmented reality technology. For example, the user interface 318 may present visual feedback in the form of a message (e.g., alphanumeric) and / or a symbol / graphic (e.g., a warning or alarm icon, a flashing screen, etc.) and / or a flashing light (LED). In some embodiments, in addition to or in lieu of a display screen, the user interface 318 may be configured as a keyboard, a microphone, a speaker, a headphone connector, an I / O interface (e.g., a USB (universal serial bus)), an SD / MMC card, and other peripherals. For example, a speaker may be used to provide feedback audibly, and / or the user interface 318 may include a vibration motor that provides vibration feedback to the user. One or any combination of visual, auditory, or tactile feedback may be used, and as previously described, variations in the intensity of the feedback format may be used.

[0076] An image capture device (image capture) 326 may also be coupled to the application processor 308. The image capture device 326 may include an optical sensor (e.g., a charge coupled device (CCD) or a complementary metal oxide semiconductor (CMOS) optical sensor). The image capture device 326 may be configured to capture and / or receive medical imaging, such as ultrasound and / or other scans.

[0077] The power management device 322 can control and manage the operation of the battery 324 and / or other power sources. Figure 3 The components depicted in the figure may share data via one or more buses, such as via data bus 332. Those skilled in the art will appreciate that, in the context of the present disclosure, the above variations may be deployed in some embodiments to achieve similar functionality.

[0078] The application processor 308 may run and / or execute application software 314 , and may include a vital signs application 315 , a language processing application 316 , and / or a feedback application 317 .

[0079] refer to Figure 4 Methods for utilizing the system components described herein are described. For example, the method can begin at block 402. At block 404, a wearable device (such as wearable device 120) can receive raw sensor data, such as accelerometer data, gyroscope data, magnetometer data, barometer data, PPG data, ECG data, etc., via one or more sensors on the wearable device.

[0080] At box 406, initial processing can be performed, and the partial cycle analysis can determine at least the top three cycles at any point in time. As an example, the initial processing can include smoothing and downsampling the raw sensor data (e.g., an input signal or a measured time series). The partial cycle analysis can include locating fractional cycle markers (e.g., waveform peaks - one to three scales, waveform valleys - one to three scales, and / or zero crossings). The partial cycle analysis can include approximating the cycle lengths and amplitudes of at least three cycles (e.g., A1, CL1, A2, CL2, A3, CL3). The partial cycle analysis can assume three maximum cycles in the body-worn sensor. The partial cycle analysis can approximate the expected cycles (e.g., P1, P2, P3) and associate them with the underlying mathematical model.

[0081] The underlying mathematical model of the chest-worn sensor can be expressed as:

[0082] {y(n)}={xr(n)}+{xg(n)}+{xa(n)}+{w(n)} (1)

[0083] in,

[0084] {y(n)} = observed chest sensor signal

[0085] {xr(n)} = measured respiration signal

[0086] {xg(n)} = measured gait signal

[0087] {xa(n)} = measured artifact signal, and

[0088] {w(n)}=white noise signal

[0089] At box 408, a system component (e.g., a wearable device and / or an implantable device and / or a device communicating with a wearable and / or implantable device) can perform a period-transform-based selection of at least one top cycle observed from the respiratory cycle analysis. Using the period-transform-based selection, a digital signal and / or a time series of physiological data can be detected. For example, the period-transform can decompose the sequence into a sum of periodic sequences by projecting onto a set Pp of periodic subspaces, which can result in leaving a residual in which the period has been removed. The resulting data representation can then be period-linear, rather than frequency-linear or scale-linear.

[0090] By way of example, selection based on period transformation can include estimating the most likely cycle length based on amplitude (e.g., A1, A2, A3) and available cycle lengths (e.g., CL1, CL2, CL3). In this way, selection based on period transformation can include determining whether adjacent cycles show dominant characteristics due to variability within the measurement interval, and if so, determining that a period band is formed and designating the center period within the band as the most likely cycle length.

[0091] As an example, in the presence of three expected cycles, the period can be set to 1 (e.g., P1=1). The linear DC component can then be removed by removing the projection onto the period (e.g., P1=1). Next, the period can be set to the cycle length (e.g., P1=CL1), and the device can check whether the projection (e.g., A1) includes at least a threshold (e.g., T) percentage of the energy in the signal (e.g., X). If so, the device can accept the projection (e.g., A1) and the cycle length (e.g., CL1) as a possible cycle that may exist. This can be repeated for each identified cycle (e.g., CL2, CL3). The most likely cycle length can then be estimated based on the available amplitude and cycle length using the determined data, the variability within the measurement interval, and the period band.

[0092] Additionally, the most likely activity within a particular time may be calculated using the maximum power cycle length of the filtered time series of sensor data, the average power cycle length of the filtered time series of sensor data, and the maximum significant estimated cycle length of the filtered time series of data.

[0093] At box 410, a system component, such as a wearable device and / or an implantable device and / or a device communicating with a wearable and / or an implantable device, can use a heuristic to determine the most likely activity of at least one top cycle observed from a partial cycle analysis. The heuristic can include data and / or data features about characteristics of a respiratory signal, characteristics of a gait signal, characteristics of a motion artifact signal, and / or characteristics of baseline electronic noise. By way of example, data and / or data features that can represent characteristics of a respiratory signal can include continuity, a specific amplitude range, one or more specific cycle lengths (periods), pseudo-periodic properties, dominance in several channels of a sensor (if not all), and correlation with measurements taken in a silent interval. By way of example, data and / or data features that can represent characteristics of a gait signal can include continuity of short durations, a specific amplitude range, one or more specific cycle lengths (periods), pseudo-periods, and differences from measurements taken in a silent interval. By way of example, data and / or data features that may characterize a motion artifact signal may include lack of continuity, a specific amplitude range, one or more specific cycle lengths (periods) (non-periodicity), dominance in several channels of the sensor (if not all), and non-correlation with measurements taken in quiet intervals. For artifacts, data and / or data features that may characterize baseline electronic noise may include: lack of any time period, non-correlation between segments, and bounded amplitude.

[0094] At box 412, a system component (e.g., a wearable device and / or an implantable device and / or a device communicating with a wearable and / or implantable device) can use the presence or absence of period information associated with partial cycle analysis to measure a signal quality index of the input signal. By way of example, data features present in the heuristic method can be used to determine the signal quality index. Or more precisely, the data features in each activity band can be defined by information continuity, band limitations and / or the absence of noise. The signal quality index can identify insignificance as defined by sampling content outside the region of interest in the time domain and / or frequency domain. By way of example, activities such as walking and / or climbing stairs can cause higher frequency content and can be outside the band of breathing activity (e.g., stage 1). Similarly, complete inactivity due to lack of sensor adhesion and / or contact can result in DC content (e.g., event 2). Both types of events can be located outside the region of interest.

[0095] At block 414, a system component (e.g., a wearable device and / or an implantable device and / or a device communicating with the wearable and / or implantable device) may use the signal quality index to determine user characteristics and / or device state information. For example, a sudden change in the signal quality index may indicate a possible posture change. As another example, a sudden increase in DC may push the signal quality index down and would indicate device removal and / or sensor error.

[0096] The method may end at block 416 .

[0097] These examples are illustrative only, and the transaction card may be reprogrammed according to any of the data described herein.

[0098] It should also be noted that the systems and methods described herein may be tangibly embodied in one of more physical media, such as, but not limited to, a compact disc (CD), a digital versatile disc (DVD), a floppy disk, a hard drive, a read-only memory (ROM), a random access memory (RAM), and other physical media capable of storing software, or a combination thereof. In addition, the figures illustrate various components (e.g., servers, computers, processors, etc.) separately. Functions described as being performed at various components may be performed at other components, and the various components may be combined or separated. Other modifications may also be made.

[0099] The present disclosure is not limited to the specific embodiments described in this application, and the embodiments are expected to be illustrations of various aspects. As may be apparent, many modifications and changes can be made without departing from its spirit and scope. In addition to those methods and devices listed herein, functionally equivalent methods and devices within the scope of the present disclosure can be apparent from the foregoing representative descriptions. Such modifications and changes are expected to be within the scope of the attached representative claims. The present disclosure is limited only by the items of the attached representative claims together with the full scope of equivalents to which the representative claims are entitled. It should also be understood that the terms used herein are only for the purpose of describing specific embodiments and are not intended to be limiting.

[0100] With respect to the use of substantially any plural and / or singular terms herein, those skilled in the art may convert the plural to the singular and / or the singular to the plural as is appropriate to the context and / or application. For clarity, various singular / plural arrangements may be expressly set forth herein.

[0101] Those skilled in the art will appreciate that, in general, the terms used herein and particularly in the appended claims (e.g., the bodies of the appended claims) are generally intended to be "open" terms (e.g., the term "comprising" should be interpreted as "comprising (but not limited to)", the term "having" should be interpreted as "having at least", the term "including" should be interpreted as "including (but not limited to)", etc.). Those skilled in the art will also appreciate that if a specific number of an introduced claim recitation is intended, such an expectation may be expressly recited in the claim, and in the absence of such a recitation, such an expectation is not present. For example, as an aid to understanding, the following appended claims may contain the use of the introductory phrases "at least one" and "one or more" to introduce claim recitations. However, the use of such phrases should not be construed to imply that the introduction of a claim recitation by the word "a" or "an" limits any particular claim containing such introduced claim recitation to embodiments containing only one such recitation, even when the same claim contains the introductory phrases "one or more" or "at least one" and, for example, the word "a" or "an" (e.g., "a" or "an" should be construed to mean "at least one" or "one or more"); the same applies to the use of "a" or "the" to introduce a claim recitation. In addition, even if a specific number of an introduced claim recitation is explicitly recited, such recitation should be construed to mean at least the number of recitations (e.g., the simple recitation of "two recitations" without other modifiers means at least two recitations, or two or more recitations). In addition, in those instances where idioms similar to "at least one of A, B, and C, etc." are used, generally, this structure is intended to be said in the sense that a person skilled in the art would understand the idiom (e.g., "a system having at least one of A, B, and C" would include (but not be limited to) systems having only A, only B, only C, A and B together, A and C together, B and C together, and / or A, B and C together, etc.). In those instances where idioms similar to "at least one of A, B, or C, etc." are used, generally, this structure is intended to be said in the sense that a person skilled in the art would understand the idiom (e.g., "a system having at least one of A, B, or C" would include (but not be limited to) systems having only A, only B, only C, A and B together, A and C together, B and C together, and / or A, B and C together, etc.). A person skilled in the art would further understand that virtually any disjunctive word and / or phrase presenting two or more alternative terms, whether in the specification, claims, or drawings, should be understood to encompass the possibility of including one of the terms, any of the terms, or both of the terms. For example, the phrase "A or B" can be understood to include the possibilities of "A" or "B" or "A and B."

[0102] The foregoing description, together with its associated embodiments, is presented for illustrative purposes only. It is not exhaustive and does not limit the invention to the precise form disclosed. Those skilled in the art will appreciate from the foregoing description that, in view of the above teachings, modifications and variations are possible, or modifications and variations may be obtained by practicing the disclosed embodiments. For example, the steps described need not be performed in the same order discussed or with the same degree of separation. Similarly, various steps may be omitted, repeated or combined as needed to achieve the same or similar goals. Therefore, the present invention is not limited to the embodiments described above, but is alternatively limited by the appended claims in view of the full scope of its equivalents.

[0103] In the previous description, various preferred embodiments have been described with reference to the accompanying drawings. However, it will be appreciated that various modifications and variations may be made thereto, and additional embodiments may be implemented, without departing from the broader scope of the invention as set forth in the appended claims. Therefore, this specification and the accompanying drawings should be regarded as illustrative and not in a restrictive sense.

Claims

1. A device (120), comprising: an accelerometer (122) configured to receive accelerometer data; a gyroscope (123) configured to receive gyroscope data; as well as A microprocessor (129) configured to: performing a partial cycle analysis based on at least one of the accelerometer data and the gyroscope data to determine at least top three cycles, wherein the partial cycle analysis comprises: identifying one or more fractional cycle markers in said at least one of said accelerometer data or said gyroscope data, said fractional cycle markers comprising at least one of: a waveform peak, a waveform valley, and a zero crossing; The at least top three cycles are determined based on: approximating cycle lengths CL and amplitudes A of at least three cycles assumed to be present in the data based on the fractional cycle markers; and approximating an expected period P of each of the three cycles based on the cycle length CL for each of the three cycles; performing a period transformation (PT) based selection of at least one top period observed from the partial cycle analysis, the PT based selection comprising, for each of the expected periods P of the three cycles: Projecting the data onto a periodic subspace corresponding to the expected period P; checking whether the projection comprises at least a threshold T percentage of the total energy in a signal comprised by the data, and if so, accepting the cycle to which the period corresponds as a possible cycle present in the data; and estimating a most likely cycle length based on the cycle lengths and amplitudes of the identified possible cycles; and A heuristic is used to determine a most likely activity for the at least one top cycle.

2. The device according to claim 1, wherein: The most likely motion includes at least one of: sudden motion, sustained motion, slow chest wall movement, deep chest wall movement, and severe vibration.

3. The device according to claim 1, wherein: The PT-based selection is performed by: (a) Assume threshold (T); (b) obtaining a signal X of length N via at least one of the accelerometer data and the gyroscope data; (c) locating a fractional cycle marker for each of the at least top three cycles; (d) Approximate cycle length (CL) for each cycle i ) and amplitude (A i ), where i is a cycle; (e) approximating the expected period for each cycle; (f) correlating the expected period with the fractional cycle marker for each cycle; (g) setting the expected period equal to one; (h) removing the linear DC component by removing the projection onto a first expected period equal to one; (i) Let the expected period be equal to CL1; (j) determining whether A1 contains at least T% of the energy in X; (k) If A1 contains at least T% of the energy in X, then accept A1 and CL1 as possible cycles; (l) For each CL i and A i Repeat steps (i)-(k); and (m) based on each cycle length (CL i ) and the amplitude of each cycle (A i ) to estimate the most likely cycle length.

4. The device according to claim 3, wherein: If adjacent periods show dominant behavior due to variability within the measurement interval, a periodic band is formed and the central period within the band is assigned as the most probable cycle length.

5. The device according to claim 1, wherein: The heuristic is based on at least one of: a specific amplitude range, a specific cycle length, data indicating continuity, data indicating the duration of continuity, data indicating a periodic nature, data indicating in what channel of the sensor the signal dominates, and a degree of correlation with measurements taken in a silent interval.

6. The device according to claim 1, wherein: The microprocessor is further configured to measure a signal quality index (SQI) of an incoming signal associated with at least one of the accelerometer data and the gyroscope data using the presence or absence of period information associated with the partial cycle analysis.

7. The device according to claim 1, wherein: The accelerometer and the gyroscope are housed in a wearable device.

8. The device according to claim 7, wherein: The wearable device is configured to be worn on the chest of a patient.

9. The device according to claim 1, wherein: The accelerometer data is received on demand.

10. The device according to claim 1, wherein: The gyroscope data is received on demand.

11. The device according to claim 6, wherein: A sudden change in the SQI for a duration less than the first SQI threshold indicates a change in attitude.

12. The device according to claim 1, wherein: The microprocessor is also configured to determine a signal quality index (SQI) associated with the most likely activity.

13. The apparatus according to claim 1, wherein: The heuristic includes at least one of: a maximum power cycle length associated with the accelerometer data, a maximum power cycle length associated with the gyroscope data, an average power cycle length associated with the accelerometer data, an average power cycle length associated with the gyroscope data, a maximum significant estimated cycle length associated with the accelerometer data, and a maximum significant estimated cycle length associated with the gyroscope data.

14. The apparatus according to claim 1, wherein: The partial cycle analysis is performed by mapping the cycles successively onto regions of maximum amplitude, minimum amplitude and zero crossing intervals and their periods.

15. The device according to claim 14, wherein: Cycles were selected to be at least the top three cycles based on amplitude threshold and cycle repeatability.

16. The apparatus according to claim 14, wherein: The cycles are selected to be at least the top three cycles based on the effective signal quality index.

17. The device according to claim 16, wherein: A baseline measurement noise magnitude is calculated and subtracted from magnitude measurements associated with at least one of the accelerometer data and the gyroscope data.

18. A method comprising: Receiving accelerometer data via an accelerometer of the wearable device (404); Receiving gyroscope data via a gyroscope of the wearable device (404); Performing a partial cycle analysis (406) based on at least one of the accelerometer data and the gyroscope data to determine at least top three cycles, wherein the partial cycle analysis includes: identifying one or more fractional cycle markers in said at least one of said accelerometer data or said gyroscope data, said fractional cycle markers comprising at least one of: a waveform peak, a waveform valley, and a zero crossing; The at least top three cycles are determined based on: approximating cycle lengths CL and amplitudes A of at least three cycles assumed to be present in the data based on the fractional cycle markers; and approximating an expected period P of each of the three cycles based on a cycle length CL for each of the three cycles; Performing a period transformation (PT) based selection (408) of at least one top period observed from the partial cycle analysis, the PT based selection comprising, for each of the expected periods P of the three cycles: Projecting the data onto a periodic subspace corresponding to the expected period P; checking whether the projection comprises at least a threshold T percentage of the total energy in a signal comprised by the data, and if so, accepting the cycle to which the period corresponds as a possible cycle present in the data; and estimating a most likely cycle length based on the cycle lengths and amplitudes of the identified possible cycles; and A most likely activity for the at least one top period is determined using a heuristic (410).

19. The method according to claim 18, wherein: The most likely activity is breathing, and the top cycle is the breathing rate.

20. The method according to claim 18, wherein: The most likely motion includes at least one of: sudden motion, sustained motion, slow chest wall movement, deep chest wall movement, and severe vibration.

21. The method according to claim 18, wherein: The PT-based selection is performed by: (a) Assume threshold (T); (b) obtaining a signal X of length N via at least one of the accelerometer data and the gyroscope data; (c) locating a fractional cycle marker for each of the at least top three cycles; (d) Approximate cycle length (CL) for each cycle i ) and amplitude (A i ), where i is a cycle; (e) approximating the expected period for each cycle; (f) correlating the expected period with the fractional cycle marker for each cycle; (g) Let the expected period be equal to one; (h) removing the linear DC component by removing the projection onto a first expected period equal to one; (i) setting the expected period equal to CL1; (j) determining whether A1 contains at least T% of the energy in X; (k) If A1 contains at least T% of the energy in X, then accept A1 and CL1 as possible cycles; (l) For each CL i and A i Repeat steps (i)-(k); and (m) based on each cycle length (CL i ) and the amplitude of each cycle (A i ) to estimate the most likely cycle length.

22. The method according to claim 21, wherein: The ratio of the magnitudes of the most likely cycle lengths indicates a signal quality index.

23. The method according to claim 21, wherein: The magnitude of the most likely cycle length and the presence of each magnitude relative to the region of interest determine a signal quality index for each estimate.