Assessment of airway constriction based on trends of ratio between exhalation time and inhalation time

Abstract

To provide assessment of airway constriction based on trends of a ratio between an exhalation time and an inhalation time.SOLUTION: Technologies are provided for monitoring of status changes of a cardiopulmonary condition. In some cases, a method includes: receiving, thoracic impedance (TI) measurement signals corresponding to a subject, the TI measurement signals being time-dependent and obtained during a time interval; generating, using the TI measurement signals, respiration signals corresponding to the subject during the time interval; determining, over the time interval, using the respiration signals, multiple values of a ratio between an exhalation time and an inhalation time of the subject; monitoring, over the time interval, using the multiple values, a time dependence of the ratio; and identifying, based on the time dependence, a status change of a cardiopulmonary condition of the subject.SELECTED DRAWING: None

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of and priority to U.S. Provisional Patent Application No. 63 / 625,749, filed January 26, 2024, U.S. Provisional Patent Application No. 63 / 625,741, filed January 26, 2024, U.S. Provisional Patent Application No. 63 / 625,787, filed January 26, 2024, U.S. Provisional Patent Application No. 63 / 551,972, filed February 9, 2024, U.S. Provisional Patent Application No. 63 / 551,956, filed February 9, 2024, and U.S. Provisional Patent Application No. 63 / 551,957, filed February 9, 2024, the contents of each of which are incorporated herein by reference in their entirety. [Background technology]

[0002] Cardiopulmonary conditions are chronic medical conditions, including chronic obstructive pulmonary disease (COPD) and congestive heart failure (CHF). In particular, COPD is associated with the coexistence of emphysema and chronic bronchitis, which can have varying degrees of severity. Even with treatment, cardiopulmonary conditions can worsen over time. Consequently, depending on the severity of the exacerbation, subjects suffering from the condition may undergo significant medical intervention. Additionally, patients with more severe exacerbations experience more exacerbations. Therefore, monitoring the status of a cardiopulmonary condition can help avoid medical intervention. However, monitoring the status of a cardiopulmonary condition typically involves outpatient care. While the status of a cardiopulmonary condition can be periodically updated by a clinician during visits to a healthcare facility, the time between visits can lead to a worsening of the cardiopulmonary condition without appropriate treatment. Furthermore, subjects suffering from a cardiopulmonary condition may have difficulty adhering to a long-term outpatient care routine for monitoring the status of their cardiopulmonary condition. The consequence of non-adherence can be identifying a change in cardiopulmonary status after a long-term deterioration in cardiopulmonary status or when the subject is in distress, both situations clearly undesirable and detrimental to a favorable prognosis.

[0003] Thus, several technical challenges remain in monitoring cardiopulmonary conditions and in the art for such monitoring, and improved techniques that address these challenges are desirable. Summary of the Invention

[0004] Embodiments of the present disclosure address the problem of identifying changes in a subject's cardiopulmonary status.

[0005] In some aspects, the present disclosure provides a system including: a wearable device configured to be attached to a torso of a subject, the wearable device including a plurality of electrodes and a plurality of sensor devices, each electrode of the plurality of electrodes configured to contact a respective skin area at a respective skin location on the torso of the subject, the plurality of sensor devices including an electrical sensor device operatively coupled to the plurality of electrodes and configured to generate a first measurement signal during a measurement period and a motion sensor device configured to generate a second measurement signal during the measurement period; and a computing device configured to communicate with the wearable device, receive the first measurement signal and the second measurement signal, and use a combination of the first measurement signal and the second measurement signal to determine a value of a metric or a respective value in a combination of metrics, each metric and combination of metrics indicating a status of a cardiopulmonary condition of the subject.

[0006] In some aspects, the present disclosure provides a method that includes generating, by one or more processors, individually or collectively, a respiratory signal corresponding to a subject using time-dependent thoracic impedance (TI) measurement signals during a time interval, generating, by one or more processors, individually or collectively, a movement signal corresponding to movement of the subject's chest wall using time-dependent acceleration measurement signals during the time interval, determining, by one or more processors, individually or collectively, a plurality of values of a metric associated with the subject's respiration over the time interval using the respiratory signal and the movement signal, monitoring, by one or more processors, individually or collectively, the time-dependence of the metric over the time interval using the plurality of values, and identifying, by the one or more processors, individually or collectively, a change in cardiopulmonary status of the subject based on the time-dependence.

[0007] In some aspects, the present disclosure provides a computing system including at least one processor and at least one memory device storing processor-executable instructions that, when executed by the at least one processor individually or jointly, cause the computing system to at least: use time-dependent thoracic impedance (TI) measurement signals during a time interval to generate a respiratory signal corresponding to a subject; use time-dependent acceleration measurement signals during the time interval to generate a movement signal corresponding to movement of the subject's chest wall; determine, over the time interval, using the respiratory signal and the movement signal, multiple values of a metric associated with the subject's respiration; monitor, over the time interval, the time-dependence of the metric using the multiple values; and identify a change in cardiopulmonary status of the subject based on the time-dependence.

[0008] In some aspects, the present disclosure provides a user device including at least one processor and at least one memory device storing processor-executable instructions that, when executed by the at least one processor individually or jointly, cause the user device to at least: use time-dependent thoracic impedance (TI) measurement signals during a time interval to generate a respiratory signal corresponding to a subject; use time-dependent acceleration measurement signals during the time interval to generate a movement signal corresponding to movement of the subject's chest wall; determine, over the time interval, multiple values of a metric associated with the subject's respiration using the respiratory signal and the movement signal; monitor the time-dependence of the metric using the multiple values during the time interval; and identify a change in cardiopulmonary status of the subject based on the time-dependence.

[0009] In some aspects, the present disclosure provides a method that includes receiving, by one or more processors, individually or collectively, a thoracic impedance (TI) measurement signal corresponding to a subject, the TI measurement signal being time-dependent and acquired during a time interval; generating, by the one or more processors, individually or collectively, a respiratory signal corresponding to the subject during the time interval using the TI measurement signal; determining, by the one or more processors, individually or collectively, a plurality of values of a ratio between the subject's expiration time and inspiration time over the time interval using the respiratory signal; monitoring, by the one or more processors, individually or collectively, the time-dependence of the ratio over the time interval using the plurality of values; and identifying, by the one or more processors, individually or collectively, a change in cardiopulmonary status of the subject based on the time-dependence. In some cases, the TI measurement signal may be received from a wearable device attached to the subject's torso.

[0010] In some aspects, the present disclosure provides a computing system including at least one processor and at least one memory device storing processor-executable instructions that, when executed by the at least one processor individually or jointly, cause the computing system to at least receive a thoracic impedance (TI) measurement signal corresponding to a subject, the TI measurement signal being time-dependent and acquired during a time interval; generate a respiratory signal corresponding to the subject during the time interval using the TI measurement signal; determine, over the time interval, using the respiratory signal, a plurality of values of a ratio between the subject's expiration time and inspiration time; monitor, over the time interval, the plurality of values, the time-dependence of the ratio; and identify a change in cardiopulmonary status of the subject based on the time-dependence. In some cases, the TI measurement signal may be received from a wearable device attached to the subject's torso.

[0011] In some aspects, the present disclosure provides a user device including at least one processor and at least one memory device storing processor-executable instructions that, when executed by the at least one processor individually or jointly, cause the user device to at least receive a thoracic impedance (TI) measurement signal corresponding to a subject, the TI measurement signal being time-dependent and acquired during a time interval; generate a respiratory signal corresponding to the subject during the time interval using the TI measurement signal; determine, over the time interval, using the respiratory signal, a plurality of values of a ratio between the subject's expiration time and inspiration time; monitor, over the time interval, the plurality of values, the time dependence of the ratio; and identify a change in cardiopulmonary status of the subject based on the time dependence. In some cases, the TI measurement signal may be received from a wearable device attached to the subject's torso. [Brief explanation of the drawings]

[0012] The accompanying drawings form part of this disclosure and are incorporated into the subject specification. The drawings illustrate exemplary aspects of the disclosure and, together with the following detailed description, serve to explain, at least in part, various principles, features, or aspects of the disclosure. Several aspects of the disclosure are described more fully below with reference to the accompanying drawings. However, various aspects of the disclosure may be implemented in many different forms and should not be construed as limited to the implementations set forth herein. Like numbers refer to like elements throughout.

[0013] [Figure 1] 1 is a schematic block diagram of an example of a system for monitoring changes in cardiopulmonary status, in accordance with one or more aspects of the present disclosure. FIG. [Figure 2A] FIG. 1 is a schematic diagram of an example of a user interface, according to one or more aspects of the present disclosure. [Figure 2B] 1 presents plots of an example of a volume of processed air as a function of time during a period of respiratory motion and an example of a thoracic impedance signal during a period of respiratory motion, in accordance with one or more aspects of the present disclosure. [Figure 2C] 1 presents an exemplary plot of the volume of processed air as a function of time during a time interval including a period of respiratory movement immediately followed by a pause in respiratory movement, and an exemplary plot of the thoracic impedance signal during the time interval, in accordance with one or more aspects of the present disclosure. [Figure 3] 1 presents an example of a wearable device according to one or more aspects of the present disclosure. [Figure 4] 1A-1D are schematic diagrams of a subject at two different moments during a pulmonary ventilation cycle, in accordance with one or more embodiments of the present disclosure. [Figure 5] 1 is a plot of an example of a pulmonary ventilation signal obtained using a subject mean-removed thoracic impedance measurement signal, in accordance with one or more aspects of the present disclosure. [Figure 6A] 1 presents plots of inertial measurement signals for two channels of a three-axis accelerometer, both as observed (or "raw") and after processing according to aspects of the present disclosure. [Figure 6B]1 presents a plot of an example pulmonary ventilation signal and a plot of an example chest wall motion signal according to one or more aspects described herein. [Figure 7] 10 presents plots of an example thoracic impedance signal, an example airflow signal, and an example chest wall motion signal according to one or more aspects described herein. [Figure 8A] 1 presents plots of an exemplary mean-removed thoracic impedance signal and an example of a chest wall motion signal for stable COPD, according to one or more embodiments described herein. [Figure 8B] 1 presents plots of an exemplary mean-removed thoracic impedance signal and an exemplary chest wall motion signal during a peak exacerbation of COPD, according to one or more embodiments described herein. [Figure 9A] 1 presents a schematic plot of metrics as a function of time, according to one or more aspects of the present disclosure. [Figure 9B] 1 presents a schematic plot of two metrics as a function of time, according to one or more aspects of the present disclosure. [Figure 10] FIG. 1 is a deviation diagram of SpO2 versus thoracic impedance for a subject with an acute exacerbation of chronic obstructive pulmonary disease (AECOPD), in accordance with one or more embodiments of the present disclosure. [Figure 11A] FIG. 1 is a schematic block diagram of a processing platform for monitoring cardiopulmonary status changes, in accordance with one or more aspects of the present disclosure. [Figure 11B] FIG. 1 is a schematic block diagram of an example of a computing device capable of providing various functionality for monitoring cardiopulmonary status changes in accordance with one or more aspects of the present disclosure. [Figure 12] FIG. 1 is a schematic block diagram of another example of a system for monitoring changes in cardiopulmonary status, in accordance with one or more aspects of the present disclosure. [Figure 13] FIG. 10 is a schematic block diagram of yet another example of a system for monitoring changes in cardiopulmonary status, in accordance with one or more aspects of the present disclosure. [Figure 14]1 illustrates an exemplary method for determining a change in cardiopulmonary status, according to one or more aspects of the present disclosure. [Figure 15] 1 illustrates an exemplary method for determining a change in cardiopulmonary status, according to one or more aspects of the present disclosure. [Figure 16] 1 illustrates an exemplary method for determining a change in cardiopulmonary status, according to one or more aspects of the present disclosure. [Figure 17] 1 illustrates an exemplary method for determining a change in cardiopulmonary status, according to one or more aspects of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0014] Embodiments of the present disclosure may address the problem of identifying changes in the status of a subject's cardiopulmonary condition. Cardiopulmonary conditions include, for example, chronic obstructive pulmonary disease (COPD) and congestive heart failure (CHF). As previously mentioned, COPD is a combination of emphysema and chronic bronchitis of varying severity. Even when treated, these conditions can become gradually debilitating and may require significant medical intervention. Therefore, monitoring the status of one or more cardiopulmonary conditions can help avoid medical intervention. Monitoring the status of a cardiopulmonary condition typically involves outpatient care. As a result, a worsening cardiopulmonary condition may be identified during a visit to a clinic or doctor's office. Thus, in some cases, a condition may have been gradually worsening and / or may have been inadequately treated for an extended period of time prior to a visit to a clinic or doctor's office. Long-term deterioration of a cardiopulmonary condition or inadequate treatment of a condition for an extended period of time can have dire consequences for the subject, which in some cases may result in expensive medical intervention and an unfavorable prognosis. Furthermore, subjects may have difficulty adhering to a long-term outpatient routine for monitoring cardiopulmonary status, which may lead to identifying a change in status after a long-term deterioration in cardiopulmonary status or when the subject is in distress, both situations being clearly undesirable and detrimental to a favorable prognosis.

[0015] Embodiments of the technology described herein provide systems, devices, techniques, and computer program products that individually or collectively enable monitoring of a subject's cardiopulmonary status and / or simultaneous identification of changes in cardiopulmonary status. Such monitoring is non-ambulatory in that the monitoring can be performed without a visit to a medical service facility and can occur in a residence (e.g., a home, a group home, a nursing home, etc.) located remotely from the medical service facility. Thus, simply for the sake of name, the monitoring described herein can be referred to as non-ambulatory monitoring. Some systems according to the present disclosure include a wearable device that can be attached to the subject's torso. The wearable device can operate according to one or a combination of multiple sensing modalities and thus provide one or several types of measurement signals associated with the subject's bodily functions. To that end, the wearable device can include multiple electrodes and multiple sensor devices. Each electrode of the multiple electrodes is configured to contact a respective skin region at a respective skin location on the subject's torso. The multiple electrodes can be arranged in a specific layout, for example, on the subject's chest. The multiple sensor devices can include an electrical sensor device operatively coupled to the multiple electrodes. The electrical sensor device may measure voltage, current, impedance, a combination thereof, or a similar physical quantity. The electrical sensor device is configured to generate a measurement signal. The measurement signal may be generated during a measurement period. The measurement period may span several pulmonary ventilation cycles (also referred to as respiratory movement cycles). The first measurement signal may include a thoracic impedance (TI) measurement signal. The TI measurement signal may be generated in a four-point (or four-electrode) measurement configuration and at a defined sampling rate (e.g., 40 KHz).

[0016] Additionally, or in some cases, the plurality of sensor devices may include one or more acoustic sensor devices configured to generate other measurement signals. Such other measurement signals may be generated during the measurement period. The acoustic sensor devices may, individually or in specific combinations, probe sounds originating from or propagating through organs present in the thoracic cavity and / or adjacent areas. For example, a first acoustic sensor device or devices of one or more of the acoustic sensor devices may function as a pulmonary auscultation probe.

[0017] Additionally, or in yet other cases, the plurality of sensors includes an inertial sensor device configured to generate additional measurement signals. Such additional measurement signals may be generated during the measurement period. The inertial sensor device may be a three-axis accelerometer, and the measurement signals generated by the inertial sensor device may be used to generate a movement signal corresponding to movement of the subject's chest wall during a time interval, such as the measurement period.

[0018] Additionally, or in some configurations, the plurality of sensor devices may also include an optical device capable of measuring an oxygen saturation level and generating a measurement signal accordingly. For example, the optical device may be a pulse oximeter. Additionally, or in other configurations, the plurality of sensor devices may also include a blood pressure monitor.

[0019] It should be noted that embodiments of the technology described herein are not limited to the sensor devices described herein, and more or fewer sensor devices may form part of a wearable device according to aspects of the present disclosure.

[0020] A system according to an aspect of the present disclosure may also include a processing platform having a plurality of computing devices. The computing devices may be server devices arranged in a cloud architecture. At least one of the server devices may operate as a gateway device. At least one of the server devices may operate as a computation node. At least one of the server devices may operate as a storage node.

[0021] The processing platform may be operatively coupled or otherwise configured to communicate with the wearable device. In some cases, the processing platform is operatively coupled to the wearable device via one or more networks (wireless networks, wired networks, or a combination of both). The processing platform may receive measurement signals generated by the wearable device over time via the network and at least one of the plurality of computing devices. The processing platform may implement a number of processes based on the measurement signals received via at least one of the plurality of computing devices. At least some of the processes may include determining the value of a particular metric or a combination of metrics based on the measurement signals. In some cases, the particular metric indicates the status of the subject's cardiopulmonary condition. Additionally, or in other cases, a combination of metrics indicates the status of the subject's cardiopulmonary condition. Examples of metrics include respiration rate (RR), tidal volume (TV), the ratio between the subject's exhalation time and inhalation time, and the delay between the mechanical start of inspiration and the start of inspiratory airflow. Note that the metric may be a quantity directly probed by the measurement signal generated by the sensor device. For example, the metric could be blood oxygen level measured directly by an oximeter present in the wearable device.

[0022] At least some of the processes, when implemented, can enable tracking of temporal changes in multiple metrics. Thus, the process can include determining multiple values of a particular metric or combination of metrics over a time interval. The time interval spans two or more measurement intervals, each of which results in a metric value for each of the tracked metrics. The process can also include monitoring using multiple values, the time dependence of a particular metric, or a combination of metrics, over the time interval. In some cases, monitoring such time dependence can include updating parameters that define a function (linear or otherwise) that fits to currently determined values of a particular metric or combination of metrics. Additionally, or in other cases, monitoring such time dependence can include updating parameters that define a rolling average of currently determined values of a particular metric or combination of metrics. Regardless of how the time dependence is monitored, the time dependence of a single metric or combination or any of the metrics can convey a trend (e.g., an upward trend, a downward trend, or an essentially constant trend). Thus, by monitoring one or more metrics individually and / or a combination of two or more metrics, embodiments of the technology described herein can provide for the detection and differentiation of cardiopulmonary exacerbations. Thus, embodiments of the technology described herein provide improvements over current techniques for monitoring and managing cardiopulmonary conditions.

[0023] At least some of the systems according to the technology described herein also include a computing device that can be located remotely from the processing platform. The computing device can also be operatively coupled or otherwise configured to communicate with the processing platform via one or more networks. In some cases, such networks can be the same networks that enable the wearable device to be operatively coupled with the processing platform described herein. The computing device can be associated with or otherwise operated by a clinician and / or insurance provider. The clinician can be involved in providing medical care for a subject's cardiopulmonary condition. Thus, the computing device can receive information related to the status of the subject's cardiopulmonary condition and / or changes in the status of the subject's pulmonary condition. At least a portion of the information can be formatted as an electronic message that can be presented by a software application or another type of program code configured to execute on the computing device. The computing device can receive and present the information via the software application. The software application can be a mobile application, a web browser, or another type of executable program code.

[0024] The computing device may also be operatively coupled or otherwise configured to communicate with a user device via one or more networks. In some cases, such a network may be the same network that enables the computing device to be operatively coupled with the processing platform described herein. In some configurations, the user device may be part of one or more systems in accordance with the techniques described herein. The user device may be associated with and operated by a subject wearing a wearable device and / or by an assistant (e.g., a family member or another type of caregiver, such as a nurse, nurse assistant, or nursing home staff member) assisting the subject in performing measurements. The user device may be configured with a software application or another type of program code for exchanging information with the computing device. Thus, the computing device may provide, via a software application configured on the computing device, an indication of an action to be taken by the subject in response to a particular value of a monitored metric and / or a status change in the cardiopulmonary condition. The type of action may be associated with the nature of the status change. In accordance with aspects described herein, an indication of an action the subject may take or have taken as the subject monitors the subject's cardiopulmonary condition over a measurement period, an examination period, and / or an analysis period may be provided. Thus, various actions directed to improving monitoring of cardiopulmonary conditions and / or improving the cardiopulmonary conditions themselves can be implemented with much greater immediacy than common techniques and approaches for monitoring cardiopulmonary conditions. As a result, embodiments of the technology described herein provide improvements over common techniques and approaches for monitoring and / or managing cardiopulmonary conditions.

[0025] The user devices described above may be operatively coupled or otherwise configured to communicate with the wearable device. The user devices may also be operatively coupled or otherwise configured to communicate with the processing platform via one or more networks. In some cases, such networks may be the same networks that enable the wearable device to be operatively coupled with the processing platform described herein.

[0026] A software application or another type of program code configured on the user device can control the manner in which measurements are performed using the wearable device. To that end, in response to the software application being executed, the user device can present a user interface that allows the user to configure a measurement session, e.g., a measurement period, the number of measurements performed during the measurement period, a combination thereof, or similar attributes of the measurement session. The user device can also present one or more other user interfaces that display various types of information, including observed data from the measurements (e.g., electrocardiogram (ECG) data, thoracic impedance, SpO2, etc.).

[0027] FIG. 1 is a schematic block diagram of an example of a system 100 for monitoring cardiopulmonary status changes according to aspects of the present disclosure. The example system 100 may include a wearable device 110 that may be mounted on the torso of a subject 104. While the wearable device 110 is depicted as being mounted on a particular side of the torso of the subject 104, the placement of the wearable device 110 is not limited in that respect. In some cases, when mounted on the subject 104, the wearable device 110 may extend from one side of the torso to another side of the torso. Thus, the wearable device 110 may be mounted on the front side of the torso, the back side of the torso, a lateral side of the torso, or in a placement extending from one side of the torso (e.g., the front, back, or side) to another different side. The wearable device 110 may operate according to one or a combination of multiple sensing modalities. Thus, the wearable device 110 can individually or collectively provide one or several types of measurement signals associated with a bodily function of the subject 104. For example, the bodily function may be a respiratory function or a cardiac function. The wearable device 110 includes a plurality of electrodes 114 and a plurality of sensor devices 118. Each electrode of the plurality of electrodes 114 is configured to contact a respective skin section of the torso of the subject 104.

[0028] The plurality of sensor devices 118 includes a group of electrical sensor devices 120a coupled to the plurality of electrodes 114. Each electrical sensor device in the group of electrical sensor devices 120a can measure voltage, current, impedance, a combination thereof, or a similar physical quantity. Additionally, each electrical sensor device in the group of electrical sensor devices 120a is configured to generate a measurement signal during a measurement period. The measurement signal may be referred to as an electrical measurement signal. The electrical measurement signals generated over time can be used to monitor the cardiopulmonary condition of the subject 104 by probing pulmonary ventilation and / or cardiac characteristics. Thus, as described herein, a measurement period can span several pulmonary ventilation cycles (also referred to as respiratory cycles), with each cycle spanning between the start of inspiration and the end of expiration. A measurement period can have a short duration corresponding to the time span of a few or several breaths of the subject. Additionally, or in other cases, a measurement period can have a long duration that can range from several minutes to several days. By way of example only, in some cases, a measurement period has a duration within a range of about 15 seconds to about 120 seconds. Examples of measurement periods include 15 seconds, 25 seconds, 30 seconds, 45 seconds, 60 seconds, 70 seconds, 80 seconds, 90 seconds, 100 seconds, 110 seconds, and 120 seconds. As another example, in other cases, the measurement period has a duration ranging from about 25 seconds to about 5 days.

[0029] Certain electrical sensor devices in the group of electrical sensor devices 120a measure impedance. Accordingly, the particular electrical sensor device is configured to generate a measurement signal indicative of or otherwise representative of impedance. Because the wearable device 110 is attached to the torso of the subject 104 (e.g., the chest of the subject 104), the impedance measured by the particular electrical sensor is thoracic impedance (TI). Therefore, the measurement signal may be referred to as a thoracic impedance (TI) measurement signal. The TI measurement signal, in some cases, is generated in a four-point configuration (or four-electrode measurement). As illustrated in the examples shown in FIGS. 2B and 2C , the TI measurement signal generated over a measurement period represents the amount of air present in the lungs as the subject 104 breathes during the measurement period. That is, the time dependence of the TI measurement signal represents the amount of air present in the lungs as a function of time. Therefore, the thoracic impedance measurement performed by the wearable device 110 may be a surrogate for measuring the amount of air present in the lungs during a respiratory movement.

[0030] Because thoracic impedance measurements can be performed at the location of the subject 104, such measurements allow for monitoring of the pulmonary ventilation characteristics of the subject 104 without relying on a medical service facility for access to specialized equipment (such as spirometry equipment) to provide a measure of the amount of air moving in and out of the lungs of the subject 104. As a result, in stark contrast to conventional techniques and outpatient monitoring, monitoring according to aspects of the present disclosure provides rich pulmonary ventilation data with a temporal resolution superior to that of typical outpatient monitoring.

[0031] Other specific electrical sensor devices in the group of electrical sensor devices 120a can generate ECG data. To do so, the specific electrical sensor devices can measure voltages or voltage differences corresponding to specific electrodes or combinations of electrodes in each of the plurality of electrodes 114. The specific electrodes, individually or in combination, allow for measuring voltages corresponding to leads that define an ECG vector. For example, specific combinations of electrodes can constitute respective leads, each of which defines an ECG vector. These leads may correspond to, or in some cases may be similar to, at least a subset of the standard precordial leads (V1, V2, V3, V4, V5, V6) and the standard limb leads (I, II, III, aVF, aVL, and aVR). Thus, the number of specific electrodes allows for the configuration of at least three leads that are used either (i) to generate ECG data defining a 12-lead ECG or (ii) to reconstruct a 12-lead ECG based on a machine learning model or other technique.

[0032] Referring again to FIG. 1 , the plurality of sensor devices 118 ( FIG. 1 ) also includes a group of acoustic sensor devices 120b. Each acoustic sensor device in the group of acoustic sensor devices 120b is configured to generate a measurement signal. The measurement signal may be generated during a measurement period. The group of acoustic sensor devices 120b, individually or in a specific combination, can probe sounds generated in or propagating through organs present in the thoracic cavity of the subject 104. In one example, the organ is the lung, and one or more first acoustic sensor devices of the acoustic sensor devices 120b can function as respective lung auscultation probes. Thus, the first acoustic sensor devices may be attached to the subject's torso (e.g., the subject's chest) according to various configurations. In one configuration, the first acoustic sensor devices may be distributed on the same section of the subject's torso. Such a section may be, for example, an anterior section, a posterior section, or a lateral section. In another configuration, the first acoustic sensor devices may be distributed on different sections of the subject's torso. As an example of such a configuration, a first acoustic sensor device may be positioned in a front section of the torso of the subject 104, and a second acoustic sensor device may be positioned in a lateral section of the torso of the subject 104. In such a configuration, the first sensor and the second sensor may probe sound propagation within the lungs of the subject 104. Specifically, the time elapsed during sound propagation between the first and second acoustic sensors may be measured. Such time may be indicative of or otherwise representative of the amount of fluid in the lungs.

[0033] The plurality of sensor devices 118 further includes a group of inertial sensor devices 120c. The wearable device 110 is mounted on the torso of the subject 104 such that each inertial sensor device is mechanically coupled to the subject's 104's chest. Specifically, each inertial sensor may be in contact with a solid medium, which is in contact with the subject's 104's chest. In some cases, the group of inertial sensor devices 120c consists of a single inertial sensor device. As an example, the single inertial sensor device may include a three-axis accelerometer. In other cases, the group of inertial sensor devices 120c includes multiple inertial sensor devices, such as a three-axis accelerometer and a three-axis gyroscope.

[0034] Regardless of the type, number, and placement of the inertial sensor devices, each inertial sensor device in the group of inertial sensor devices 120c is configured to generate a measurement signal. The measurement signal may be generated during a measurement period. The measurement signal is generated as the subject 104 breathes and may be referred to as an inertial measurement signal (or acceleration measurement signal). The inertial measurement signal may be used to generate a movement signal that indicates or otherwise represents movement of the subject's 104's chest wall during the measurement period. Thus, over a time interval including two or more test periods, the inertial measurement signal may be used to monitor movement of the subject's 104's chest wall as the subject breathes over the time interval.

[0035] It should be noted that in some implementations, the plurality of sensor devices 118 may include other types of motion sensor devices instead of inertial sensor devices. The motion sensor devices may be or include transducer devices that convert kinetic energy corresponding to the movement of the subject's 104's chest wall into an output signal (e.g., an electrical signal, a magnetic signal, an electromagnetic signal, and / or a delayed signal) that indicates or otherwise represents the movement of the subject's 104's chest wall. Thus, the output signal may be referred to as a motion signal. As an example, such a motion sensor device may include a piezoelectric material that can convert the amount of chest wall displacement into an electrical signal (e.g., a voltage signal or a current signal), which indicates or otherwise represents the movement of the subject's 104's chest wall. As another example, the motion sensor device may be or include an optoelectronic assembly having a light source device and a photodetector device that can measure the amplitude, direction, and / or speed of the chest wall movement. The optoelectronic assembly may be configured to generate one or more electrical signals (e.g., current signals) and, in some cases, delayed signals that, individually or in combination, indicate or otherwise represent movement of the chest wall of the subject 104.

[0036] With further reference to FIG. 1 , if the first inertial sensor device of the group of inertial sensor devices 120c is a three-axis accelerometer, the three-axis accelerometer generates three inertial measurement signals corresponding to three orthogonal axes, such as x, y, and z axes of a Cartesian coordinate system. The z-axis may be oriented along the direction of gravity. The inertial measurements may collectively represent (i) the orientation of the three-axis accelerometer (or the wearable device 110) relative to the chest wall of the subject 104 and (ii) a linear acceleration vector. While not intending to be bound by the modeling, during regular breathing movements, the change in the second derivative of the chest wall displacement vector with respect to time is negligible, and therefore the magnitude of the acceleration vector is negligibly small relative to the acceleration of gravity. For example, the magnitude of the acceleration vector may be approximately three orders of magnitude smaller than the acceleration of gravity. Therefore, the inertial measurement signals may essentially be considered to represent the orientation of the three-axis accelerometer relative to the chest wall of the subject 104. In a scenario where the subject 104 lies supine during the measurement period, the orientation of the three-axis accelerometer relative to the chest wall of the subject 104 is defined by the tilt angle relative to the horizontal plane supporting the subject 104. Thus, the three-axis accelerometer is in effect a tilt sensor device.

[0037] With respect to a Cartesian coordinate system, the three inertial measurement signals are respectively the first component a (along the x-axis) of the gravitational acceleration vector x , the second component (along the y-axis) of the gravitational acceleration vector a y , and the third component a of the gravitational acceleration vector (along the z-axis) z The first and second components are the in-plane components a h =a x cos(φ)+a y Define sin(φ), where φ is the a in the (x, y) plane of the three-axis accelerometer (or wearable device 110). h is the polar angle coordinate of a h is the rotation angle of

[0038] As the subject breathes, the position of the three-axis accelerometer (or wearable device 110) changes along an axis 410 that is parallel to the direction of gravity. Such a change in position, Δh, relative to the position of the three-axis accelerometer (or wearable device 110) at the end of exhalation has an in-plane component a h Change in Δa h In FIG. 4, the (x,y) plane at the end of expiration is represented by dashed line segment 420, and the (x,y) plane at the peak of inspiration is represented by solid line segment 430. Changes in the orientation of the triaxial accelerometer due to chest wall movement during the respiratory cycle are primarily represented by changes in the components of the gravitational acceleration vector on the x, y, and z axes. In particular, without intending to be bound by theory and / or modeling, it is believed that the in-plane component a h The change in Δa h =Δa x cos(φ)+Δa y sin(φ), where Δa x and Δa y are the first component a as measured by the triaxial accelerometer, respectively. x The variation of the second component a y Therefore, the movement of the chest wall of the subject 104 determines φ and Δa x a first inertial signal indicative of Δa y and a second inertial signal indicative of

[0039] The value of φ is determined for each measurement period because the wearable device 110 may be removed after a previous measurement period and replaced with the current measurement period. hA satisfactory (e.g., best or next-best) value of φ can be iteratively determined by maximizing the correlation between φ and the pulmonary ventilation signal obtained from the thoracic impedance signal. In some cases, the correlation may be a shape-based correlation. Thus, to calculate such a correlation (denoted by ρ), for a first data series {u} and a second data series {v}, the cross-covariance of {u} and {v} (denoted by cov(u,v)) can be determined. The cross-covariance of {u} and {v} can then be normalized with respect to the standard deviation of {u} and {v}. That is, ρ=cov(u,v) / (σ u σ v ) and σ u and σ u represent the standard deviations of {u} and {v}, respectively. In the iterative determination of Φ, {u} is a x is the time series of values of a y is a time series of values of

[0040] In some configurations, the plurality of sensor devices 118 also includes an oximeter device 120d that can enable measurement of oxygen saturation levels. The oximeter device 120d is configured to generate a measurement signal during a measurement period. Additionally, or in other configurations, the plurality of sensor devices 118 also includes a sphygmomanometer (not shown in FIG. 1 ).

[0041] It should be noted that embodiments of the technology described herein are not limited to the described plurality of sensor devices 118. Additionally, the electrical sensor devices of the group of electrical sensor devices 120a may be used to measure the body temperature of the subject 104.

[0042] The wearable device 110 is depicted as a single block attached to the torso of the subject 104 for illustrative purposes only. While the wearable device 110 is monolithic in some implementations, there are other implementations in which the wearable device 110 is not monolithic. FIG. 3 presents an example of an arrangement of multiple electrodes 114 and a housing 310 that holds multiple sensor devices 118, a processor 122, a memory device 126, an input / output (I / O) interface 130, a network adapter 134, and, in some cases, other components. In FIG. 3, the multiple electrodes 114 include four electrodes 320(1), 320(2), 320(3), and 320(4) used for four-point thoracic impedance measurements. In addition, the wearable device 110 illustrated in FIG. 3 also includes a fifth electrode 320(5) that embodies the left arm (LA) for use in multiple leads for electrocardiogram measurements. A fifth electrode 320(5) can function as a reference electrode. The wearable device 110 illustrated in FIG. 3 also includes a piezoelectric transducer 340 that is part of an acoustic sensor (not shown in FIG. 3) and allows heart sounds to be measured. In some cases, the piezoelectric transducer 340 can be used in combination with another piezoelectric transducer (not shown) to probe sound propagation across the lungs of the subject 104. The electrodes 320(1), 320(2), 320(3), 320(4), and 320(5) and the piezoelectric transducer 340 connect to multiple sensor devices 118 (not shown in FIG. 3) via cables and a single connector / adapter in the housing 310.

[0043] Wearable device 110 also includes one or more processors 122, one or more memory devices 126, a plurality of I / O interfaces 130, and one or more network adapters 134. At least one of processors 122 and at least one of memory devices 126 may form a control unit. In some cases, the control unit may implement control operations related to the setup / positioning of wearable device 110 and / or the performance of one or more measurements by at least one of the plurality of sensor devices 118 that provide measurement signals. A first one of network adapters 134 may be embodied in a wireless unit that enables wireless exchange of information between wearable device 110 and another device.

[0044] Wearable device 110 may be operatively coupled to or otherwise configured to communicate with processing platform 150, which is also part of exemplary system 100. Such functional coupling can be implemented in many ways and can enable wearable device 110 to provide data and / or signaling (e.g., control instructions) to processing platform 150. In some cases, as illustrated in FIG. 1 , wearable device 110 is operatively coupled to or otherwise configured to communicate with user device 160 and processing platform 150 via one or more networks 140 (wireless networks, wired networks, or a combination of both). In other cases (as shown in FIG. 12 ), wearable device 110 is operatively coupled to or otherwise configured to communicate with processing platform 150 via network 140 without user device 160 providing an intermediary element to enable such coupling.

[0045] User device 160 is depicted as a smartphone for illustrative purposes only. The present disclosure is not limited in that respect. In fact, user device 160 may be any device having computing resources that are capable of individually or collectively executing processor-accessible instructions and causing a display device to display information. The processor-accessible instructions may be processor-executable program code. In some cases, the processor-executable program code may be embodied in a software library, an application programming interface (API), a processor-executable module, or the like. The display device may be integrated into or functionally coupled to user device 160. Furthermore, user device 160 may be mobile (handheld or otherwise) or semi-stationary. In addition to smartphones, examples of user device 160 include phablet devices, tablet computers, laptop computers, or similar devices.

[0046] The processing platform 150 includes multiple server devices 154. The processing platform 150 can receive measurement signals generated by the wearable device 110 over time via the network 140 and at least one first server device of the multiple server devices 154. The processing platform 150 can implement multiple processes using the received measurement signals via at least one second server device of the multiple server devices 154. Such processes can enable determining a cardiopulmonary condition status or status change of the subject 104. The at least one second server device can hold a group of modules 156 that, in response to being executed by a processor, cause the at least one second server device, individually or jointly, to perform at least one of the processes. More specifically, at least some of such processes can include determining a value of a particular metric or combination of metrics based on the measurement signals. In some cases, the particular metric is indicative of the cardiopulmonary condition status of the subject 104. Additionally, or in other cases, the combination of metrics is indicative of the cardiopulmonary condition status of the subject 104.

[0047] The processing platform 150 can evaluate various types of metrics, which individually or in combination can identify changes in cardiopulmonary status. In the present disclosure, the type of metric can be a direct type or a combined type. A direct type metric (referred to as a direct metric) is a quantity directly probed by a sensor device among the plurality of sensor devices 118. That is, a measurement signal generated by the sensor device indicates a respective value of the metric. The quantity can be a physical quantity, a chemical quantity, or a physicochemical quantity. Examples of physical quantities include thoracic impedance and the velocity of sound propagation. An example of a chemical quantity is oxygen saturation. As described above, the oximeter device 120d can directly probe the oxygen saturation level. Therefore, the measurement signal generated by the oximeter device 120d indicates the oxygen saturation level. The second server device can then obtain an observation value indicating the oxygen saturation level from the measurement signal generated by the oximeter device 120d. The second server device can then assign the observation value to a direct metric corresponding to the oxygen saturation.

[0048] A metric of a composite type (referred to as a composite metric) is a quantity derived by manipulating measurement signals generated by a sensor device among the plurality of sensor devices 118. The second server device can manipulate measurement signals received from the wearable device 110. The second server device manipulates the measurement signals according to one or more processes corresponding to which the composite metric is evaluated. Some composite metrics can be derived by manipulating one type of measurement signal, e.g., TI measurement signals. Other composite metrics can be derived by manipulating two or more types of measurement signals. Examples of composite metrics that can be derived by manipulating TI measurement signals include respiration rate (RR), tidal volume (TV), and the ratio between expiratory time and inspiratory time. Such ratios are referred to herein as ρ simply for the sake of name. EIAn example of a composite metric that can be derived by manipulating the TI and inertial measurement signals is the delay between the mechanical onset of inspiration and the onset of inspiratory airflow.

[0049] To determine the value of a comprehensive metric associated with pulmonary ventilation, a server device of the plurality of server devices 154 can generate a pulmonary ventilation signal (also referred to as a respiration signal) by processing the TI measurement signal, and can then use the pulmonary ventilation signal to evaluate the comprehensive metric. Processing the TI measurement signal includes filtering the TI measurement signal using a low-pass filter configured to remove frequencies above a cutoff frequency within a respiratory motion frequency band, where the respiratory motion frequency band is a range of frequencies that includes essentially all possible frequencies of pulmonary ventilation in an adult human. The frequency range can range, for example, from about 0.05 Hz to about 0.75 Hz. In one example, the cutoff frequency is 0.75 Hz. Filtering the TI measurement signal in such a manner can remove frequency components associated with bodily functions other than respiratory motion from the TI measurement signal. The processing also includes subtracting an average value of the filtered TI measurement signal from the TI measurement signal. Subtracting such an average value results in a mean-removed TI measurement signal. The processing further includes subtracting a running average of the mean-removed TI measurement signal from the mean-removed TI measurement signal. Subtracting such a moving average can remove baseline drift within the test period corresponding to the TI measurement signal, resulting in a pulmonary ventilation signal.

[0050] An example plot 500 of a pulmonary ventilation signal is shown in FIG. 5. The pulmonary ventilation signal spans 15 seconds, which may be just one example of a measurement period. The pulmonary ventilation signal is cyclical and therefore includes various maxima (or peaks) and minima (or troughs). The pulmonary ventilation signal allows various respiratory parameters to be determined. Specifically, respiratory cycle duration is the time difference between successive peaks.

number

number

number

number

number

number

number

[0051] Evaluating the comprehensive metric using the pulmonary ventilation signal includes identifying maxima (or peaks) and minima (or troughs) of the pulmonary ventilation signal. To that end, a peak and trough detection process can be applied to the pulmonary ventilation signal. Such a detection process can include determining multiple extrema of the pulmonary ventilation signal by applying a time-domain zero-crossing process to a first derivative with respect to time of the pulmonary ventilation signal. The detection process can also include determining multiple peaks within the extrema of the pulmonary ventilation signal, at least in part, by determining a second derivative with respect to time of the pulmonary ventilation signal. The multiple peaks have respective first zero-crossing times, at which times the second derivative with respect to time of the pulmonary ventilation signal is negative. The detection process can further include determining multiple troughs within the extrema of the pulmonary ventilation signal, at least in part, by determining the second derivative with respect to time of the pulmonary ventilation signal. The multiple troughs have respective second zero-crossing times, at which times the second derivative with respect to time of the pulmonary ventilation signal is positive.

[0052] Evaluating the composite metric also includes using the maximum and / or minimum values of the pulmonary ventilation signal to generate a series of values of the composite metric {μ n The definition of the overall metric determines whether the set of values is determined using only the maximum values, only the minimum values, or a combination of the maximum and minimum values. In addition, evaluating the overall metric also involves determining the set of values {μ n} Representative value

number

number

number

[0053] As mentioned above, some composite metrics can be evaluated using two or more types of measurement signals. For example, the delay between the mechanical onset of inspiration and the onset of inspiratory airflow is a composite metric evaluated by manipulating TI and inertial measurement signals. Such delay represents the relationship between mechanical respiration and airflow and, depending on its magnitude, can indicate the presence or absence of certain cardiopulmonary conditions.

[0054] To determine the delay between the mechanical onset of inspiration and the onset of inspiration airflow, a server device of the plurality of server devices 154 can generate a motion signal representing the motion of the chest wall of the subject 104 based on the inertial measurement signals and the TI measurement signals during the measurement period. The motion of the chest wall can be represented by a linear combination of (i) a first inertial measurement signal representing a first component of gravity along a first direction and (ii) a second inertial measurement signal representing a second component of gravity along a second direction. The first direction and the second direction are contained within the plane of the wearable device 110. The first inertial measurement signal and the second inertial measurement signal can be generated by a first channel and a second channel of a three-axis accelerometer, respectively. Specifically, the first inertial measurement signal and the second inertial measurement signal can be represented by Δa x and Δa y Therefore, the movement of the chest wall can be expressed as Δa x cos(φ)+Δa y It can be expressed as sin(φ).

[0055] Therefore, to generate such a motion signal, the server device receives a first inertial measurement signal (Δa x ) and the second inertial measurement signal (Δa yIn FIG. 6A , plots 610a and 610b present examples of a first inertial measurement signal and a second inertial measurement signal, respectively. Processing such an inertial measurement signal includes filtering the first inertial measurement signal using a low-pass filter configured to remove frequencies above a cutoff frequency within a respiratory motion frequency band. As noted above, the respiratory motion frequency band can span a frequency range from about 0.05 Hz to about 0.75 Hz. In one example, the cutoff frequency is 0.75 Hz. Processing also includes filtering the second inertial measurement signal using a low-pass filter. In FIG. 6A , plots 620a and 620b present examples of a filtered first inertial measurement signal and a filtered second inertial measurement signal, respectively. Processing also includes subtracting an average value of the filtered first inertial measurement signal from the filtered first inertial measurement signal. Subtracting such an average value results in a first inertial measurement signal with the average value removed. The filtered second inertial measurement signal is also mean-removed. That is, the processing further includes subtracting the mean value of the filtered second inertial measurement signal from the filtered second inertial measurement signal. Subtracting such mean value results in a mean-removed second inertial measurement signal. In FIG. 6A, plots 630a and 630b provide examples of a mean-removed first inertial measurement signal and a mean-removed second inertial measurement signal, respectively.

[0056] The processing also involves the TI measurement signal. Specifically, the processing includes converting each of the first mean-removed inertial measurement signal and the second mean-removed inertial measurement signal to the time base of the TI measurement signal. Such conversion allows the inertial measurement signals and the TI measurement signal (or a signal derived from the TI measurement signal) to be directly compared on the same time base. To perform such conversion, a time grid can be generated from the time base of the TI measurement signal using the start and end times of the TI measurement signal and also using the sampling duration of the TI measurement signal. The sampling duration is obtained from the sampling rate of the measured TI. In addition, each of the first and second mean-removed inertial measurement signals is then interpolated in time on the time grid, thus providing a mean-removed inertial measurement signal on the same time grid as the TI signal.

[0057] Processing involving the TI measurement signal also includes using the TI measurement signal to generate a pulmonary ventilation signal (see, e.g., FIG. 5), as described above. The processing then involves determining φ by iteratively varying φ and varying Δa until correlation is maximized or otherwise achieves a satisfactory value. x cos(φ)+Δa y and determining a correlation between sin(φ) and the pulmonary ventilation signal. The motion signal representing the chest wall of the subject 104 is then constructed as a linear combination of the first and second mean-removed inertial measurement signals resulting from setting φ to the value φ that produces maximum, or otherwise satisfactory, correlation.

[0058] 6B presents a plot 650 of an example pulmonary ventilation signal and a plot 680 of an example movement signal determined according to aspects described herein. Both the pulmonary ventilation signal and the movement signal correspond to the same measurement period and are determined using multimodal measurements performed by the wearable device 110 (FIG. 1) during the measurement period. The illustrated correlation between the pulmonary ventilation signal and the movement signal is equal to 0.83.

[0059] Furthermore, to determine the delay between the mechanical onset of inspiration and the onset of inspiratory airflow, a server device among the plurality of server devices 154 processes the movement signal to determine times corresponding to the mechanical onset of each movement in the respiratory cycle included in the measurement period. These times may be referred to as marker points. The server device may determine the marker points by determining minimum (trough) and maximum (peak) values of the movement signal. For a particular minimum value, the server device may determine successive maximum values and may also determine a first value of the movement signal at the particular minimum value. The server device may then identify a time when a second value of the movement signal exceeds the first value by a defined amount. The defined amount is a defined fraction of the third value of the movement signal at the successive maximum values. The server device may configure the identified time as a marker point. The server device may then identify another minimum value and determine another marker point in the same manner.

[0060] As part of determining the delay between the mechanical onset of inspiration and the onset of inspiratory airflow, the server device can also generate an airflow signal based on the pulmonary ventilation signal determined from the TI measurement signal during the measurement period. To do so, the server device can determine the first derivative with respect to time of the pulmonary ventilation signal, which results in the airflow signal over the measurement period. The server device can then determine the times at which the airflow signal is maximum (or at its peak) and configure those times as marker points for peak positive airflow. Such marker points correspond to the onset of inspiratory airflow. Simply by way of example, FIG. 7 presents a plot 710 of a mean-removed thoracic impedance signal corresponding to a subject (e.g., subject 104) and a plot 720 of an airflow signal obtained from the mean-removed thoracic impedance signal according to embodiments described herein. FIG. 7 also presents a plot 730 of a chest wall motion signal corresponding to the subject.

[0061] It should be noted that the start of inspiratory flow can be obtained in other ways. For example, the server device can use the respiratory signal to determine the start of inspiratory airflow by applying zero-crossing processing to the respiratory signal to determine a time point corresponding to airflow exceeding a threshold amount. Additionally, the service device can configure this time point as the start of inspiratory airflow.

[0062] Further, the server device can identify a respiratory motion cycle within the measurement period and a first marker point and a second marker point associated with the respiratory motion cycle. The first marker point corresponds to the mechanical start of inspiration, and the second marker point corresponds to the start of inspiration airflow. The server device can then determine the delay between the mechanical start of inspiration and the start of inspiration airflow as the difference between the second marker point and the first marker point. The server device can identify other respiratory motion cycles within the measurement period and determine other such delays in the same manner. Referring again to FIG. 7 , the server device can identify a first marker point 740 and a second marker point 750 corresponding to the mechanical start of inspiration and the start of inspiration airflow, respectively. The delay between the mechanical start of inspiration and the start of inspiration airflow is the difference between the second marker point 750 and the first marker point 740, and is represented in FIG. 7 by Δτ.

[0063] The processing platform 150 (FIG. 1) can use the inertial measurement signals and the TI measurement signals to evaluate a composite metric representative of respiratory effort. Such a composite metric is associated with the subject's breathing. Without intending to be bound by theory and / or modeling, respiratory effort may be defined as the amount of movement of the subject's chest wall between the inspiration and expiration phases of the respiratory cycle. Furthermore, because the degree of chest wall movement can have a direct relationship to the volume of air entering and leaving the lungs, a more appropriate way to represent and measure respiratory effort is by normalizing chest wall movement with respect to the volume of air entering and leaving the lungs (also referred to as the volume of processed air). Here, a direct relationship between quantities refers to a relationship in which a first change in one of the quantities directly causes a second change in another of the quantities that is not necessarily linearly related to the first change.

[0064] As described herein, the variation in the pulmonary ventilation signal obtained from thoracic impedance measurements represents the volume of processed air. Thus, in some cases, an example of a comprehensive metric representing respiratory effort may be the amount of energy present in the motion signal relative to another amount of energy present in the pulmonary ventilation signal (also referred to as the respiration signal). In some implementations, the energy content of a signal (e.g., the motion signal or the respiration signal) may be determined on a sample-by-sample basis. Thus, the processing platform 150 may calculate an energy content E[n] for sample n of the motion signal and another energy content E for sample n of the respiration signal. ’ The processing platform 150 can then determine E ’ The ratio of E[n] to E[n] can be evaluated to determine the value of the overall metric. In other implementations, the energy content of a signal can be determined as a sum (e.g., an average or another function) of the energies of sample n and one or more immediately preceding samples. Thus, the processing platform 150 can determine the energy content E[n] for sample n of the movement signal as a sum of the energies of sample n and one or more immediately preceding samples. The processing platform 150 can also determine another energy content E[n] for a sample of the respiration signal.’ [n] can be determined as the sum of sample n and one or more immediately preceding samples.

[0065] Additionally, or alternatively, the subject's chest wall motion may be normalized for changes in thoracic impedance. Thus, the expression for respiratory effort is:

number

number

number

number

number

[0066] 8A presents a plot 800 of the mean-removed thoracic impedance signal and a plot 830 of the chest wall motion signal for a subject with stable COPD. The respiratory effort R (Equation (1)) calculated using such signals is equal to 0.0043. FIG. 8B presents a plot 860 of the mean-removed thoracic impedance signal and a plot 890 of the chest wall motion signal during a COPD exacerbation in the same subject. The respiratory effort R (Equation (1)) calculated using such signals is equal to 0.0194.

[0067] The processing platform 150 (FIG. 1) can implement a process for determining a change in the cardiopulmonary status of the subject 104. The change in status can be determined by tracking temporal changes in one or more metrics, such as direct metrics, integrated metrics, or a combination thereof. The process can include determining multiple values of a particular metric or combination of metrics over a time interval. The time interval includes an analysis period spanning two or more test periods. Each test period spans multiple measurement periods and includes at least one measurement period during which the wearable device 110 performs respective measurements and generates measurement signals. An analysis period can have a duration of at least one hour to one day or one week, which is greater than the duration of another measurement period. Additionally, or in some circumstances, an analysis period can range from several weeks to one or several months, which is greater than the duration of another measurement period.

[0068] Additionally, and as part of determining a status change, the processing platform 150, via one or more computational nodes, can monitor the time dependency of a particular metric or combination of metrics over a time interval using multiple values. In some cases, monitoring such time dependency can include updating parameters that define a function (linear or otherwise) that fits to currently determined values of each metric of a particular metric or combination of metrics. Additionally, or in other cases, monitoring such time dependency can include updating parameters that define a rolling average of currently determined values of a particular metric or combination of metrics. Regardless of how the time dependency is monitored, the time dependency of a particular metric or combination of metrics or any of the metrics can convey a trend. The trend can be an upward trend, a downward trend, or an essentially constant trend. An upward trend can signal a worsening cardiopulmonary condition, whereas a downward trend can signal an improvement in the cardiopulmonary condition. An essentially constant trend indicates that the cardiopulmonary condition remains unchanged. Thus, by monitoring single metrics and / or combinations of metrics, the techniques described herein can provide for the detection and / or differentiation of cardiopulmonary exacerbations.

[0069] By way of example, FIG. 9A presents a schematic plot 900 of a metric as a function of time over successive test periods according to embodiments described herein. The metric may be any of the metrics according to the present disclosure and is represented in FIG. 9A as "Metric A" for illustrative purposes only. The ordinate is the metric (e.g., ρ EI), where the abscissa represents time. The consecutive test periods include a first test period 910(K), a second test period 910(K+1), a third test period 910(K+2), and a fourth test period 910(K+3). The first test period 910(K) and the second test period 910(K+1) each include a single measurement period. The third period 910(K+2) includes three measurement periods. The fourth test period 910(K+3) includes one measurement period. Each measurement period produces one or more measurement signals. The processing platform 150, via one or more server devices, can determine the value of a metric using the one or more measurement signals. Thus, the processing platform 150 determines a metric value 930(J) corresponding to measurement period 920(J) and a metric value 930(J+1) corresponding to measurement period 920(J+1). Test period 910(K+2) includes measurement period 920(J+2), measurement period 920(J+3), and measurement period 920(J+4). Thus, for such test period 910(K+2), processing platform 150 determines metric value 930(J+2), metric value 930(J+3), and metric value 930(J+4). Test period 910(K+3) includes measurement period 920(J+5), and processing platform 150 determines metric value 930(J+5). In summary plot 900, for each metric value 930(J) through 930(J+5), processing platform 150, via one or more server devices, can determine a respective deviation value relative to a baseline value for metric A. The baseline value can change over time. 9A, each metric 930(J) through 930(J+5) has a respective deviation value relative to a baseline value 932. For illustrative purposes only, the deviation value for metric value 930(J+4) is indicated by arrow 934.

[0070] Continuing with the example, processing platform 150 (FIG. 1), via one or more server devices, can determine the time dependency of a metric over an analysis period 940 (e.g., FIG. 9A), which spans three test periods. To do so, in some cases, processing platform 150 updates parameters defining a linear function fitting metric values 930(J+1) through 930(J+5) within analysis period 940. As shown in FIG. 9A, in one example, the updated parameters define linear function 950 with a positive slope. A positive slope indicates an upward trend. Depending on the particular metric represented by metric A, such an upward trend may signal a worsening of the cardiopulmonary condition. The magnitude of the positive slope may indicate the severity of the worsening. Additionally, or in other cases, processing platform 150 determines the time dependency of the metric by updating parameters indicating a rolling average of metric values 920(J+1) through 920(J+5) over analysis period 940. Regardless of how the time dependency of a metric over the analysis period 940 is determined, the processing platform 150, via one or more server devices, may determine that the metric exhibits an upward trend.

[0071] In some cases, the combination of metrics and their respective time dependencies can determine status changes in a cardiopulmonary condition (e.g., COPD) and distinguish the status change from another status change in another cardiopulmonary condition (e.g., CHF). As an example, both acute exacerbations of COPD and exacerbations of CHF can exhibit a decrease in oxygen saturation level (SpO2). In AECOPD, the decrease in SpO2 is more pronounced due to poor ventilation. Furthermore, AECOPD can cause a slight decrease in thoracic impedance (e.g., due to excessive mucus accumulation) or can exhibit essentially unchanged thoracic impedance. However, in some cases, AECOPD can exhibit a significant increase in thoracic impedance. In contrast, in CHF, moderate levels of fluid accumulation affecting a small portion of the alveoli do not significantly affect SpO2 because the body can increase respiratory rate and thus hyperventilate other portions of the unaffected alveoli, thereby maintaining oxygen saturation levels during the exacerbation. Second, thoracic impedance may exhibit a decrease in magnitude even at moderate levels of exacerbation / decompensation. At significantly higher levels of exacerbation / decompensation where oxygen saturation levels cannot be maintained, thoracic impedance may decrease dramatically. As another example, in heart failure decompensation or respiratory exacerbation, respiratory rate may increase over time, and tidal volume may decrease as time increases.

[0072] 9B is a schematic diagram 960 in which a combination of Metric A and Metric B can be monitored as a function of time to determine changes in cardiopulmonary condition status. As described herein, processing platform 150, via one or more server devices, determines that Metric A increases with time over analysis period 940. Processing platform 150 also determines that Metric B decreases as time increases over analysis period 940. To that end, processing platform 150 determines a metric value 970(J) corresponding to measurement period 920(J), a metric value 970(J+1) corresponding to measurement period 920(J+1), a metric value 970(J+2), a metric value 970(J+3), and a metric value 970(J+4) for measurement periods 920(J+2) through 920(J+4), respectively, and a metric value 970(J+5) corresponding to measurement period 920(J+5). Processing platform 150, via one or more server devices, can then determine the time dependence of metric B over analysis period 940. To do so, in some cases, processing platform 150 updates parameters defining a linear function that fits metric values 970(J+1) through 970(J+5) within analysis period 940. As illustrated in FIG. 9B , the updated parameters define linear function 980 with a negative slope. A negative slope indicates a downward trend. Depending on metric B, such a downward trend may individually signal a worsening cardiopulmonary condition. Further, depending on the specific metrics A and B, the combination of an upward trend in metric A and a downward trend in metric B over analysis period 940 may indicate a change in cardiopulmonary condition status. In one example, metric A is respiration rate and metric B is tidal volume, and the combination of the trends represented by linear function 950 and linear function 980 indicates worsening CHF or COPD.

[0073] Subjects with both CHF and AECOPD present with symptoms that can be puzzling to treating clinicians. It is often difficult to determine whether an exacerbation in these subjects is due to CHF decompensation or an increase in the severity of AECOPD. Symptoms such as shortness of breath and cough are common to both conditions. Nevertheless, according to embodiments of the present disclosure, the origin of such an exacerbation can be revealed by, for example, jointly monitoring the SpO2 and thoracic impedance trends of such subjects. Subjects with CHF tend to maintain SpO2 levels through pulmonary hyperventilation during mild to moderate exacerbations due to fluid overload. However, at higher levels of fluid overload, SpO2 decreases, and affected subjects exhibit a significant decrease in thoracic impedance. On the other hand, because AECOPD is an obstructive disorder of the lungs and airways, AECOPD causes a more significant decrease in SpO2, even during mild to moderate exacerbations. Thoracic impedance may then remain relatively stable, may decrease slightly due to excessive mucus accumulation, or may show a significant increase due to air trapping such as is present in emphysema.

[0074] FIG. 10 is a two-dimensional plot 1000 comparing the deviation of SpO2 from baseline versus the deviation of thoracic impedance (TI) from baseline for patients with AECOPD and CHF exacerbations. The deviation is quantified as a percentage of the baseline value. From the two-dimensional plot 1000, it is easy to visualize that the data occupies two distinct regions of the plot that can be well separated. In fact, a classification line 1010 can be defined. Thus, the combination of the respective values of SpO2 and thoracic impedance can classify or otherwise distinguish the type of exacerbation (either AECOPD or CHF).

[0075] Similar two-dimensional plots showing deviations in SpO2 from baseline versus deviations in RR or minute ventilation (the product of RR and TV) can also provide a differential picture that allows for differentiation between exacerbations of AECOPD and CHF. As noted above, CHF patients with moderate decompensation may be able to maintain SpO2 levels with increased ventilation. However, as with chronic bronchitis, patients with AECOPD, particularly those with airway obstruction (or narrowing), may be unable to maintain SpO2.

[0076] A three-dimensional plot with SpO2 deviation from baseline on a first axis, RR or differential minute ventilation deviation from baseline on a second axis, and thoracic impedance deviation from baseline on a third axis can also constitute a differentiation map that allows localization of specific differentiation locations in three-dimensional space to clearly differentiate between AECOPD or CHF decompensation. Such a differentiation map can include two-dimensional classification boundaries that distinguish one type of exacerbation from the other. Similarly, ρ EI Other combinations of metrics such as respiratory morphology metrics with SpO2, thoracic impedance, and / or respiratory rate can provide meaningful insight into the nature of the exacerbation.

[0077] Referring again to FIG. 1 , as described herein, processing platform 150 (e.g., via one or more of server devices 154) or a computing device can use values of metrics associated with a subject's respiration and / or respective values of combinations of such metrics to identify a change in the status of the cardiopulmonary condition of subject 104. Such metrics can be direct metrics or composite metrics according to aspects described herein. In some cases, processing platform 150 can identify a change in the status of the cardiopulmonary condition based on a change in the value of the metric relative to a past value. More specifically, processing platform 150 can obtain multiple values of the metric over each measurement period within an analysis period. Processing platform 150 can monitor the time dependency of the metric over the analysis period using the multiple values and another value of the metric, the another value being determined at another measurement period. Processing platform 150 can then identify a change in the status of the cardiopulmonary condition based on the time dependency.

[0078] Additionally, or in other cases, processing platform 150 or a computing device can identify a change in cardiopulmonary condition status based on individual changes in each value of a metric in a metric combination relative to its respective past value. More specifically, processing platform 150 can obtain multiple respective values of a metric combination over each measurement period within an analysis period. Processing platform 150 can then monitor the time dependency of each of the metrics in the metric combination over the analysis period using the multiple respective values of the metric combination and each other respective value of the metric combination. These other respective values may have been determined over different measurement periods. Processing platform 150 can then identify a change in cardiopulmonary condition status based on the respective time dependencies.

[0079] Exemplary system 100 and other systems according to the technology described herein also include computing device 170, which can be located remotely with respect to both processing platform 150 and residence 106. The locale 172 of computing device 170 can be, for example, a healthcare facility (e.g., a hospital) or the residence of the operator of computing device 170. Computing device 170 can be mobile, and thus locale 172 can change over time as computing device 170 moves from one location to another.

[0080] Computing device 170 is depicted as a laptop computer for illustrative purposes only. The present disclosure is not limited in that respect. In fact, computing device 170 may be any device having computing resources that are capable of individually or collectively executing processor-accessible instructions and causing a display device to display information. The processor-accessible instructions may be processor-executable program code. In some cases, the processor-executable program code may be embodied in a software library, an application programming interface (API), a processor-executable module, or the like. The display device may be integrated into or functionally coupled to computing device 170. Furthermore, computing device 170 may be mobile (handheld or otherwise) or semi-stationary. Besides laptop computers, examples of computing device 170 include smartphones, phablet devices, tablet computers, or similar devices.

[0081] Computing device 170 is operatively coupled or otherwise configured to communicate with processing platform 150 via at least one of networks 140. Computing device 170 may be associated with or otherwise operated by a clinician. Thus, in some cases, computing device 170 may be referred to as a clinician device. In other cases, computing device 170 may be associated with or operated by a caregiver or subject 104. Thus, in some cases, computing device 170 may be referred to as a caregiver device. In still other cases, computing device 170 may be a computing device within a hospital's computing system. Additionally, or in some scenarios, another computing device (not shown in FIG. 1 ) may also be operatively coupled or otherwise configured to communicate with processing platform 150. That other computing device may be associated with or otherwise operated by an agent of a health insurance provider. The agent may be a human or an autonomous bot executed by such a computing device. A clinician may be involved in providing medical care regarding the cardiopulmonary condition of subject 104. An agent may be involved in making decisions related to financial compensation for such care. Accordingly, computing device 170 and other computing devices (not shown in FIG. 1 ) may receive information related to the status of the cardiopulmonary condition of subject 104 and / or changes in the status of the cardiopulmonary condition of subject 104. Because changes in cardiopulmonary status may require medical intervention, such as transport to a hospital and / or hospitalization, the contemporaneous availability of information related to either or both of the change in cardiopulmonary status or the change itself can avoid potentially fatal delays in medical care. Thus, systems, devices, and techniques according to embodiments of the technology described herein, individually or in combination, provide distinct improvements over common techniques for managing cardiopulmonary conditions.

[0082] At least a portion of the information provided by processing platform 150 to computing device 170 may be formatted as an electronic message that may be presented by a software application or another type of program code configured to execute on computing device 170. Computing device 170 may receive and present the information via the software application. The information may be presented on at least one of multiple user interfaces 174 that computing device 170 may present in response to the software application being executed. In some cases, the information may be presented on a display device integrated with computing device 170 or a user interface operatively coupled to computing device 170. In other cases, the information may be presented as an overlay (e.g., a push-up message) on a home interface presented on a display device in response to the software application being executed. In one example, processing platform 150 may cause computing device 170 to present one or more markings indicating a change in cardiopulmonary status, e.g., a transition from subject 104's historical baseline to an exacerbated cardiopulmonary status. The markings may be presented in a user interface or overlay and may be formatted to convey the nature of the status change and, in some cases, identify the subject 104. For example, for a transition from a historical baseline to a critical condition, the markings may be formatted to prominently convey such a transition.

[0083] 2A presents exemplary user interface 202 that may be part of multiple user interfaces 174 presented by computing device 170. Because computing device 170 may have access to information corresponding to multiple wearable devices and subjects other than wearable device 110 and subject 104, exemplary user interface 202 includes a first selectable visual element 204 that, in response to being selected, causes computing device 170 to (i) obtain data identifying wearable devices available to monitor the respective subject, and (ii) present a list of wearable devices (including wearable device 110). Each item in the list may also be selectable, in response to being selected, causing exemplary user interface 202 to include a visual element 206 that identifies the selected wearable device (e.g., wearable device 110). Exemplary user interface 202 also includes a second selectable visual element 208 that, in response to being selected, causes computing device 170 to establish a connection (e.g., a communication session) with the selected wearable device.

[0084] The exemplary user interface 202 also includes a visual element 210 that identifies the subject 104 corresponding to the wearable device 110. For example, the visual element 210 may include text and / or other markings that identify the subject. The exemplary user interface 202 also includes a second visual element 220 that indicates an SpO2 value, a plot 230 of ECG data over a measurement period 235, and a plot 240 of thoracic impedance over a measurement period (e.g., 30 seconds, 60 seconds, 120 seconds). In some cases, the exemplary user interface 202 also includes a first selectable visual element 250 and a third selectable visual element 260. Selection of the first selectable visual element 250 causes the computing device 170 to instruct the wearable device 110 to generate a measurement signal. Selection of the fourth selectable visual element 260 causes the computing device 170 to instruct the wearable device 110 to stop generating a measurement signal. This disclosure, of course, is not limited to the visual elements and layout of the visual elements shown in the exemplary user interface 202. Other types of visual elements may be presented in the UI of the user interfaces 174 and / or other layouts of visual elements may be implemented.

[0085] 1 , computing device 170 may also be operatively coupled or otherwise configured to communicate with user device 160 via at least one of networks 140. In some configurations, user device 160 may be part of exemplary system 100 or other systems according to aspects of the technology described herein. User device 160 may be owned, rented, and / or operated by subject 104. User device 160 may also be operated by an assistant assisting the subject in performing measurements. The assistant may be, for example, a family member or another type of caregiver, such as a nurse, nurse's assistant, nursing home staff, or similar support personnel. User device 160 may be configured with a software application or another type of program code for exchanging information with computing device 170 and wearable device 110. Thus, computing device 170 may provide, via a software application configured on computing device 170, an indication of a particular value of a metric being monitored and / or an indication of an action to be taken by subject 104 in response to a change in the cardiopulmonary status of subject 104. The indication may be, for example, a command or another type of instruction according to a particular control protocol. User device 160 may receive such an indication via a software application configured on user device 160 and, in response, may present a message instructing subject 104 to perform an action. The message may be presented on at least one of multiple user interfaces 164 that computing device 160 may present in response to the software application being executed. The message may be, for example, a push-up message or a recorded voice message. The push-up message may be part of or form one of multiple user interfaces 164. In some cases, the push-up message may be presented on a home screen or a lock screen of user device 160.The recorded voice message may be selected from a menu of voice messages stored within the user device 160 or may be generated by the user device 160 via a software application. The voice message may be stored in a memory device integrated with the user device 160. Thus, based on a particular value of a metric or a particular value of each metric in a combination of metrics, the computing device 170 may prompt the subject 104, a clinician, and / or a caregiver to cause the wearable device 110 to generate additional measurement signals.

[0086] Additionally, or in some cases, the computing device 170 can trigger the sending of an electronic communication to a clinician device and / or a second electronic communication to a caregiver device to provide an indication of an action taken by the subject 104. The electronic communication and the second electronic communication both include the indication. Each of the electronic communications can be one of an email, a text message, a telephone call, or a video conference call. As described herein, the indication can be provided in response to a particular value of a metric being monitored, a particular value of a combination of metrics, a particular respective value of a metric in a combination of metrics, and / or a change in the cardiopulmonary status of the subject 104.

[0087] By way of example only, a variation of exemplary user interface 202 ( FIG. 2A ) may be part of a plurality of user interfaces 164 presented by user device 160. For example, in cases where user device 160 is only operatively coupled to communicate with wearable device 110 or is otherwise configured, a variation of exemplary user interface 202 may exclude first selectable visual element 204, visual element 206, and second selectable visual element 208. This disclosure is, of course, not limited to the visual elements and layout of visual elements shown in exemplary user interface 202 or a variation of user interface 202. Indeed, user device 160 may present other types of visual elements in the UI of plurality of user interfaces 164 and / or implement other layouts of visual elements.

[0088] In some cases, the type of action directed by computing device 170 is associated with the nature of the status change. As one example, for a transition from a historical baseline of a metric or combination of metrics to a distress state, the action may include going to the emergency room, contacting a physician, and / or contacting an assistant. As another example, based on the value of the metric or combination of metrics, the action may include causing wearable device 110 to generate an additional measurement signal. In some implementations, computing device 170 may cause wearable device 110 to generate the additional measurement signal as part of an additional measurement period without intervention from subject 104. In these implementations, user device 160 may relay the command to generate the additional measurement signal, or in some cases, user device 160 may generate such a command and then transmit the command to wearable device 110. 9A, measurement periods 920(J+3) and 920(J+4) may be triggered by computing device 170 in response to metric A value 930(J+2) being greater than metric A value 930(J+1). Of course, other actions are contemplated.

[0089] 1 , as described herein, user device 160 may be operatively coupled or otherwise configured to communicate with wearable device 110. User device 160 may also be operatively coupled or otherwise configured to communicate with processing platform 150 via at least one of networks 140. Thus, in some configurations, user device 160 may provide at least some of the functionality of computing device 170 described herein in accordance with aspects of the present disclosure.

[0090] A software application, or another type of program code, that may be configured on user device 160 can control the manner in which measurements are performed using wearable device 110. To that end, as described herein, in response to the software application being executed, user device 160 can present a user interface that allows configuration of a measurement session, e.g., the number of measurements to be performed (or signal samples to be acquired) during a measurement period. A measurement session may be referred to as a measurement cycle. The user interface may be one of multiple user interfaces 164.

[0091] The configuration of the measurement session may be guided by the user device 160 via a software application. For example, the user device 160 may prompt the subject 104 or an assistant via the software application to perform actions to configure attributes of the measurement session. One example of an attribute of the measurement session is the placement of the wearable device 110. Thus, the user device 160 may prompt the subject 104 or assist the subject 104 in adjusting the placement of the wearable device 110 via the software application by continuously or intermittently vibrating the wearable device 110 until proper placement is achieved. Specifically, as the placement of the wearable device 110 is adjusted, the user device 160 may determine whether the placement of the wearable device 110 on the torso of the subject 104 satisfies a placement rule. To determine the placement, for example, the user device 160 may receive measurement signals from an inertial sensor that is part of the wearable device 110. For some placements, user device 160 may determine that the placement of wearable device 110 on the torso of subject 104 falls short of satisfying the placement rules. In response to such a determination, user device 160 may instruct a haptic device integrated into wearable device 110 to cause vibrations of wearable device 110. In some cases, the haptic device is included in I / O interface 130. In other cases, the haptic device may be a standalone component coupled with processor 122, memory device 126, I / O interface 130, and / or network adapter 134. User device 160 may continue to receive measurement signals from the inertial sensors and thus may continue to monitor the placement of wearable device 110. As part of such monitoring, at a point after an initial improper placement of wearable device 110, user device 160 may determine that an adjusted placement of wearable device 110 on the torso of subject 104 satisfies the placement rules.In response, user device 160 can instruct the haptic device to stop vibrating wearable device 110. Additionally, or alternatively, user device 160 can present a notification (e.g., visual and / or auditory) indicating that wearable device 110 is properly placed on the torso of subject 104. Additionally, or in some configurations, wearable device 110 itself can assess proper placement of wearable device 110 in accordance with aspects described herein. To that end, wearable device 110 can implement the operations described herein that user device 160 can implement for placement of wearable device 110.

[0092] Additionally, or in some cases, a software application or other program code configured on the user device 160 can control end-user activities that prepare the subject 104 for a measurement using the wearable device 110. To that end, in some cases, in response to the software application being executed, the user device 160 can present a user interface that includes an indication of an action to be performed by the subject prior to the measurement (or a measurement period associated with the measurement). The user interface can be one of the user interfaces 164. The indication can include, for example, one or more visual elements identifying the action to be performed and, in some cases, can provide a tutorial on how to perform the action. The visual elements can include text or other markings, still images, video segments, or a combination thereof. The action can include, for example, performing one or more exercises to stimulate or otherwise stress the cardiopulmonary system of the subject 104. The exercises performed can be customized to the subject's 104's level of fitness and / or mobility. Information regarding the subject's 104's level of fitness and / or mobility can be maintained in a memory device integrated with the user device 160. The user profile may hold information regarding the subject's 104 level of fitness and / or mobility. Other data structures other than a user profile may be used. Additionally, or in some cases, information may be held regarding the subject's 104 level of fitness and / or mobility and may be held in a storage node (e.g., one of the server devices 154) of the processing platform 150. Examples of exercises performed include walking in place for a defined period of time, jogging in place for a defined period of time, climbing a number of stairs, performing compound exercises (such as lunges, squats, or stand-up movements), swinging the torso and arms, etc.

[0093] Additionally, or in some cases, the user device 160 may also present (e.g., via a software application) one or more other user interfaces that display observed data from the measurements. The observed data may include, for example, thoracic impedance values at one or more times, SpO2 values, etc. As described herein, FIG. 2A illustrates one example of a user interface that presents observed data for a subject.

[0094] 1 , user device 160 (e.g., via a software application) can determine that a reporting rule has been satisfied and, in response, can trigger the presentation of a patient-reported outcome (PRO) questionnaire associated with the cardiopulmonary condition of subject 104. The PRO questionnaire can be presented as a single user interface or a series of user interfaces. The single user interface and the series of user interfaces can be part of multiple user interfaces 164. To trigger the presentation of the PRO questionnaire, user device 160 can cause a display device to present the PRO questionnaire. The display device can be incorporated into user device 160 or operatively coupled to user device 160. Computing device 170 can also provide such functionality.

[0095] To determine whether a reporting rule is satisfied, the user device 160 can evaluate data associated with monitoring the cardiopulmonary status of the subject 104 according to the reporting rule. In one example, the reporting rule dictates that a PRO questionnaire be presented upon or after a defined number of measurement sessions have been completed. Thus, data that may be evaluated includes data defining the number of measurement sessions currently completed. In addition, or in another example, the reporting rule dictates that a PRO questionnaire be presented after a defined number of consecutive measurements yield a value of a metric indicative of a cardiopulmonary status greater than a baseline value. In a further example, the reporting rule dictates that a PRO questionnaire be presented in response to input information received by the user device 160 indicating that the subject is ready to respond to the PRO questionnaire. In some instances, the result of such evaluation indicates that the reporting rule has been satisfied. In those instances, the user device 160 triggers the presentation of the PRO questionnaire. The computing device 170 can also provide such functionality.

[0096] User device 160 may receive the responses to the PRO survey and may transmit one or more of the responses to computing device 170 and / or processing platform 150 .

[0097] As described herein, user device 160 and computing device 170 may be configured with software applications that provide the functionality described herein in connection with monitoring and identifying changes in cardiopulmonary status of a subject. A group of server devices 154 within processing platform 150 may host the software applications. Thus, user device 160, computing device 170, and any other computing devices configured with software applications may implement the functionality of server device 154 via the software applications (e.g., via APIs and / or other types of libraries and associated function calls).

[0098] As described herein, it should be noted that the present disclosure is not limited to the structure of sensor device 118 shown in Figure 1. Sensor device 118 may include fewer or more types of sensor devices than those shown in Figure 1 and still achieve the functionality described herein related to monitoring and identifying status changes in cardiopulmonary conditions.

[0099] 11A is a schematic block diagram of an example computing system 1100 capable of performing analysis of multi-modal measurement signals generated by wearable device 110 (FIG. 1) in accordance with one or more aspects of the present disclosure. Computing system 1100 may embody or be part of processing platform 150 described herein in connection with the example systems and techniques of the present disclosure. Thus, example computing system 1100 may provide at least a portion of the functionality described herein in connection with monitoring cardiopulmonary status changes using multi-modal measurement signals in accordance with aspects described herein.

[0100] As previously described, processing platform 150 includes multiple server devices 154. The multiple server devices 154 may be arranged in a cloud architecture. Accordingly, exemplary computing system 1100 includes two types of server devices: compute server devices 1120 and storage server devices 1130. A subset of the compute server devices 1120 may host various modules that, individually or collectively, enable implementing the analyses involved in monitoring cardiopulmonary status changes using multimodal measurement signals according to aspects described herein. Accordingly, the subset of compute server devices 1120 may operate according to the functionality described herein in connection with monitoring cardiopulmonary status changes using multimodal measurement signals. The architecture of each of the compute server devices 1120, including compute server device 1122, includes multiple input / output (I / O) interfaces 1124, one or more processors 1126, one or more memory devices 1128, and a bus architecture operatively coupling the processors and memory devices. In some cases, the computing server devices 1122 may store such modules in at least one of such memory devices 1128. At least a subset of the computing server devices 1120 may be operatively coupled or otherwise configured to communicate with one or more of the storage server devices 1130. The coupling may be direct or may be mediated by at least one of the gateway devices 1110. The storage server devices 1130 include data and / or metadata that may be used to implement functionality described herein in connection with monitoring cardiopulmonary status changes using multimodal measurement signals.

[0101] Each gateway device of the gateway devices 1110 may include one or more processors operatively coupled to or otherwise configured to communicate with one or more memory devices capable of holding application programming interfaces (APIs) and / or other types of program code for access to the compute server devices 1120 and storage server devices 1130. Such access may be programmatic, for example, via defined function calls. A subset of the compute server devices 1120 may host one or a combination of modules capable of using the APIs provided by the gateway devices 1110 to provide results that implement functionality described herein in connection with monitoring cardiopulmonary status changes using multimodal measurement signals according to aspects described herein.

[0102] FIG. 11B illustrates an example of a computing device capable of providing various functionality for monitoring and identifying changes in a subject's cardiopulmonary status according to aspects of the present disclosure. In some cases, the example computing device 1150 may embody user device 160 ( FIG. 1 ). In other cases, the example computing device 1150 may embody computing device 170. In still other cases, the example computing device 1150 may embody another type of computing device according to aspects of the present disclosure, such as a caregiver device. The example computing device 1150 may provide such functionality in response to the execution of one or more software components retained within the computing device 1150. Such components may make the example computing device 1150 a particular machine for monitoring and identifying changes in a subject's cardiopulmonary status, among other functions the example computing device 1150 may have. The software components may be embodied in or include one or more processor-accessible instructions, e.g., processor-readable and / or processor-executable instructions. In one scenario, at least a portion of the processor-accessible instructions may be embodied and / or executed to perform at least a portion of one or more of the techniques described herein. One or more processor-accessible instructions embodying a software component may be arranged in one or more program modules that may be compiled, linked, and / or executed on, for example, the exemplary computing device 1150 or other computing devices. Generally, such program modules include computer code, routines, programs, objects, components, information structures (e.g., data structures and / or metadata structures), etc. that may perform particular tasks (e.g., one or more operations) in response to execution by one or more processors 1152 integrated in the exemplary computing device 1150.The software components may form a software application for monitoring and identifying changes in the status of a subject's cardiopulmonary condition in accordance with the present disclosure, as described herein in connection with user device 160 and other computing devices.

[0103] Various exemplary aspects of the present disclosure can operate with numerous other general-purpose or special-purpose computing system environments or configurations. Examples of well-known computing systems, environments, and / or configurations that may be suitable for implementing various aspects of the present disclosure in connection with non-contact monitoring of vital signs can include personal computers, server computers, laptop devices, handheld computing devices such as mobile tablet or laptop computers, wearable computing devices, and multiprocessor systems. Additional examples include networked personal computers (PCs), mainframe computers, blade computers, programmable logic controllers, embedded systems, distributed computing environments that include any of the above systems or devices, and the like.

[0104] 11B , the exemplary computing device 1150 includes one or more processors 1152, one or more input / output (I / O) interfaces 1156, one or more memory devices 1160 (referred to as memory 1160), and a bus architecture 1162 (referred to as bus 1162) that operatively couples various functional elements of the exemplary computing device 1150. The exemplary computing device 1150 may optionally include a radio unit 1154. The radio unit 1154 may include one or more antennas and a communication processing unit, which may enable wireless communication between the exemplary computing device 1150 and another device, such as a remote computing device, a display device, and / or a remote sensor device. The bus 1162 may include at least one of a system bus, a memory bus, an address bus, or a message bus and may enable the exchange of information (data and / or signaling) between the processor 1152, the I / O interface 1156, and / or the memory 1160, or their respective functional elements. In some cases, the bus 1162 may enable such exchange of information in conjunction with one or more internal programming interfaces 1180 (also referred to as interfaces 1180). In cases where the processor 1152 includes multiple processors, the exemplary computing device 1150 may utilize parallel computing.

[0105] The I / O interface 1156 may enable communication of information between the exemplary computing device 1150 and an external device, such as another computing device, a display device, or a similar device. Such communication may include direct or indirect communication, such as an exchange of information between the exemplary computing device 1150 and an external device via a network or elements of a network. As illustrated, the I / O interface 1156 may include one or more of a network adapter, a peripheral adapter, and a display unit. Such adapters may enable or otherwise facilitate connectivity between an external device and one or more of the processor 1152 or memory 1160. For example, a peripheral adapter may include a group of ports that may include at least one of a parallel port, a serial port, an Ethernet port, a V.35 port, or an X.21 port. In certain aspects, the parallel port may include a general-purpose interface bus (GPIB), IEEE-1284, while the serial port may include recommended standard (RS)-232, V.11, Universal Serial Bus (USB), FireWire, or IEEE-1394.

[0106] The I / O interface 1156 may include a network adapter that can operatively couple the exemplary computing device 1150 to one or more remote computing devices, display devices, or sensor devices (not depicted in FIG. 11B ) via one or more traffic and signaling pipes that can enable or otherwise facilitate the exchange of traffic and / or signaling between the exemplary computing device 1150 and such one or more remote computing devices or sensors. Such network coupling, provided at least in part by the network adapter, may be implemented in a wired environment, a wireless environment, or both. Information communicated by the network adapter may result from the implementation of one or more operations of a method or combination of methods according to aspects of the present disclosure. The I / O interface 1156, in some cases, may include more than one network adapter.

[0107] Additionally, or in some cases, depending on the architectural complexity and / or form factor of the exemplary computing device 1150, the I / O interface 1156 may include a user device interface unit that may enable control of the operation of the exemplary computing device 1150 or that may enable communication or indication of operating conditions of the computing device 710. The user device interface may be embodied in or may include a display unit. The display unit, in some cases, may include a display device with touchscreen functionality. Additionally, or in some cases, the display unit may include light emitters, such as light-emitting diodes, that may communicate operating states of the computing device 1150.

[0108] The bus 1162 may have at least one of several types of bus structures, depending on the architectural complexity and / or form factor of the computing device 1150. The bus structure may include a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor, or a local bus using any of a variety of bus architectures. By way of example, such architectures may include an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, an Enhanced ISA (EISA) bus, a Video Electronics Standards Association (VESA) local bus, an Accelerated Graphics Port (AGP) bus, a Peripheral Component Interconnect (PCI) bus, a PCI Express bus, a Personal Computer Memory Card International Association (PCMCIA) bus, a Universal Serial Bus (USB), etc.

[0109] The exemplary computing device 1150 may include a variety of computer-readable media. Computer-readable media may be any available media (transitory and non-transitory) that can be accessed by a computing device. In one aspect, computer-readable media may include computer non-transitory storage media (or computer-readable non-transitory storage media) and communication media. Examples of computer-readable non-transitory storage media include any available media that can be accessed by the exemplary computing device 1150, including both volatile and non-volatile media, and removable and / or non-removable media. The memory 1160 may include computer-readable media in the form of volatile memory, such as random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM).

[0110] Memory 1160 may include functionality instruction storage 1164 and functionality data storage 1168. Functionality instruction storage 1164 may include processor-accessible instructions that, in response to execution (e.g., by at least one of processors 1152, individually or jointly), may implement one or more of the disclosed functionalities in connection with monitoring and identifying changes in a subject's cardiopulmonary condition status. The processor-accessible instructions may embody or include one or more software components, exemplified as monitoring component 1167. Execution of at least one component of monitoring component 1167 may implement, individually or in combination, one or more of the methods according to aspects described herein. Such execution may cause a processor executing at least one component (e.g., one of processors 1152) to perform at least a portion of a method disclosed herein.

[0111] A processor of processors 1152 executing at least one of monitoring components 1167 can retrieve data from or retain data in one or more memory elements 1170 in functionality data storage 1168 to operate according to functionality programmed or otherwise configured by monitoring component 1167. The one or more memory elements 1170 can be referred to as monitoring data 1170. Such information can include at least one of code instructions, a data structure, or the like. For example, at least a portion of such a data structure can define one or more of various time series of values for a signal according to aspects of the present disclosure.

[0112] An interface 1180 (e.g., an application programming interface) may enable or facilitate communication of data between two or more components within functionality instruction storage 1164. Data that may be communicated by interface 1180 may result from the performance of one or more operations in a method or combination of methods of the present disclosure. In some cases, one or more of functionality instruction storage 1164 or functionality data storage 1168 may be embodied in or include removable / non-removable and / or volatile / non-volatile computer storage media.

[0113] At least a portion of at least one of the monitoring components 1167 or the monitored data 1170 can program or otherwise configure one or more of the processors 1152 to operate at least in accordance with the functionality described herein. One or more of the processors 1152 can individually or collectively execute at least one of the monitoring components 1167 and can use at least a portion of the data in the functionality data storage 1168 to provide monitoring and identification of changes in the status of a subject's cardiopulmonary condition in accordance with one or more aspects described herein. In some cases, the functionality instruction storage 1168 can embody or include a computer-readable non-transitory storage medium having computer-accessible instructions that, upon execution, cause at least one processor (e.g., one or more of the processors 1152) to perform a group of operations or blocks, including those described in connection with the example methods disclosed herein.

[0114] Additionally, memory 1170 may include processor-accessible instructions and information (e.g., data, metadata, and / or program code) that enable or facilitate operation and / or management (e.g., upgrades, software installation, any other configuration, etc.) of exemplary computing device 1150. Thus, as illustrated, memory 1160 may include memory element 1172 (labeled operating system (O / S) instructions 1172) that includes one or more program modules that embody or include one or more operating systems, such as a Windows operating system, Unix, Linux, Symbian, Android, Chromium, and virtually any OS suitable for mobile or fixed computing devices. In one aspect, the operational and / or architectural complexity of exemplary computing device 1150 may determine a suitable O / S. Memory 1160 also includes system information storage 1176 with data, metadata, and / or program code that enable or facilitate operation and / or management of exemplary computing device 1150. Elements of O / S instructions 1172 and system information storage 1176 may be accessible or operable by at least one of processors 1152 .

[0115] Although the components held in the functionality instruction storage 1164 and other executable program components, such as the O / S instructions 1172, are illustrated herein as separate blocks, it should be appreciated that such software components may reside at various times in different memory components of the exemplary computing device 1150 and may be executed individually or jointly by at least one of the processors 1152.

[0116] The exemplary computing device 1150 may include a power source (not shown) capable of powering components or functional elements within such a device. The power source may be a rechargeable power source, such as a rechargeable battery, and may include one or more transformers to achieve a power level suitable for operation of the exemplary computing device 1150 and the components, functional elements, and associated circuitry therein. In some cases, the power source may be attached to a conventional power grid to recharge and ensure that such a device may be operational. To that end, the power source may include an I / O interface (e.g., one of interfaces 1176) for connecting to a conventional power grid. Additionally, or in other cases, the power source may include an energy conversion component, such as a solar panel, to provide additional or alternative power resources or autonomy to the exemplary computing device 1150.

[0117] In some scenarios, the exemplary computing device 1150 can operate in a network environment by utilizing connections to one or more remote computing devices and / or sensor devices (not depicted in FIG. 11B ). By way of example, the remote computing device may be a personal computer, a portable computer, a server, a router, a network computer, a peer device, or other common network node. As described herein, the connection (physical and / or logical) between the exemplary computing device 1150 and the remote computing device or sensor may be through one or more traffic and signaling pipes, which may include wired and / or wireless links, as well as several network elements (routers or switches, concentrators, servers, etc.) that form a local area network (LAN), a wide area network (WAN), and / or other networks (wireless or wired) with different footprints.

[0118] Other architectures of a system for monitoring cardiopulmonary condition status changes can also be implemented. As illustrated, FIG. 12 is a schematic block diagram of an example system 1200 for monitoring cardiopulmonary condition status changes in accordance with one or more aspects of the present disclosure. In example system 1200, the structure of wearable device 110 can be simplified relative to example system 100 (FIG. 1). To that end, a base station device 1210 operatively coupled to or otherwise configured to communicate with wearable device 110 can provide control functionality for wearable device 110. Base station device 1210 can also provide data and signaling to processing platform 150, which can be operatively coupled to or otherwise configured to communicate with processing platform 150. The data can be indicative of measurement signals generated by multiple sensor devices 118. Base station device 1210 can also be operatively coupled to or otherwise configured to communicate with user device 160 and computing device 170 via network 140.

[0119] 13 is a schematic block diagram of an example system 1300 for monitoring cardiopulmonary status changes, according to one or more aspects of the present disclosure. In the example system 1300, the wearable device 110 may be operatively coupled or otherwise configured to communicate with the processing platform 150 via the network 140 and may provide data and signaling to the processing platform 150. The data may represent measurement signals generated by the plurality of sensor devices 118. Rather than being operatively coupled to or configured to communicate directly with the user device 160, as in the example system 100 (FIG. 1), the wearable device 110 may be operatively coupled to the user device 160 via the network 140.

[0120] In view of the aspects described herein, exemplary methods that may be implemented in accordance with the present disclosure may be better understood with reference to the flowcharts in FIGS. 14-17, for example. For simplicity of explanation, the exemplary methods disclosed herein are presented and described as a series of blocks (each block representing, e.g., an action or operation in the method). However, the exemplary methods are not limited by the order of the blocks and associated actions or operations, as some blocks may occur in a different order and / or concurrently with other blocks based on the order illustrated and described herein. Furthermore, the illustrated blocks and associated actions may not necessarily be required to implement an exemplary method according to one or more aspects of the present disclosure. Two or more of the exemplary methods (and any other methods disclosed herein) may be implemented in combination with each other. It should be noted that the exemplary methods (and any other methods disclosed herein) may alternatively be represented as a series of interrelated states or events, such as in a state diagram.

[0121] 14 is a flowchart of an example method for determining a cardiopulmonary status change according to one or more aspects of the present disclosure. A computing device or system of computing devices can implement the example method 1400 in whole or in part. To that end, each computing device of the computing devices includes computing resources that can implement at least one of the blocks included in the example method 1400 and other methods described herein. Computing resources include, for example, a central processing unit (CPU), a graphics processing unit (GPU), a tensor processing unit (TPU), other types of processors, memory, disk space, incoming and / or outgoing bandwidth, interfaces (such as I / O interfaces or APIs, or both), controller devices, power sources, combinations of these, and / or similar resources. Computing devices and computing systems can include multiple modules (e.g., a group of modules 156 or a software application described herein) and can implement the example method 1400 by executing one or more instances of such modules. To execute instances of such modules (or other program code), one or more processors, individually or collectively if the processors are part of the computing resources described above, may execute the modules (or other program code). In one example, the computing system is or includes processing platform 150.

[0122] At block 1410, a computing system may receive a thoracic impedance (TI) measurement signal corresponding to a subject. The TI measurement signal is a time-dependent signal. For illustrative purposes, in aspects of the present disclosure, a time-dependent signal may be a time series of signal values, where the signal has one value at one time (or instant) and another value at another time (or instant). A signal value at one time (or instant) may be the same as or different from another value at another time (or instant). A wearable device attached to the subject's torso (e.g., the subject's chest) acquires the TI measurement signal during a time interval. Thus, in some cases, the computing system may receive (directly or indirectly) the TI measurement signal from or otherwise access the wearable device. In other cases, the computing system may receive or otherwise access the TI measurement signal from another type of computing device that has access to and / or includes the TI measurement signal. A time interval may include an analysis period spanning two or more test periods. As described herein, each test period can span 24 hours in some cases. The TI measurement signal is obtained via an electrical sensor device configured to measure impedance and electrically coupled to electrodes in contact with respective sections of the subject's skin. The TI measurement signal may be obtained in a four-electrode arrangement. Thus, the electrical sensor is coupled to at least four electrodes. In one example, the wearable device is wearable device 110 (FIG. 1), the electrical sensor device is included in a group of electrical sensor device 120a (FIG. 1), and the at least four electrodes are part of the plurality of electrodes 114.

[0123] At block 1420, the computing system can determine, over a time interval, multiple values of a metric representative of the subject's respiratory function using the TI measurement signals. The metric can be a direct metric or a comprehensive metric. In one implementation, the metric is the ratio between the subject's exhalation time and inhalation time. As described herein, such a ratio can be expressed as ρ EI (real number in arbitrary units). In another implementation, the metric is the magnitude of the TI at the peak in the pulmonary respiratory cycle.

[0124] The metric that represents respiratory function is ρ EI In some implementations, determining the plurality of values of the metric includes manipulating the TI measurement signal to generate a pulmonary ventilation signal (also referred to as a respiration signal) corresponding to the subject during the time interval. That is, in some implementations, the exemplary method 1400 includes using the TI measurement signal to generate a respiration signal corresponding to the subject during the time interval. The computing system can then use the respiration signal to evaluate the metric for each measurement period included in the time interval. Thus, each value of the plurality of values of the metric corresponds to a measurement period, as described herein. In other words, in some implementations, the computing system can use the respiration signal to determine a plurality of values of the ratio between the subject's exhalation time and inhalation time over the time interval.

[0125] At block 1430, the computing system may monitor the time dependency of the metric using the multiple values over a time interval. In some cases, the monitoring may include determining that the time dependency is indicative of an increase in the metric (e.g., the ratio of the subject's exhalation time to inhalation time). In other cases, the monitoring may include determining that the time dependency is indicative of a decrease in the metric (e.g., the ratio of the subject's exhalation time to inhalation time). In still other cases, the monitoring may include determining that the time dependency is indicative of a substantially constant metric.

[0126] At block 1440, the computing system may identify a change in the subject's cardiopulmonary status status based on time dependency. In an implementation where the metric is the ratio of the subject's exhalation time to inhalation time, ρ EI A time dependency showing an increase in ρ can indicate increased airway obstruction and / or a worsening emphysematous condition, and thus, a worsening cardiopulmonary condition of the subject. EI A time dependence indicating a decrease in ρ may indicate a decrease in airway limitation and therefore an improvement in cardiopulmonary status. EI By determining that the time dependence of ρ is approximately constant, it can be determined that the cardiopulmonary status remains unchanged. EI In the case of a determination that the time dependence of is approximately constant and approximately equal to 1, the status change may correspond to CHF decompensation.

[0127] In block 1450, the computing system may instruct or otherwise cause the computing device to perform an action or sequence of actions based on the status change. In some cases, the computing device may be a user device. Additionally, or in other cases, the computing device may be a clinician device or another device within the hospital system.

[0128] In some cases, as part of example method 1400, the computing system may instruct or otherwise cause the wearable device to perform a measurement cycle of the subject's thoracic impedance based on the status change. As described herein, the wearable device may be a type of computing device.

[0129] Additionally, or alternatively, as part of example method 1400, the computing system may, based on the status change, prompt the subject to have the wearable device perform measurements of the subject's thoracic impedance over a measurement period.

[0130] Although exemplary method 1400 is described as being implemented by a computing system such as processing platform 150 (FIG. 1), the disclosure is not limited in that respect. Indeed, a computing device according to aspects of the disclosure, such as user device 160 or computing device 170, may also implement exemplary method 1500.

[0131] FIG. 15 is a flowchart of an example method for determining a change in a subject's cardiopulmonary status according to one or more aspects of the present disclosure. The example method 1500 determines a change in a subject's cardiopulmonary status by assessing the subject's respiratory effort. A computing device or a system of computing devices can implement the example method 1500 in whole or in part. To that end, each computing device includes computing resources that can implement at least one of the blocks included in the example method 1500 and other methods described herein. The computing resources include, for example, a CPU, a graphics processing unit (GPU), a TPU, memory, disk space, incoming and / or outgoing bandwidth, an interface (such as an I / O interface or API, or both), a controller device, a power supply, a combination of these, and / or similar resources. Computing devices and computing systems can include, for example, multiple modules (e.g., a group of modules 156 or a software application described herein) and can implement the example method 1500 by executing one or more instances of such modules. To execute instances of such modules (or other program code), one or more processors, when the processors are part of the computing resources described above, may individually or collectively execute the modules (or other program code). A computing system that implements example method 1400 (FIG. 14) may also implement example method 1500. In one example, the computing system is or includes processing platform 150.

[0132] In block 1510, the computing system can use thoracic impedance (TI) measurement signals during the time interval to generate a respiratory signal corresponding to the subject during the time interval. As described herein, the TI measurement signal is a time-dependent signal. Thus, the respiratory signal is also a time-dependent signal. A wearable device attached to the subject's torso can acquire the TI measurement signal during the time interval. The time interval includes an analysis period spanning two or more test periods. In some cases, as described herein, each test period can span 24 hours. As also described herein, the TI measurement signal can be acquired via an electrical sensor device configured to measure impedance and electrically coupled to electrodes contacting respective regions of the subject's skin at respective skin locations on the subject's torso (e.g., the subject's chest, e.g., FIG. 3 ). The TI measurement signal can be acquired in a four-electrode configuration. Thus, in some cases, the electrical sensor is coupled to at least four electrodes. In one example, the wearable device is wearable device 110 (FIG. 1), the electrical sensor device is included in the group of electrical sensor devices 120a (FIG. 1), and the at least four electrodes are part of the plurality of electrodes 114.

[0133] In block 1520, the computing system can use the acceleration measurement signal during the time interval to generate a movement signal corresponding to a movement of the subject's chest wall during the time interval. The computing system can generate the movement signal by implementing the example method 1600 shown in FIG. 16 and described below. As described herein, the acceleration measurement signal is a time-dependent signal. Thus, the movement signal is also a time-dependent signal. The wearable device that acquires the TI measurement signal can also acquire the acceleration measurement signal. As also described herein, the acceleration signal can be acquired via an inertial sensor (e.g., a three-axis accelerometer) configured to measure the direction and / or magnitude of an acceleration vector corresponding to the movement of the subject's chest wall. Thus, the acceleration measurement signal can be measured along a first axis (e.g., ax a first acceleration measurement signal corresponding to a component of an acceleration vector along a second axis (e.g., a y a second acceleration measurement signal corresponding to another component of the acceleration vector along a third axis (e.g., a z and a third acceleration measurement signal corresponding to a further component of the acceleration vector along the first axis, the second axis, and the third axis. The first axis, the second axis, and the third axis are mutually orthogonal. In the case where the wearable device is wearable device 110 (FIG. 1), the inertial sensor device may be included in the group of inertial sensor devices 120c.

[0134] At block 1530, the computing system can determine, over a time interval, multiple values of a metric associated with the subject's respiration using the respiratory signal and the movement signal. For example, the metric can be associated with the subject's respiratory function. In some cases, the metric indicates the delay between the mechanical onset of inspiration and the onset of inspiratory airflow. In other cases, the metric represents the subject's respiratory effort, where the metric indicates the amount of energy present in the movement signal relative to another amount of energy present in the respiratory signal. An exemplary metric representing the subject's respiratory effort is defined as the ratio of the variance of the movement signal to the variance of the respiratory signal. The computing system can determine such a ratio according to equation (1) or equation (2) above.

[0135] In some cases, to determine the start of inspiratory airflow using the respiratory signal, the computing system can determine a time point corresponding to airflow exceeding a threshold amount by applying zero-crossing processing to the respiratory signal, and the computing system can then configure this time point as the start of inspiratory airflow.

[0136] Additionally, or alternatively, to determine the start of inspiratory airflow using the respiratory signal, the computing system can determine the airflow signal based on the first derivative with respect to time of the respiratory signal over a second time interval. In addition, the computing system can then determine a peak in the airflow signal during the second time interval and identify a time point corresponding to the peak. Further, the computing system can configure this time point as the start of inspiratory airflow.

[0137] For the mechanical start of inspiration, the computing system can determine a trough of the movement signal during a second time interval. Then, the computing system can determine a peak of the movement signal during the second time interval. Then, the computing system can identify a second time point corresponding to a value of the movement signal that exceeds a second value of the movement signal at the trough by a defined amount. The defined amount can be a defined fraction of a third value of the movement signal at the peak. Then, the computing system can configure the second time point as the mechanical start of inspiration.

[0138] At block 1540, the computing system may monitor the time dependence of a metric associated with the subject's respiration using multiple values over a time interval.

[0139] At block 1550, the computing system can identify a status change in the subject's cardiopulmonary condition based on time dependency. The computing system can identify the status change according to aspects described herein.

[0140] At block 1560, the computing system may instruct or otherwise cause the computing device to perform an action or sequence of actions based on the status change. In some cases, the computing device may be a user device. Additionally, or in other cases, the computing device may be a clinician device or another device within the hospital system.

[0141] Although exemplary method 1500 is described as being implemented by a computing system such as processing platform 150 (FIG. 1), the disclosure is not limited in that respect. Indeed, a computing device according to aspects of the disclosure, such as user device 160 or computing device 170, may also implement exemplary method 1500.

[0142] 16 is a flowchart of an example of a method for generating a movement signal corresponding to movement of a subject's chest wall, according to one or more aspects of the present disclosure. As described herein, in some cases, a computing system implementing example method 1500 (FIG. 15) can also implement example method 1600. At block 1610, the computing system can use a low-pass filter to filter an acceleration measurement signal that is in a respiratory frequency band (also referred to as a respiratory motion frequency band) to provide a filtered acceleration signal. For example, the computing system can use a low-pass filter to filter a first acceleration measurement signal (e.g., a x In addition, the computing system may use a low-pass filter to filter the second acceleration measurement signal (e.g., a time series of values of a) to provide a first filtered acceleration signal. y In some cases, the first acceleration measurement signal may be filtered to provide a second filtered acceleration signal. x and the second acceleration measurement signal is a time series of values of a yIn other words, the acceleration measurement signal relied upon to generate the movement signal may be an in-plane acceleration signal.

[0143] As described herein, the low-pass filter can be configured to remove frequencies above a cutoff frequency within a respiratory frequency band (or respiratory motion frequency band). In this disclosure, the respiratory frequency band is a range of frequencies that includes most or essentially all of the likely frequencies of pulmonary ventilation in a human (e.g., an adult human). The frequency range can range, for example, from about 0.05 Hz to about 0.75 Hz. In some implementations, the cutoff frequency is 0.75 Hz.

[0144] At block 1620, the computing system may subtract the average values of each of the filtered acceleration signals from the filtered acceleration measurement signals. Subtracting such average values results in acceleration measurement signals with the average values removed. In one example, the computing system may subtract the average values of the filtered first acceleration measurement signals from the filtered first acceleration measurement signals to result in first acceleration measurement signals with the average values removed. Additionally, the computing system may subtract the average values of the filtered second acceleration measurement signals from the filtered second acceleration measurement signals to result in second acceleration measurement signals with the average values removed.

[0145] In block 1630, the computing system can convert the acceleration measurement signal from which the mean value has been removed to the time base of a TI measurement signal corresponding to the subject. Such conversion allows for a direct comparison of the acceleration measurement signal from which the mean value has been removed and the TI measurement signal (or a signal derived from the TI measurement signal) on the same time base. As described herein, a wearable device that generates an acceleration measurement signal can also generate the TI measurement signal essentially simultaneously with generating the acceleration measurement signal.

[0146] In block 1640, the computing system can generate a pulmonary ventilation signal for the subject using the TI measurement signal. The pulmonary ventilation signal is generated according to embodiments described herein. An example of a pulmonary ventilation signal is shown in FIG. 5.

[0147] At block 1650, the computing system may determine a sufficient polar angle φ of an in-plane acceleration vector formed by the first mean-removed acceleration measurement signal and the second mean-removed acceleration measurement signal. That is, as described herein, the in-plane acceleration vector is a linear combination of the first and second mean-removed inertial measurement signals: Δa x cos(φ)+Δa y sin(φ), where Δa x and Δa y represent the inertial measurement signal with the first and second mean values removed (or vice versa), respectively. The computing system iteratively varies φ and Δa until the correlation is maximized or otherwise achieves a satisfactory value. x cos(φ)+Δa y and determining the correlation between sin(φ) and the pulmonary ventilation signal. A sufficient value may be configurable. At the end of such an iterative process, φ is determined or otherwise identified as the value of φ in the last iteration.

[0148] The computing system can then construct a motion signal representing the motion of the subject's chest wall as a linear combination of the first and second mean-removed inertial measurement signals that results from setting φ to the value φ that results in maximum or otherwise satisfactory correlation. That is, the motion signal can be expressed as Δa x cos(φ0)+Δa y It is constructed as sin(φ0).

[0149] Although exemplary method 1600 is described as being implemented by a computing system such as processing platform 150 (FIG. 1), the disclosure is not limited in that respect. Indeed, a computing device according to aspects of the disclosure, such as user device 160 or computing device 170, may also implement exemplary method 1600.

[0150] FIG. 17 is a flowchart of an example method for determining a cardiopulmonary status change, according to one or more embodiments of the present disclosure. A computing device or system of computing devices can implement the example method 1700 in whole or in part. To that end, each computing device of the computing devices includes computing resources that can implement at least one of the blocks included in the example method 1800 and other methods described herein. Computing resources include, for example, a CPU, a graphics processing unit (GPU), a TPU, memory, disk space, incoming and / or outgoing bandwidth, interfaces (such as I / O interfaces or APIs, or both), controller devices, power supplies, combinations of these, and / or similar resources. Computing devices and computing systems can include multiple modules (e.g., a group of modules 156 or software applications described herein) and can implement the example method 1700 by executing one or more instances of such modules. To execute an instance of such a module (or other program code), one or more processors can execute the module (or other program code) individually or collectively, if the processors are part of the computing resources described above. A computing system that implements example method 1400 (FIG. 14), example method 1500 (FIG. 15), example method 1600 (FIG. 16), or two or more of those methods, may also implement example method 1700. In one example, the computing system is or includes processing platform 150.

[0151] In block 1710, the computing system may receive a plurality of measurement signals corresponding to the subject during a time interval. The time interval includes an analysis period spanning two or more test periods. As described herein, each test period may, in some cases, span 24 hours. Each measurement signal of the plurality of measurement signals is acquired according to a respective sensing modality during the time interval. A wearable device (e.g., wearable device 110 (FIG. 1)) attached to the subject's torso acquires the plurality of measurement signals during the time interval. The wearable device includes a plurality of sensor devices (e.g., sensor device 118 (FIG. 1)). The plurality of sensor devices includes groups of sensor devices, each group having one or more sensor devices. Each group of sensor devices is configured to probe a particular physical quantity of the subject associated with the subject's cardiopulmonary function. The probing of a particular physical quantity is referred to as a sensing modality. Thus, each group of sensor devices is configured to generate a measurement signal according to a particular sensor modality. As described herein, the plurality of sensor devices may include one or a combination of: (i) a group of electrical sensor devices 120a; (ii) a group of acoustic sensor devices 120b; (iii) a group of inertial sensor devices 120c; or (iv) an oximeter device 120d.

[0152] At block 1720, the computing system may use the plurality of measurement signals over a time interval to determine multiple values of one or more metrics representative of the subject's cardiopulmonary function. As described herein, each of the metrics may be either a direct metric or a comprehensive metric.

[0153] At block 1730, the computing system may monitor the time dependency of each of the one or more metrics using the multiple values over the time interval. The time dependency of a metric may be referred to as the trend of the metric.

[0154] At block 1740, the computing system may identify a status change in the subject's cardiopulmonary condition based on one or a combination of the respective time dependencies (or respective trends). The status change may be identified according to aspects described herein.

[0155] In block 1750, the computing system may instruct or otherwise cause the computing device to perform an action or sequence of actions based on the status change. In some cases, the computing device may be a user device. Additionally, or in other cases, the computing device may be a clinician device or another device within the hospital system.

[0156] Although exemplary method 1700 is described as being implemented by a computing system such as processing platform 150 (FIG. 1), the disclosure is not limited in that respect. Indeed, a computing device according to aspects of the disclosure, such as user device 160 or computing device 170, may also implement exemplary method 1700.

[0157] Numerous exemplary embodiments emerge from the above detailed description and accompanying drawings. Exemplary embodiments include:

[0158] Example 1. A system comprising: a wearable device configured to be attached to a torso of a subject, the wearable device comprising a plurality of electrodes and a plurality of sensor devices, each electrode of the plurality of electrodes configured to contact a respective skin area at a respective skin location on the torso of the subject, the plurality of sensor devices including an electrical sensor device operatively coupled to the plurality of electrodes and configured to generate a first measurement signal during a measurement period, and a motion sensor device configured to generate a second measurement signal during the measurement period; and a computing device configured to communicate with the wearable device and configured to receive the first measurement signal and the second measurement signal, and to determine a value of a metric or a respective value in a combination of metrics using a combination of the first measurement signal and the second measurement signal, wherein each of the metrics and combinations of metrics indicates a status of the cardiopulmonary condition of the subject.

[0159] Example 2. The system of Example 1, wherein the computing device is further configured to identify a change in cardiopulmonary status based on a change in value relative to a past value of the metric.

[0160] Example 3. The system of Example 1 or 2, wherein the computing device is further configured to identify a change in cardiopulmonary status based on an individual change in each value of a metric in the combination of metrics relative to its respective past value.

[0161] Example 4. The system of any one of the preceding examples, wherein the motion sensor device comprises an inertial sensor device.

[0162] Example 5. The system of any one of the preceding examples, wherein the wearable device further includes a haptic device configured to: determine that a placement of the wearable device on the subject's torso falls short of satisfying the placement rule; instruct the haptic device to cause vibration of the wearable device; determine that an updated placement of the wearable device on the subject's torso satisfies the placement rule; and instruct the haptic device to stop vibrating the wearable device.

[0163] Example 6. The system of any one of the preceding examples, wherein the computing device is further configured to provide an indication of actions performed by the subject prior to the measurement period, including performing one or more movements to stress the subject's cardiopulmonary system.

[0164] Example 7. A system described in any one of the preceding examples, wherein the computing device is further configured to obtain multiple second values of the metric over each second measurement period within the analysis period, monitor the time dependency of the metric using the value and the multiple second values over the analysis period, and identify a status change in the cardiopulmonary condition based on the time dependency.

[0165] Example 8. A system described in any one of the preceding examples, wherein the computing device is further configured to obtain a plurality of second respective values of the metric combination over each second measurement period within the analysis period, monitor the time dependency of each of the metrics in the metric combination using the respective values and the plurality of second respective values over the analysis period, and identify a status change in the cardiopulmonary condition based on the respective time dependency.

[0166] Example 9. The system of any one of the preceding examples, wherein the measurement period has a duration in the range of about 25 seconds to about 120 seconds.

[0167] Example 10. The system of any one of the preceding examples, wherein the measurement period has a duration in the range of about 25 seconds to about 5 days.

[0168] Example 11. The system of any one of the preceding examples, wherein the analysis period has a duration of at least 1 hour that is longer than the duration of another of the measurement periods.

[0169] Example 12. The system of any one of the preceding examples, wherein the computing device is further configured to cause the wearable device to generate an additional measurement signal based on the status change.

[0170] Example 13. The system of any one of the preceding examples, wherein the computing device is further configured to prompt one or more of the subject, clinician, or caregiver to cause the wearable device to generate additional measurement signals based on the first value of the particular metric or each second value in a particular combination of metrics.

[0171] Example 14. A system described in any one of the preceding examples, wherein the computing device is further configured to provide an indication of an action to be performed by the subject in response to at least one of a first value of a particular metric, a first value of a combination of metrics, or a status change.

[0172] Example 15. The system of any one of the preceding examples, wherein the computing device is configured to cause the presentation of a message instructing the subject to proceed to an emergency room, a second message instructing the subject to contact their physician, or a third message instructing the subject to contact an assistant, to provide an indication of an action to be taken by the subject.

[0173] Example 16. The system of any one of the preceding examples, wherein the computing device is configured to cause transmission of an electronic communication to a clinician device or transmission of a second electronic communication to a caregiver device to provide an indication of an action performed by the subject, wherein the electronic communication and the second electronic communication include the indication.

[0174] Example 17. The system of any one of the preceding examples, wherein the computing device is configured to present a message to one or more of the subject, clinician, or caregiver instructing them to adjust the placement of the wearable device on their torso to provide an indication of an action performed by the subject.

[0175] Example 18. The system of any one of the preceding examples, wherein the computing device is further configured to execute the program code and, in response thereto, present a patient-reported outcome (PRO) questionnaire associated with the cardiopulmonary condition.

[0176] Example 19. The system of any one of the preceding examples, wherein the plurality of sensor devices further includes an acoustic sensor device configured to generate a third measurement signal during a measurement period.

[0177] Example 20. The system of any one of the preceding examples, wherein the computing device is further configured to receive the first measurement signal, the second measurement signal, and the third measurement signal, and to determine another value of the metric in the combination of metrics or each other value using the combination of the first measurement signal, the second measurement signal, and the third measurement signal.

[0178] Example 21. The system of any one of the preceding examples, wherein the plurality of sensor devices further includes an optical device configured to generate a fourth measurement signal during the measurement period.

[0179] Example 22. The system of any one of the preceding examples, wherein the optical device comprises a pulse oximeter.

[0180] Example 23. The system of any one of the preceding examples, wherein the computing device is further configured to receive the first measurement signal, the second measurement signal, the third measurement signal, and the fourth measurement signal, and to determine a further value of the metric in the combination of metrics or a further value of each metric using a combination of the first measurement signal, the second measurement signal, the third measurement signal, and the fourth measurement signal.

[0181] Example 24. The system of any one of the preceding examples, wherein the computing device is further configured to determine that the fourth measurement signal indicates an oxygen saturation level that is below a threshold level, determine that the change in cardiopulmonary status indicates a worsening of the cardiopulmonary condition, and present the subject with a message instructing them to proceed to an emergency room, another message instructing them to contact their physician, or yet another message instructing them to contact an assistant.

[0182] Example 25. A method comprising: generating, by one or more processors, individually or collectively, during a time interval, a respiratory signal corresponding to a subject using a time-dependent thoracic impedance (TI) measurement signal; generating, by one or more processors, individually or collectively, during a time interval, a movement signal corresponding to movement of the subject's chest wall using a time-dependent acceleration measurement signal; determining, by one or more processors, individually or collectively, a plurality of values of a metric associated with the subject's respiration over the time interval using the respiratory signal and the movement signal; monitoring, by one or more processors, individually or collectively, the time-dependence of the metric over the time interval using the plurality of values; and identifying, by one or more processors, individually or collectively, a change in cardiopulmonary status of the subject based on the time-dependence.

[0183] Example 26. The method of example 25, wherein the time interval comprises an analysis period spanning at least one test period, each of the at least one test period spanning a plurality of measurement periods.

[0184] Example 27. The method described in Example 25 or 26, wherein the TI measurement signal is acquired by a wearable device attached to the subject's chest and the acceleration measurement signal is acquired by the wearable device.

[0185] Example 28. The method of any one of the preceding examples, wherein the metric indicates the delay between the mechanical onset of inspiration and the onset of inspiratory airflow.

[0186] Example 29. The method of any one of the preceding examples, further comprising determining, by one or more processors, individually or jointly, the onset of inspiratory airflow using the respiratory signal.

[0187] Example 30. A method according to any one of the preceding examples, wherein determining the start of inspiratory airflow includes determining a time point corresponding to airflow exceeding a threshold amount by applying zero-crossing processing to the respiratory signal, and configuring the time point as the start of inspiratory airflow.

[0188] Example 31. The method of any one of the preceding examples, wherein determining the start of inspiratory airflow includes determining the airflow signal based on a first derivative with respect to time of the respiratory signal over a second time interval, determining a peak in the airflow signal during the second time interval, identifying a time point corresponding to the peak, and configuring the time point as the start of inspiratory airflow.

[0189] Example 32. The method of any one of the preceding examples, further comprising: determining, by the one or more processors, individually or jointly, a trough of the movement signal during a second time interval; determining, by the one or more processors, individually or jointly, a peak of the movement signal during the second time interval; identifying, by the one or more processors, individually or jointly, a second time point corresponding to a value of the movement signal that exceeds a second value of the movement signal at the trough by a defined amount that is a defined fraction of a third value of the movement signal at the peak; and configuring, by the one or more processors, individually or jointly, the second time point as a mechanical start of inspiration.

[0190] Example 33. The method of any one of the preceding examples, wherein the metric represents a subject's respiratory effort, and the metric indicates an amount of energy present in the movement signal relative to a second amount of energy present in the respiratory signal.

[0191] Example 34. The method of any one of the preceding examples, wherein the metric is defined as the ratio of the variance of the movement signal to the variance of the respiration signal.

[0192] Example 35. A computing system comprising at least one processor and at least one memory device storing processor-executable instructions that, when executed by the at least one processor individually or jointly, cause the computing system to at least: use time-dependent thoracic impedance (TI) measurement signals during a time interval to generate a respiratory signal corresponding to a subject; use time-dependent acceleration measurement signals during the time interval to generate a movement signal corresponding to movement of the subject's chest wall; determine multiple values of a metric associated with the subject's respiration using the respiratory signal and the movement signal over the time interval; monitor the time-dependence of the metric using the multiple values over the time interval; and identify a change in cardiopulmonary status of the subject based on the time-dependence.

[0193] Example 36. The computing system of Example 35, wherein the time interval includes an analysis period spanning at least one test period, each of the at least one test period spanning a plurality of measurement periods.

[0194] Example 37. A computing system described in Example 35 or 36, wherein the TI measurement signal is acquired by a wearable device attached to the subject's chest and the acceleration measurement signal is acquired by the wearable device.

[0195] Example 38. The computing system of any one of the preceding examples, wherein the metric indicates the delay between the mechanical onset of inspiration and the onset of inspiratory airflow.

[0196] Example 39. A computing system described in any one of the preceding examples, wherein the processor-executable instructions, in response to execution by at least one processor, individually or jointly, further cause the computing system to determine, by at least one processor, individually or jointly, using the respiratory signal, the onset of inspiratory airflow.

[0197] Example 40. A computing system as described in any one of the preceding examples, wherein the processor-executable instructions, in response to execution by at least one processor individually or jointly, to determine the start of inspiratory airflow, further cause the computing system to at least determine a time point corresponding to airflow exceeding a threshold amount by applying zero-crossing processing to the respiratory signal, and configure the time point as the start of inspiratory airflow.

[0198] Example 41: To determine the start of inspiratory airflow, the processor-executable instructions, in response to execution by at least one processor individually or jointly, further cause the computing system to determine an airflow signal based on at least a first derivative with respect to time of the respiratory signal over a second time interval, determine a peak in the airflow signal during the second time interval, identify a time point corresponding to the peak, and configure the time point as the start of inspiratory airflow. A computing system described in any one of the preceding examples.

[0199] Example 42. A computing system described in any one of the preceding examples, wherein the processor-executable instructions, in response to execution by at least one processor individually or jointly, further cause the computing system to at least determine a trough of the movement signal during a second time interval, determine a peak of the movement signal during the second time interval, identify a second time point corresponding to a value of the movement signal that exceeds a second value of the movement signal at the trough by a defined amount that is a defined fraction of a third value of the movement signal at the peak, and configure the second time point as the mechanical start of inspiration.

[0200] Example 43. A computing system according to any one of the preceding examples, wherein the metric represents the subject's respiratory effort and the metric indicates an amount of energy present in the movement signal relative to a second amount of energy present in the respiratory signal.

[0201] Example 44. A computing system according to any one of the preceding examples, wherein the metric is defined as the ratio of the variance of the movement signal to the variance of the respiration signal.

[0202] Example 45. A user device comprising at least one processor and at least one memory device storing processor-executable instructions that, when executed by the at least one processor individually or jointly, cause the user device to at least: use a time-dependent thoracic impedance (TI) measurement signal during a time interval to generate a respiratory signal corresponding to a subject; use a time-dependent acceleration measurement signal during the time interval to generate a movement signal corresponding to movement of the subject's chest wall; determine, over the time interval, multiple values of a metric associated with the subject's respiration using the respiratory signal and the movement signal; monitor the time-dependence of the metric using the multiple values during the time interval; and identify a change in the subject's cardiopulmonary status based on the time-dependence.

[0203] Example 46. A user device as described in Example 45, wherein the time interval includes an analysis period spanning at least one test period, each of the at least one test period spanning multiple measurement periods.

[0204] Example 47. A user device described in Example 45 or 46, wherein the TI measurement signal is acquired by a wearable device attached to the subject's chest and the acceleration measurement signal is acquired by the wearable device.

[0205] Example 48. A user device according to any one of the preceding examples, wherein the metric indicates the delay between the mechanical onset of inspiration and the onset of inspiratory airflow.

[0206] Example 49. A user device described in any one of the preceding examples, wherein the processor-executable instructions, in response to execution by at least one processor, individually or jointly, further cause the user device to determine, by at least one processor, individually or jointly, using the respiratory signal, the onset of inspiratory airflow.

[0207] Example 50. A user device described in any one of the preceding examples, wherein the processor-executable instructions, in response to execution by at least one processor individually or jointly, to determine the start of inspiratory airflow, further cause the user device to at least determine a time point corresponding to airflow exceeding a threshold amount by applying zero-crossing processing to the respiratory signal, and configure the time point as the start of inspiratory airflow.

[0208] Example 51. A user device described in any one of the preceding examples, wherein the processor-executable instructions, in response to execution by at least one processor individually or jointly, further cause the user device to determine an airflow signal based on at least a first derivative with respect to time of the respiratory signal over a second time interval, determine a peak in the airflow signal during the second time interval, identify a time point corresponding to the peak, and configure the time point as the start of inspiratory airflow, in order to determine the start of inspiratory airflow.

[0209] Example 52. A user device described in any one of the preceding examples, wherein the processor-executable instructions, in response to execution by at least one processor individually or jointly, further cause the user device to at least determine a trough of the movement signal during a second time interval, determine a peak of the movement signal during the second time interval, identify a second time point corresponding to a value of the movement signal that exceeds a second value of the movement signal at the trough by a defined amount that is a defined fraction of a third value of the movement signal at the peak, and configure the second time point as the mechanical start of inspiration.

[0210] Example 53. A user device described in any one of the preceding examples, wherein the metric represents the subject's respiratory effort and the metric indicates an amount of energy present in the movement signal relative to a second amount of energy present in the respiratory signal.

[0211] Example 54. A user device according to any one of the preceding examples, wherein the metric is defined as the ratio of the variance of the movement signal to the variance of the respiration signal.

[0212] Example 55. A method comprising: receiving, by one or more processors, individually or collectively, a thoracic impedance (TI) measurement signal corresponding to a subject, the TI measurement signal being time-dependent and acquired during a time interval; generating, by one or more processors, individually or collectively, a respiratory signal corresponding to the subject during the time interval using the TI measurement signal; determining, by one or more processors, individually or collectively, a plurality of values of a ratio between the subject's expiratory time and inhalation time over the time interval using the respiratory signal; monitoring, by one or more processors, individually or collectively, the time-dependence of the ratio over the time interval using the plurality of values; and identifying, by one or more processors, individually or collectively, a change in the subject's cardiopulmonary status based on the time-dependence.

[0213] Example 56. The method of Example 55, further comprising causing the computing device, by one or more processors, individually or jointly, to present one or more markings indicative of the status change.

[0214] Example 57. The method of Example 55 or 56, wherein the cardiopulmonary condition includes at least one of airway narrowing or emphysema, and the method further includes determining, by one or more processors, individually or collectively, that the time dependency indicates an increase in the ratio between the subject's exhalation time and inhalation time, and identifying, by one or more processors, individually or collectively, the status change as a worsening of the cardiopulmonary condition.

[0215] Example 58. The method of any one of the preceding examples, wherein the cardiopulmonary condition includes at least one of airway narrowing or emphysema, and the method further includes determining, by the one or more processors, individually or collectively, that the time dependency indicates a decrease in the ratio between the subject's exhalation time and inhalation time, and identifying, by the one or more processors, individually or collectively, the status change as an improvement in the cardiopulmonary condition.

[0216] Example 59. A method as described in any one of the preceding examples, wherein the TI measurement signal is received from a wearable device attached to the subject's torso, and the method further includes causing the wearable device to perform a measurement cycle of the subject's thoracic impedance based on the status change, by one or more processors, individually or jointly.

[0217] Example 60. A method as described in any one of the preceding examples, wherein the TI measurement signal is received from a wearable device attached to the subject's torso, and the method further includes prompting the subject, by one or more processors, individually or jointly, based on the status change, to cause the wearable device to perform measurements of the subject's thoracic impedance over a measurement period.

[0218] Example 61. A method as described in any one of the preceding examples, wherein generating a respiratory signal using the TI measurement signal includes filtering the TI measurement signal using a low-pass filter configured to remove frequencies above a cutoff frequency within the respiratory frequency band, subtracting an average value of the filtered TI measurement signal from the TI measurement signal to result in a mean-removed TI measurement signal, and subtracting a moving average of the mean-removed TI measurement signal from the mean-removed TI measurement signal to result in the respiratory signal.

[0219] Example 62. A computing system comprising at least one processor and at least one memory device storing processor-executable instructions that, in response to execution by the at least one processor individually or jointly, cause the computing system to at least receive a thoracic impedance (TI) measurement signal corresponding to a subject, the TI measurement signal being time-dependent and obtained during a time interval; generate a respiratory signal corresponding to the subject during the time interval using the TI measurement signal; determine, over the time interval, using the respiratory signal, multiple values of a ratio between the subject's expiratory time and inhalation time; monitor, over the time interval, the multiple values, the time-dependence of the ratio; and identify a change in the subject's cardiopulmonary status status based on the time-dependence.

[0220] Example 63. A computing system as described in Example 62, wherein the processor-executable instructions, in response to execution by at least one processor individually or jointly, further cause the computing system to cause the computing device to present one or more markings indicating a status change.

[0221] Example 64. A computing system as described in Example 62 of Example 63, wherein the cardiopulmonary condition includes at least one of airway narrowing or emphysema, and the processor-executable instructions, in response to execution by at least one processor individually or jointly, further cause the computing system to determine that the time dependency indicates an increase in the ratio between the subject's exhalation time and inhalation time, and identify the status change as a worsening of the cardiopulmonary condition.

[0222] Example 65. A computing system described in any one of the preceding examples, wherein the cardiopulmonary condition includes at least one of airway narrowing or emphysema, and the processor-executable instructions, in response to execution by at least one processor individually or jointly, further cause the computing system to determine that the time dependency indicates a decrease in the ratio between the subject's exhalation time and inhalation time, and identify the status change as an improvement in the cardiopulmonary condition.

[0223] Example 66. A computing system described in any one of the preceding examples, wherein a TI measurement signal is received from a wearable device attached to the torso of the subject, and the processor-executable instructions, in response to execution by at least one processor individually or jointly, further cause the computing system to cause the wearable device to perform a measurement cycle of the subject's thoracic impedance based on a status change.

[0224] Example 67. A computing system described in any one of the preceding examples, wherein a TI measurement signal is received from a wearable device attached to the subject's torso, and the processor-executable instructions, in response to execution by at least one processor individually or jointly, further cause the computing system to prompt the subject based on a status change to cause the wearable device to perform measurements of the subject's thoracic impedance over a measurement period.

[0225] Example 68. A computing system described in any one of the preceding examples, wherein the processor-executable instructions, in response to execution by at least one processor individually or jointly, further cause the computing system to filter the TI measurement signal using a low-pass filter configured to remove at least frequencies above a cutoff frequency within the respiratory frequency band, subtract an average value of the filtered TI measurement signal from the TI measurement signal to result in a mean-removed TI measurement signal, and subtract a moving average of the mean-removed TI measurement signal from the mean-removed TI measurement signal to result in a respiratory signal, to generate a respiratory signal using the TI measurement signal.

[0226] Example 69. A user device comprising at least one processor and at least one memory device storing processor-executable instructions that, when executed by the at least one processor individually or jointly, cause the user device to at least receive a thoracic impedance (TI) measurement signal corresponding to a subject, the TI measurement signal being time-dependent and obtained during a time interval; generate a respiratory signal corresponding to the subject during the time interval using the TI measurement signal; determine, over the time interval, using the respiratory signal, multiple values of a ratio between the subject's expiratory time and inhalation time; monitor, over the time interval, the multiple values, the time-dependence of the ratio; and identify a change in the subject's cardiopulmonary status based on the time-dependence.

[0227] Example 70. A user device as described in Example 69, wherein the processor-executable instructions, in response to execution by at least one processor individually or jointly, further cause the user device to cause the computing device to present one or more markings indicating a status change.

[0228] Example 71. A user device as described in Example 69 or 70, wherein the cardiopulmonary condition includes at least one of airway narrowing or emphysema, and the processor-executable instructions, in response to execution by at least one processor individually or jointly, further cause the user device to determine that the time dependency indicates an increase in the ratio between the subject's exhalation time and inhalation time, and identify the status change as a worsening of the cardiopulmonary condition.

[0229] Example 72. A user device described in any one of the preceding examples, wherein the cardiopulmonary condition includes at least one of airway narrowing or emphysema, and the processor-executable instructions, in response to execution by at least one processor individually or jointly, further cause the user device to determine that the time dependency indicates a decrease in the ratio between the subject's exhalation time and inhalation time, and identify the status change as an improvement in the cardiopulmonary condition.

[0230] Example 73. A user device described in any one of the preceding examples, wherein a TI measurement signal is received from a wearable device attached to the subject's torso, and the processor-executable instructions, in response to execution by at least one processor individually or jointly, further cause the user device to cause the wearable device to perform a measurement cycle of the subject's thoracic impedance based on a status change.

[0231] Example 74. A user device described in any one of the preceding examples, wherein a TI measurement signal is received from a wearable device attached to the subject's torso, and the processor-executable instructions, in response to execution by at least one processor individually or jointly, further cause the user device to prompt the subject, based on a status change, to cause the wearable device to perform measurements of the subject's thoracic impedance over a measurement period.

[0232] Example 75. A user device described in any one of the preceding examples, wherein the processor-executable instructions, in response to execution by at least one processor individually or jointly, further cause the user device to filter the TI measurement signal using a low-pass filter configured to remove at least frequencies above a cutoff frequency within the respiratory frequency band, subtract an average value of the filtered TI measurement signal from the TI measurement signal to result in a mean-removed TI measurement signal, and subtract a moving average of the mean-removed TI measurement signal from the mean-removed TI measurement signal to result in a respiratory signal, to generate a respiratory signal using the TI measurement signal.

[0233] Various aspects of the present disclosure may take the form of entirely or partially hardware aspects, entirely or partially software aspects, or a combination of software and hardware. Furthermore, as described herein, various aspects of the present disclosure (e.g., systems and methods) may take the form of a computer program product including a computer-readable, non-transitory storage medium having processor-accessible instructions (e.g., computer-readable and / or computer-executable instructions), such as computer software, encoded on or otherwise embodied in such storage medium. These instructions may be read or otherwise accessed and executed, individually or jointly, by one or more processors to perform or enable performance of the operations described herein. The instructions may be provided in any suitable form, such as source code, compiled code, interpreted code, executable code, static code, dynamic code, assembler code, or combinations thereof. Any suitable computer-readable, non-transitory storage medium may be utilized to form a computer program product. For example, a computer-readable medium may include any tangible, non-transitory medium for storing information in a form readable or otherwise accessible by one or more computers or processors operatively coupled to the non-transitory medium. Non-transitory storage media may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media, optical storage media, flash memory, etc.

[0234] Aspects of the present disclosure are described herein with reference to block diagrams and flowchart illustrations of processor-implemented methods, systems, devices, apparatus, and computer program products. It can be understood that each block of the block diagrams and flowchart illustrations, and combinations of blocks in the block diagrams and flowchart illustrations, respectively, can be implemented by processor-accessible instructions. Such instructions can include, for example, computer program instructions (e.g., processor-readable and / or processor-executable instructions). The processor-accessible instructions can be constructed (e.g., linked and compiled) and stored in processor-executable form in one or more memory devices or one or many other processor-accessible non-transitory storage media. These computer program instructions may also be stored in a processor-readable memory, and in response to execution by one or more processors, individually or collectively, the computer program instructions may direct a computer, computing device, or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the processor-readable memory produce a product including processor-accessible instructions (e.g., processor-readable instructions and / or processor-executable instructions) for implementing the functions specified in the flowchart blocks (individually or in a specific combination) or blocks in the block diagrams (individually or in a specific combination). The computer program instructions may be loaded into a computer, computing device, or other programmable data processing apparatus to cause a series of operations to be performed on the computer or other programmable apparatus to generate a computer-implemented process. The series of operations may be performed in response to execution by one or more processors or other types of processing circuits. Thus, such instructions executed on a computer or other programmable apparatus provide operations for implementing the functions specified in the flowchart blocks (individually or in a specific combination) or blocks in the block diagrams (individually or in a specific combination).

[0235] In some implementations, the processor-accessible instructions may be loaded into or incorporated into a general-purpose computer, a special-purpose computer, or another programmable information processing apparatus to create a specific machine, such that the operations or functions specified in the flowchart block(s) may be implemented in response to execution by the computer or processing apparatus. More specifically, the loaded processor-accessible instructions may be accessed and executed by one or more processors, individually or jointly, or by other types of processing circuitry. In response to execution, the loaded processor-accessible instructions provide the functionality described in association with the flowchart blocks (individually or in specific combinations) or block diagram blocks (individually or in specific combinations). Thus, such instructions executed on a computer, computing device, or other programmable data processing apparatus can create means for implementing the functions specified in the flowchart blocks (individually or in specific combinations) or block diagram blocks (individually or in specific combinations).

[0236] Unless expressly stated otherwise, it is in no way intended that any protocol, procedure, process, or method described herein be construed as requiring that its acts or steps be performed in a particular order. Thus, where a process or method claim does not actually recite the order in which its acts or steps are to be followed, or where the claims or description of the subject disclosure do not otherwise specifically recite that the steps are limited to a particular order, no order is intended to be inferred in any respect. This applies to any possible implicit basis for interpretation, including questions of logic regarding the arrangement of steps or operational flow, the apparent meaning derived from grammatical construction or punctuation, the number or type of aspects set forth in the specification or accompanying drawings, etc.

[0237] As used in this disclosure, including the accompanying drawings, terms such as “component,” “module,” “interface,” and “system” are intended to refer to computer-related entities or entities relating to devices having one or more specific functionalities. An entity may be hardware, a combination of hardware and software, software, or software in execution. One or more such entities may also be referred to as a “functional element.” By way of example, a component may be a processor, a processor, an object, an executable file, a thread of execution, a program, and / or a process running on a computer. For example, both an application running on a server or network controller and the server or network controller may be components. One or more components may reside within a process and / or thread of execution, and a component may be localized on one computer and / or distributed between two or more computers. These components may also execute from various computer-readable media having various data structures stored thereon. Components can communicate via local and / or remote processes, such as according to signals comprising one or more data packets (e.g., data from one component interacting via signals with another component in a local system, with another component in a distributed system, and / or with other systems over a network such as the Internet). As another example, a component can be a device having specific functionality provided by mechanical parts operated by electrical or electronic circuits, which parts can be controlled or otherwise operated by program code executed by a processor. As yet another example, a component can be a device that provides specific functionality through electronic components without mechanical parts, which electronic components can include a processor for executing program code that provides, at least in part, the functionality of the electronic component.As yet another example, an interface may include an I / O component or an application programming interface (API) component. Although the above examples are directed to aspects of components, the illustrated aspects or features also apply to systems, modules, and the like.

[0238] Additionally, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified or clear from the context, "X employs A or B" is intended to mean either of the natural inclusive permutations. That is, if X employs A, X employs B, or X employs both A and B, then "X employs A or B" is satisfied under any of the above cases. Furthermore, as used in this specification and the accompanying drawings, "a" and "an" should be construed to mean "one or more" unless otherwise specified or clear from the context to be directed to the singular form.

[0239] Additionally, the terms "example" and "such as" are used herein to mean serving as an example or illustration. Any aspect or design described herein as "example" or referred to in conjunction with an "e.g., " clause is not necessarily to be construed as preferred or advantageous over other aspects or designs described herein. Rather, use of the terms "example" or "such as" is intended to present concepts in a concrete manner. Terms such as "first," "second," "third," etc., used in the claims and description are for clarity only and do not necessarily denote or imply any order in time or space, unless otherwise clear from the context.

[0240] The term "processor" as used in this disclosure may refer to any computing processing unit or device comprising processing circuitry capable of manipulating data and / or signaling. Computing processing units or devices may include, for example, single-core processors, single processors with software multithreading execution capabilities, multi-core processors, multi-core processors with software multithreading execution capabilities, multi-core processors with hardware multithreading technology, parallel platforms, and parallel platforms with distributed shared memory. Additionally, a processor may include an integrated circuit, an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a field-programmable gate array (FPGA), a programmable logic controller (PLC), a complex programmable logic device (CPLD), discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. In some cases, a processor may utilize nanoscale architectures, such as molecular and quantum dot-based transistors, switches, and gates, to optimize space usage or improve performance of user equipment. A processor may also be implemented as a combination of computing processing units. A processor may also be implemented as a combination of computing processing units. Additionally or alternatively, a processor may be implemented as a virtual machine (or virtual processor) that enables a host device to provide a software environment that shares the computing resources of the host device with other virtual processors and / or components of the host device. The software environment, sometimes referred to as a virtualization environment, enables the virtual processor to perform operations by executing processor-executable instructions that are maintained on a portion of the underlying computing resources.As described herein, computing resources may include, for example, an operating system (O / S), a CPU, memory, disk space, incoming bandwidth, and / or outgoing bandwidth.

[0241] Additionally, terms such as "store," "data store," "data storage," "database," and substantially any other information storage component associated with the operation and functionality of a component refer to a "memory component," or an entity embodied in a "memory" or component that comprises memory. It will be understood that the memory components described herein can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory. Furthermore, memory components can be removable or fixed to a functional element (e.g., device, server).

[0242] By way of example only, non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM), which acts as external cache memory. By way of example, and not limitation, RAM is available in many forms, including synchronous RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct Rambus RAM (DRRAM). Additionally, the disclosed memory components of a system or method herein are intended to include, without being limited to, these and any other suitable types of memory.

[0243] Various aspects described herein may be implemented as a method, system, device, apparatus, or article of manufacture using standard programming and / or engineering techniques. Additionally, various aspects disclosed herein may also be implemented by program modules or other types of computer program instructions stored in a memory device and executed by a processor or other combination of hardware and software or hardware and firmware. In some cases, a virtual machine (or virtual processor) may execute the program modules or other types of computer program instructions. Such program modules or computer program instructions may be loaded onto a general-purpose computer, a special-purpose computer, or another type of programmable data processing apparatus to generate a machine, such that the instructions, executing on the computer or other programmable data processing apparatus, create means for implementing the functionality disclosed herein.

[0244] The term "article of manufacture," as used herein, is intended to encompass a computer program accessible from any computer-readable device, carrier, or medium. For example, computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard drive disks, floppy disks, magnetic strips, or the like), optical disks (e.g., compact disks (CDs), digital versatile disks (DVDs), Blu-ray disks (BDs), or the like), smart cards, and flash memory devices (e.g., cards, sticks, key drives, or the like).

[0245] What has been described above includes examples of one or more aspects of the present disclosure. Of course, for purposes of describing these examples, it is not possible to describe every conceivable combination of elements or methodologies, and it can be recognized that many further combinations and permutations of the aspects are possible. Accordingly, the aspects disclosed and / or claimed herein are intended to embrace all such alternatives, modifications, and variations that are within the spirit and scope of the Detailed Description and the appended claims. Furthermore, to the extent one or more of the terms "includes," "including," "has," "have," or "having" are used in either the Detailed Description or the claims, such terms are intended to be inclusive in the same manner as the term "comprising," as "comprising" is interpreted when employed as a transitional term in the claims.

Claims

1. 1. A method comprising: receiving, by one or more processors individually or jointly, a thoracic impedance (TI) measurement signal corresponding to the subject, the thoracic impedance measurement signal being time-dependent and acquired during a time interval; generating, by the one or more processors, individually or jointly, a respiratory signal corresponding to the subject during the time interval using the TI measurement signal; determining, by the one or more processors, individually or jointly, using the respiratory signal, a plurality of values of a ratio between exhalation time and inhalation time of the subject over the time interval; monitoring, by said one or more processors individually or jointly, the time dependence of said ratio over said time interval using said plurality of values; and identifying, by the one or more processors individually or jointly, a change in cardiopulmonary status of the subject based on the time dependency.

2. The method of claim 1 , further comprising causing, by the one or more processors, individually or collectively, a computing device to present one or more markings indicative of the status change.

3. the cardiopulmonary condition comprises at least one of airway narrowing or emphysema, and the method further comprises: determining, by the one or more processors, individually or jointly, that the time dependency indicates an increase in the ratio between the exhalation time and the inhalation time of the subject; The method of claim 1 , further comprising: identifying, by the one or more processors, individually or collectively, the status change as a worsening of the cardiopulmonary condition.

4. the cardiopulmonary condition comprises at least one of airway narrowing or emphysema, and the method further comprises: determining, by the one or more processors, individually or jointly, that the time dependency indicates a decrease in the ratio between the exhalation time and the inhalation time of the subject; The method of claim 1 , further comprising: identifying, by the one or more processors, individually or collectively, the status change as an improvement in the cardiopulmonary condition.

5. 2. The method of claim 1, wherein the TI measurement signal is received from a wearable device attached to the subject's torso, the method further comprising causing the one or more processors, individually or jointly, to perform a measurement cycle of the subject's thoracic impedance based on the status change.

6. 2. The method of claim 1, wherein the TI measurement signal is received from a wearable device attached to the subject's torso, and the method further includes prompting the subject, by the one or more processors, individually or jointly, based on the status change, to cause the wearable device to perform thoracic impedance measurements of the subject over a measurement period.

7. generating the respiration signal using the TI measurement signal; filtering the TI measurement signal using a low pass filter configured to remove frequencies above a cutoff frequency within a respiratory frequency band; subtracting the mean value of the filtered TI measurement signal from the TI measurement signal to result in a mean-removed TI measurement signal; and subtracting a running average of the mean-removed TI measurement signal from the mean-removed TI measurement signal to yield the respiration signal.

8. 1. A computing system comprising: at least one processor; at least one memory device storing processor-executable instructions that, in response to execution by the at least one processor individually or collectively, cause the computing system to: receiving a thoracic impedance (TI) measurement signal corresponding to a subject, the TI measurement signal being time-dependent and acquired during a time interval; generating a respiratory signal corresponding to the subject during the time interval using the TI measurement signal; determining, over the time interval, a plurality of values of a ratio between exhalation time and inhalation time of the subject using the respiratory signal; monitoring the time dependence of the ratio using the plurality of values over the time interval; at least one memory device configured to identify a change in cardiopulmonary status of the subject based on the time dependency.

9. 10. The computing system of claim 8, wherein the processor-executable instructions, in response to execution by the at least one processor individually or jointly, further cause the computing system to cause a computing device to present one or more markings indicative of the status change.

10. the cardiopulmonary condition includes at least one of airway narrowing or emphysema, and the processor-executable instructions, in response to execution by the at least one processor individually or jointly, further provide the computing system with: determining that the time dependence indicates an increase in the ratio between the exhalation time and the inhalation time of the subject; The computing system of claim 8 , wherein the status change is identified as a deterioration in the cardiopulmonary condition.

11. the cardiopulmonary condition includes at least one of airway narrowing or emphysema, and the processor-executable instructions, in response to execution by the at least one processor individually or jointly, further provide the computing system with: determining that the time dependency indicates a decrease in the ratio between the exhalation time and the inhalation time of the subject; The computing system of claim 8 , wherein the status change is identified as an improvement in the cardiopulmonary condition.

12. 10. The computing system of claim 8, wherein the TI measurement signal is received from a wearable device mounted on the subject's torso, and the processor-executable instructions, in response to execution by the at least one processor individually or jointly, further cause the computing system to cause the wearable device to perform a measurement cycle of thoracic impedance of the subject based on the status change.

13. 10. The computing system of claim 8, wherein the TI measurement signal is received from a wearable device attached to the torso of the subject, and the processor-executable instructions, in response to execution by the at least one processor individually or jointly, further cause the computing system to prompt the subject based on the status change to cause the wearable device to perform a measurement of the subject's thoracic impedance over a measurement period.

14. To generate the respiratory signal using the TI measurement signal, the processor-executable instructions, in response to execution by the at least one processor, individually or jointly, further cause the computing system to: filtering the TI measurement signal using a low pass filter configured to remove frequencies above a cutoff frequency within a respiratory frequency band; subtracting the mean value of the filtered TI measurement signal from the TI measurement signal to result in a mean-removed TI measurement signal; 9. The computing system of claim 8, wherein a moving average of the mean-removed TI measurement signal is subtracted from the mean-removed TI measurement signal to yield the respiration signal.

15. 1. A user device, comprising: at least one processor; at least one memory device storing processor-executable instructions that, in response to execution by the at least one processor individually or collectively, transmit to the user device at least: receiving a thoracic impedance (TI) measurement signal corresponding to a subject, the TI measurement signal being time-dependent and acquired during a time interval; generating a respiratory signal corresponding to the subject during the time interval using the TI measurement signal; determining, over the time interval, a plurality of values of a ratio between exhalation time and inhalation time of the subject using the respiratory signal; monitoring the time dependence of the ratio using the plurality of values over the time interval; and at least one memory device that identifies a change in cardiopulmonary status of the subject based on the time dependency.

16. 16. The user device of claim 15, wherein the processor-executable instructions, in response to execution by the at least one processor individually or jointly, further cause the user device to cause a computing device to present one or more markings indicative of the status change.

17. the cardiopulmonary condition includes at least one of airway narrowing or emphysema, and the processor-executable instructions, in response to execution by the at least one processor individually or jointly, further cause the user device to: determining that the time dependence indicates an increase in the ratio between the exhalation time and the inhalation time of the subject; The user device of claim 15 , wherein the change in status is identified as a worsening of the cardiopulmonary condition.

18. the cardiopulmonary condition includes at least one of airway narrowing or emphysema, and the processor-executable instructions, in response to execution by the at least one processor individually or jointly, further cause the user device to: determining that the time dependency indicates a decrease in the ratio between the exhalation time and the inhalation time of the subject; The user device of claim 15 , wherein the change in status is identified as an improvement in the cardiopulmonary condition.

19. 16. The user device of claim 15, wherein the TI measurement signal is received from a wearable device attached to the torso of the subject, and the processor-executable instructions, in response to execution by the at least one processor individually or jointly, further cause the user device to cause the wearable device to perform a measurement cycle of the subject's thoracic impedance based on the status change.

20. 16. The user device of claim 15, wherein the TI measurement signal is received from a wearable device attached to the subject's torso, and the processor-executable instructions, in response to execution by the at least one processor individually or jointly, further cause the user device to prompt the subject, based on the status change, to cause the wearable device to perform a measurement of the subject's thoracic impedance over a measurement period.

Images