Automatic Detection of Diaphragm in Time-Operation Data Using the Waveform of a Ventilator

Abstract

The diaphragm measurement system includes at least one electronic processor programmed to perform a diaphragm measurement method, the diaphragm measurement method including receiving ultrasonic image data of a patient's diaphragm over a time period including a plurality of breaths, receiving the patient's respiratory data over the time period, calculating a diaphragm thickness metric based on the received ultrasonic image data of the diaphragm and the received respiratory data, and displaying a representation of the calculated diaphragm thickness metric on a display device.

Description

Technical Field

[0001] This patent application claims the benefit of U.S. Provisional Patent Application No. 63 / 354,818, filed on Jun. 23, 2022, under 35 U.S.C. § 119, the content of which is incorporated herein by reference.

[0002] The following generally relates to respiratory therapy techniques, mechanical ventilation techniques, ventilator-induced lung injury (VILI) techniques, mechanical ventilation weaning techniques, and related techniques.

Background Art

[0003] The transdiaphragmatic thickness fraction (TFdi or TFDI) measured by ultrasound (US) is widely recognized for assessing diaphragm function to optimize ventilator support and weaning. TFdi is defined as the rate of increase in diaphragm thickness relative to the end-expiratory diaphragm thickness during quiet breathing. TFdi depends on diaphragm activity and reflects the work of breathing (WoB) of the diaphragm (i.e., respiratory effort) (see, e.g., Vivier E, Mekontso Dessap A, Dimassi S, et al., “Diaphragm ultrasonography to estimate the work of breathing during non-invasive ventilation.” Intensive Care Med 2012; 38: 796-803; Goligher EC, Fan E, Herridge MS, et al., “Evolution of diaphragm thickness during mechanical ventilation. Impact of inspiratory effort.” Am J Respir Crit Care Med 2015; 192: 1080-1088).

[0004] The thickness and strain of the diaphragm can be evaluated at the zone of apposition (ZOA) during inspiration and expiration using a 10 - 15 MHz linear high - frequency transducer. The ZOA is the chest wall area where the lower rib cage reaches the abdominal contents. The probe is placed perpendicular to the chest wall between the anterior axillary line and the mid - axillary line. Using ultrasound in B - mode, the hemidiaphragm is identified as a hypoechoic layer of muscle tissue located beneath the intercostal muscles between two hyper - echogenic lines (the peritoneal line and the pleural line) (see, for example, Fayssoil A, Behin A, Ogna A et al., Diaphragm: Pathophysiology and Ultrasound Imaging in Neuromuscular Disorders. J Neuromuscul Dis. 2018). Diaphragmatic hypertrophy is evaluated by the hypertrophy rate (TFdi), calculated as the increase rate of the inspiratory diaphragm thickness relative to the expiratory end - tidal diaphragm thickness (T ee ) during quiet breathing, that is, according to Equation (1).

Equation

[0005] Several studies have evaluated the correlation between TFdi and respiratory effort (see, for example, M. Umbrello et al., “Diaphragm ultrasound as indicator of respiratory effort in critically ill patients undergoing assisted mechanical ventilation: a pilot clinical study.” Crit Care 19(1): 161, 2015). In this study, correlation coefficients of R = 0.8 were found between TFdi and the esophageal pressure-time product, and R = 0.7 between TFdi and the diaphragmatic pressure-time product. In other studies (see, for example, E. Oppersma et al., “Functional assessment of the diaphragm by speckle tracking ultrasound during inspiratory loading.” J Appl Physiology, 123(5): 1063-1070, 2017), in the ZOA, diaphragm strain can similarly be measured in real time. For example, in this study, the functional assessment of the diaphragm by speckle tracking ultrasound during inspiratory loading was analyzed. The technique of speckle tracking ultrasound enables the detection and tracking of diaphragm strain over time by analyzing acoustic markers called speckles. These speckles are formed by the interference of ultrasound scattered from physical structures sized corresponding to the ultrasound wavelength. Both diaphragm strain and diaphragm strain rate were strongly correlated with transdiaphragmatic pressure Pdi (strain r 2 = 0.72, strain rate r 2 = 0.80) and EAdi (strain r 2 = 0.60, strain rate r 2 = 0.66).

[0006] Furthermore, the use of ultrasound to evaluate the function of respiratory muscles (especially the diaphragm) is relatively new and is still rarely used due to the supposed difficulties in obtaining appropriate measurements (see, for example, Aarab Y, Jaber S, De Jong A, “Diaphragm Ultrasonography in ICU: Why, How, and When To Use It?” ICU Management & Practice, Volume 21 - Issue 3, 2021; Tuinman, P.R., Jonkman, A.H., Dres, M. et al., “Respiratory muscle ultrasonography: methodology, basic and advanced principles and clinical applications in ICU and ED patients―a narrative review.” Intensive Care Med 46, 594-605 (2020)). For example, confounding factors that can reduce the reproducibility and accuracy of daily bedside measurements include, for example, the position of the US probe over the patient at each measurement, the posture of the probe (angulation), the phase point in the patient's respiratory cycle, the pressure of the probe hand on the skin, the ultrasound settings selected by the user, the rate of hypertrophy that varies across the diaphragm muscle, the effort to manually record, memorize, and process data points, and various other conditions.

[0007] The thickness and thickness ratio of the diaphragm can be evaluated using B-mode and M-mode images (see, for example, Kalin BS, Gtirsel G. “Does it make difference to measure diaphragm function with M mode (MM) or B mode (BM)?” J Clin Monit Comput. Vol. 34, 1247-1257, 2020). In the case of M-mode, first, a 2D B-mode video is recorded. From these images, a single scan line intersecting the diaphragm region of interest is selected. Then, the time-motion image of that scan line is plotted, from which the thickness and thickness ratio of the diaphragm are determined.

[0008] A wearable ultrasonic patch for non-invasively and continuously evaluating the thickness of the diaphragm can be used in several potential applications such as, for example, detection of continuous atrophy, detection of diaphragm dysfunction, detection of accurate respiratory rate, prediction of extubation, detection of asynchrony, and proportional ventilation (non-invasive NAVA).

Summary of the Invention

Problems to be Solved by the Invention

[0009] Ideally, an ultrasonic patch for measuring the thickness (or hypertrophy rate) of the diaphragm is designed to operate in M-mode, i.e., to create one or several scan lines instead of a complete two-dimensional (2D) image. This reduces cost, installation area, power consumption, and the amount of data that needs to be processed and transferred. However, without a complete 2D image, it is difficult to identify the diaphragm in a single scan line.

[0010] The following discloses certain improvements to overcome these and other problems.

Means for Solving the Problems

[0011] In one aspect, a diaphragm measurement system includes at least one electronic processor programmed to perform a diaphragm measurement method including receiving ultrasonic image data of a patient's diaphragm over a time period including a plurality of breaths, receiving the patient's respiratory data over the time period, calculating a diaphragm thickness metric based on the received ultrasonic image data of the diaphragm and the received respiratory data, and displaying a representation of the calculated diaphragm thickness metric on a display device.

[0012] In other aspects, a diaphragm measurement method includes receiving ultrasonic image data of a patient's diaphragm over a time period including a plurality of breaths using at least one electronic processor, receiving the patient's respiratory data over the time period, calculating a diaphragm thickness metric based on the received ultrasonic imaging data of the diaphragm and the received respiratory data, and displaying a representation of the calculated diaphragm thickness metric on a display device.

[0013] One advantage is the use of a wearable ultrasonic (US) patch to acquire ultrasonic image data of a patient.

[0014] Another advantage is determining the position of a patient's diaphragm from ultrasonic image data.

[0015] Another advantage is determining the position of a patient's diaphragm without a complete ultrasonic image.

[0016] Another advantage is controlling the setting of an ultrasonic patch for acquiring ultrasonic image data of a patient.

[0017] Another advantage is controlling the setting of a mechanical ventilator based on ultrasonic image data of a patient.

[0018] A given embodiment may not provide any, one, two, more, or all of the advantages described above, and / or may provide other advantages that will become apparent to those skilled in the art upon reading and understanding the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The present disclosure may take the form of various components and arrangements thereof, and various steps and arrangements of the steps. The drawings are for the purpose of merely illustrating preferred embodiments and are not to be construed as limiting the present disclosure.

Figure 1

Figure 2

[0020] In the specification, unless specifically stated clearly in context, even if not stated as plural, it includes that there are plural ones. As used herein, the expressions that two or more parts or components are "coupled", "connected", or "engaged" mean that these parts are joined either directly or indirectly, i.e., by any of one or more intermediate parts or components, or operate together as long as they are interlocked. The directional expressions used in the specification, for example, but not limited to, up, down, left, right, upper, lower, front, rear, and their derivatives are related to the orientation of the elements shown in the drawings and do not limit the scope of the claimed invention unless specifically described in this specification. The terms "having" and "including" do not exclude the presence of elements or steps other than those described in this specification and / or recited in the claims. In an apparatus composed of several means, some of these means may be embodied by the same item of hardware.

[0021] Referring to FIG. 1, a diaphragm measuring device or system 1 is shown. A mechanical ventilator 2 is configured to administer ventilation therapy to an associated patient P. As shown in FIG. 1, the mechanical ventilator 2 includes an outlet 4 connectable to a patient breathing circuit 5 for delivering mechanical ventilation to the patient P. The patient breathing circuit 5 includes, for example, an intake line 6, an optional exhaust line 7 (which is omitted if the ventilator uses a single-limb patient circuit), a connector or port 8 for connecting to an endotracheal tube (ETT) 16, and one or more breathing sensors (not shown), such as a gas flow meter, a pressure sensor, and / or an end-tidal carbon dioxide (etC2) sensor, etc., typical components for a mechanical ventilator. The mechanical ventilator 2 is designed to deliver air, an air-oxygen mixture, or another breathable gas (not shown) to the outlet 4 at a programmed pressure and / or flow rate to ventilate the patient via the ETT. The mechanical ventilator 2 also includes at least one electronic processor or controller 13 (e.g., an electronic processor or microprocessor), a display device 14, and a non-transitory computer-readable medium 15 storing instructions executable by the electronic controller 13.

[0022] FIG. 1 illustrates a patient P with an inserted ETT 16 (the lower part of which is inside the patient P and is shown by a phantom line). The connector or port 8 connects to the ETT 16 to operably connect the mechanical ventilator 2 and deliver breathable air to the patient P via the ETT 16. The mechanical ventilation provided by the mechanical ventilator 2 via the ETT 16 is therapeutic for a wide range of diseases, such as various types of lung diseases like emphysema or pneumonia, viral or bacterial infections affecting respiration like COVID-19 infection or severe influenza, or cardiovascular diseases where the patient P receives a breathable gas enriched with oxygen.

[0023] FIG. 1 shows a patient P who has already had a tube inserted. That is, FIG. 1 shows the patient after tracheal intubation has been performed and the ETT 16 has been inserted into the patient. However, in order to perform tracheal intubation safely, an anesthesiologist or other qualified medical professional first evaluates the patient P to select the ETT size of the ETT 16, and then inserts the ETT of the selected size into the patient P by means of a tracheal intubation procedure.

[0024] FIG. 1 also shows a medical imaging device 18 (also referred to as an image acquisition device, an imaging device, etc.). As mainly described in this specification, the medical imaging device 18 includes an ultrasonic (US) medical imaging device 18. In other embodiments, the image acquisition device 18 can be a computed tomography (CT) image acquisition device, a C-arm imaging device, or other X-ray imaging devices, that is, a magnetic resonance (MR) image acquisition device, or a medical imaging device of another modality. As described in this specification, the medical imaging device 18 is used to acquire an image of the patient P. In some embodiments, the medical imaging device 18 can include a wearable ultrasonic imaging device 18. In other embodiments, the medical imaging device 18 can include an ultrasonic imaging probe 18.

[0025] In a more specific example, the medical imaging device 18 includes an ultrasonic patch 20 that can be worn by the patient P (e.g., on the abdomen or chest of the patient P at an appropriate position for imaging the patient's diaphragm as shown in FIG. 1). The ultrasonic patch 20 has one or more transducers and is arranged to acquire ultrasonic image data (i.e., an ultrasonic image) 24 of the patient P's diaphragm. For example, the ultrasonic patch 20 is configured to acquire image data of the patient P's diaphragm, and more specifically, is configured to acquire ultrasonic image data related to the thickness of the patient P's diaphragm during inhalation and exhalation while the patient P is receiving mechanical ventilation therapy using the mechanical ventilator 2. The electronic processor 13 controls the ultrasonic imaging device 18 to receive ultrasonic image data 24 of the patient P's diaphragm from the portable ultrasonic patch 20. In other embodiments, the electronic processor 13 can be implemented within the ultrasonic imaging device 18 and can be configured to control the operations of both the ultrasonic imaging device 18 and / or the mechanical ventilator 2. In a further embodiment, the electronic processor 13 can be implemented in a separate electronic processing device (not shown), such as a computer and a smart tablet, etc.

[0026] In some embodiments, the non - transitory computer - readable medium 15 stores an artificial neural network (ANN) model 22 configured to determine a diaphragm thickness metric based on the patient's ultrasonic image data 24 and respiratory data. The non - transitory computer - readable medium 15 also stores instructions executable by the electronic controller 13 for performing the diaphragm measurement method or process 100.

[0027] Referring to FIG. 2 and continuing to refer to FIG. 1, an exemplary embodiment of the diaphragm measurement method 100 is schematically shown as a flowchart. In operation 101, ultrasonic image data 24 of the patient P's diaphragm is received over a time period including a plurality of breaths. For example, the electronic processor 13 controls the ultrasonic imaging patch 20 to acquire ultrasonic image data 24 of the patient P's diaphragm.

[0028] In operation 102, respiratory data of the patient over the time period is received. This respiratory data is, for example, airway pressure (from a pressure sensor), airway flow (from an airflow sensor), or the output of a respiratory monitor (such as a respiratory belt worn by patient P).

[0029] In operation 103, based on the received ultrasonic image data 24 of the diaphragm of patient P and the received respiratory data, a thickness metric of the diaphragm can be calculated. In one example, the thickness metric of the diaphragm includes a diaphragm hypertrophy rate indicating the thickness of the diaphragm during inspiration relative to the thickness of the diaphragm during exhalation. In another example, the thickness metric of the diaphragm includes the average thickness of the diaphragm over a plurality of respiratory cycles.

[0030] In operation 104, a representation 30 of the calculated thickness metric of the diaphragm is displayed on the display device 14 of the mechanical ventilator 2. In some embodiments, in operation 105, the mechanical ventilator 2 can be controlled to adjust one or more parameters of the mechanical ventilation therapy delivered to the patient based on the calculated thickness metric of the diaphragm.

[0031] In some embodiments, the ultrasonic image data 24 has M-mode ultrasonic image data. For example, the diaphragm can be automatically detected in a single-channel ultrasonic echo pattern, thereby utilizing the correlation between the airway pressure and the thickness of the diaphragm of a patient who is breathing actively under pressure support ventilation, or under controlled or volume-controlled mandatory ventilation. For example, as shown in the inset A of FIG. 1, in the case of pressure support ventilation mode, the airway pressure correlates with the thickness of the diaphragm. In such an embodiment, calculating a diaphragm thickness metric based on the received M-mode ultrasonic image data 24 of the diaphragm and the received respiratory data includes identifying components of the M-mode ultrasonic image data 24 corresponding to the diaphragm of patient P based on the respiratory data of patient P, and calculating a diaphragm thickness metric based on the identified components of the M-mode ultrasonic image data 24 corresponding to the diaphragm of patient P. To do so, high echo lines within the M-mode ultrasonic image data 24 are identified, grouped, and paired high echo lines are formed. For example, the high echo lines can be identified by thresholding, edge detection, or any other suitable technique. Alternatively, this can be done on the raw ultrasonic image data 24 before the ultrasonic image data 24 is converted to a grayscale image by identifying high amplitude portions (i.e., strong echoes reflected from high echo structures) in the echo pattern. The pairs of high echo lines represent possible boundaries of the diaphragm. Preferably, the diaphragm should appear as a low echo layer of muscle tissue located between two adjacent high echo lines, i.e., the pleural line and the peritoneal line, and these adjacent lines are grouped together.

[0032] For each pair of high echo lines, the distance between the pair of high echo lines is determined as a function of time, and the correlation between the determined distance between the pair of high echo lines as a function of time and the respiratory data of patient P is determined. The component of the M-mode ultrasonic image data 24 corresponding to the diaphragm of patient P is identified as one of the pairs of high echo lines based on the determined correlation. In the case of pressure support ventilation, since the airway pressure correlates with the hypertrophy of the diaphragm, the pair with the maximum correlation coefficient is selected as the two high echo lines between which the diaphragm is located. For example, the respiratory rate of the patient over the time period is identified from the respiratory data of patient P, and the M-mode ultrasonic image data 24 is filtered using a bandpass filter 26 (for example, implemented on the non-transitory computer-readable medium 15 of the mechanical ventilator 2) having a passband centered on the identified respiratory rate, and the component of the M-mode ultrasonic image data 24 corresponding to the diaphragm of patient P is extracted.

[0033] In the case of a plurality of scan lines, the optimal scan line can be selected by selecting the scan line with the maximum correlation coefficient. Also, a plurality of scan lines can be selected (for example, for the correlation coefficient exceeding a predetermined threshold level) to calculate the average or arithmetic mean thickness of the diaphragm. If the correlation coefficient does not exceed the predetermined threshold level, the user / caregiver can receive a warning (for example, to reposition the patch 20 or to check for partial or complete (paralyzed) diaphragm dysfunction). This procedure can be repeated periodically (for example, daily).

[0034] In some embodiments, the ultrasonic image data 24 of the diaphragm of patient P is received, for example, during inspiration and expiration, over a time period including a plurality of breaths while the patient P is receiving mechanical ventilation therapy using the mechanical ventilator 2. In such embodiments, the electronic controller 13 is configured to determine a phase shift between the band-pass filtered M-mode ultrasonic image data 24 and the respiratory data of patient P. The patient-ventilator asynchrony is determined based on the phase shift, and an indication of the determined patient-ventilator asynchrony is displayed on the display device 14 of the mechanical ventilator 2. To do so, the ultrasonic image data 24 and the respiratory data are acquired, and the frequency of the mechanical ventilator 2 is determined. The time motion data of the ultrasonic imaging is filtered, and a phase shift between the muscle thickening signal from the time motion data of the ultrasonic imaging and the pressure signal of the ventilator is determined.

[0035] In some embodiments, the diaphragm measurement method 100 can be repeated for successive sessions based on adjustments to the system 1. In one example, one or more settings of the mechanical ventilator 2 are adjusted, and the method 100 is repeated for each adjustment. For example, the diaphragm is identified by taking advantage of the negative correlation between the thickening rate of the diaphragm of a patient who is actively breathing while receiving pressure support by changing the settings of the ventilator, and the pressure support level, and identifying the diaphragm in the echo pattern. To do this, the support level of the ventilator is set. High echo lines in the time motion data are identified, and the distance between each pair of adjacent high amplitude portions is determined. For each breath, time stamps of the end of inspiration and the end of expiration are determined from the pressure waveform or the flow waveform. These time stamps are used to calculate the thickening rate for each pair. These operations are repeated for several support levels. The correlation coefficient between the support level and the maximum thickness for each pair is determined. The pair with the maximum correlation coefficient is selected as the two high echo lines between which the diaphragm is located.

[0036] In the case of multiple scan lines, these operations can be repeated for each scan line, and the optimal scan line can be selected by selecting the scan line with the maximum correlation coefficient. Also, multiple scan lines can be selected, for example, when their correlation coefficients exceed a predetermined threshold level, and the average or arithmetic mean thickness of the diaphragm can be calculated. Additionally, when the correlation coefficient does not exceed the predetermined threshold level, the user / caregiver is warned, for example, to reposition the patch 20.

[0037] In another example, one or more settings of the ultrasonic patch 20 (e.g., frequency, time-varying gain, steering angle, focus depth, and aperture size and position (i.e., selection of active elements in the ultrasonic array)) are adjusted, and the method 100 is repeated for each adjustment. The ultrasonic patch 20 includes a transducer array that enables steering and can record several scan lines by sweeping an angle. The optimal scan line can be selected, or the average thickness (rate) can be calculated. Similarly, the optimal settings for frequency, focus depth, etc. can be found.

[0038] In another embodiment, the calculation of the diaphragm thickness metric can include inputting the M-mode ultrasonic image data 24 and respiratory data into the ANN model 22 and determining the diaphragm thickness metric based on the M-mode ultrasonic image data 24 and the respiratory data of the patient P. The correlation between pressure and diaphragm thickness is implicitly learned during the training of the ANN model 22. To do so, the M-mode ultrasonic image data 24 and respiratory data are acquired, input into the ANN model 22, and the ANN model 22 is trained to reproduce the ground truth diaphragm.

[0039] In some embodiments, the mechanical ventilator (MV) 2 provides several types of waveforms (e.g., pressure, flow rate, work of breathing, volume, etc.). A correlation is determined for each pair of the US (ultrasonic) line and the MV signal, and a selection of the optimal correlation of the MV waveform is determined. In the case of partial or complete diaphragmatic dysfunction, under pressure or volume-controlled ventilation, the diaphragmatic thickening rate can be negative (e.g., see Santana PV, Cardenas LZ, Albuquerque ALP, Carvalho CRR, Caruso P. Diaphragmatic ultrasound: a review of its methodological aspects and clinical uses. J Bras Pneumol. 2020 Nov 20) due to passive stretching. Also, other factors, such as too high a pressure support level, can result in a negative diaphragmatic thickening rate. Thus, when detecting a negative diaphragmatic thickening rate, a caregiver can be alerted or the ventilation settings can be automatically adapted.

[0040] Although described with respect to mechanical ventilation therapy, the system 1 can be used in any suitable environment, including cardiac surgery, monitoring of heart failure, asynchronous detection, home ventilation, monitoring of bladder and prostate hypertrophy, stenosis of the carotid artery (e.g., stroke, cardiac output, and A-fib, etc.), and myocardial function and cardiac output in an emergency care environment (i.e., heart attack).

[0041] The present disclosure has been described with reference to preferred embodiments. Others may conceive of modifications and variations upon reading and understanding the foregoing detailed description. Exemplary embodiments are intended to include all such modifications and variations insofar as they fall within the scope of the appended claims or the equivalents thereof.

Claims

1. In a diaphragm measurement system having at least one electronic processor programmed to perform a diaphragm measurement method, the diaphragm measurement method comprises: receiving ultrasonic image data of a patient's diaphragm over a time period including a plurality of breaths; receiving the patient's respiratory data over the time period; calculating a diaphragm thickness metric based on the received ultrasonic image data of the diaphragm and the received respiratory data; and displaying a representation of the calculated diaphragm thickness metric on a display device A diaphragm measurement system comprising.

2. The system of claim 1, wherein the diaphragm thickness metric includes a diaphragm hypertrophy rate indicating the thickness of the diaphragm during inspiration relative to the thickness of the diaphragm during exhalation.

3. The system of claim 1, wherein the diaphragm thickness metric includes an average diaphragm thickness over a plurality of respiratory cycles.

4. Further comprising an ultrasonic imaging patch wearable by the patient, The at least one electronic processor controls the ultrasonic imaging patch to acquire ultrasonic image data of the patient's diaphragm. The system of claim 1.

5. The ultrasonic image data has M-mode ultrasonic image data, Calculating the diaphragm thickness metric based on the received M-mode ultrasonic image data of the diaphragm and the received respiratory data includes: identifying components of the M-mode ultrasonic image data corresponding to the patient's diaphragm based on the patient's respiratory data; and calculating the diaphragm thickness metric based on the identified components of the M-mode ultrasonic image data corresponding to the patient's diaphragm. The system of claim 1.

6. The at least one electronic processor includes: identifying high echo lines of the M-mode ultrasonic image data; grouping the high echo lines into pairs of high echo source lines; for each pair of the high echo lines, determining the distance between the pair of high echo lines as a function of time; for each pair of the high echo lines, determining a correlation between the distance determined as a function of time between the pair of high echo lines and the patient's respiratory data; and identifying, based on the determined correlation, a component of the M-mode ultrasonic image data corresponding to the patient's diaphragm as one of the pairs of high echo lines The system according to claim 5, which is programmed to identify components of the M-mode ultrasonic image data corresponding to the diaphragm of the patient by performing **Claim 7** Identifying components of M-mode ultrasonic image data corresponding to the diaphragm of the patient based on the respiratory data of the patient comprises identifying the respiratory rate of the patient over the time period from the respiratory data of the patient, filtering the M-mode ultrasonic image data using a band-pass filter having a passband centered on the identified respiratory rate to extract components of the M-mode ultrasonic image data corresponding to the diaphragm of the patient The system according to claim 5, which includes **Claim 8** The patient is undergoing mechanical ventilation over the time period, and the electronic processor determines a phase shift between the band-pass filtered M-mode ultrasonic image data and the respiratory data of the patient, determines patient-ventilator asynchrony based on the phase shift, and displays an indication of the determined patient-ventilator asynchrony on the display device The system according to claim 7, which is further programmed to **Claim 9** The respiratory data of the patient includes airway pressure, airway flow, or the output of a respiratory monitor. The system according to claim 1 **Claim 10** The patient is undergoing mechanical ventilation over the time period, and the electronic processor adjusts one or more settings of the mechanical ventilator and repeats the diaphragm measurement method for each adjustment The system according to claim 1, which is programmed to **Claim 11** The electronic processor adjusts one or more settings of the ultrasonic patch configured to acquire the ultrasonic image data and repeats the diaphragm measurement method for each adjustment The system according to claim 1, which is programmed to **Claim 12** Calculating the thickness metric of the diaphragm based on the received ultrasonic image data of the diaphragm and the received respiratory data comprises inputting the ultrasonic image data and the respiratory data into an artificial neural network (ANN) model configured to determine the thickness metric of the diaphragm based on the ultrasonic image data and the respiratory data of the patient The system according to claim 1, which includes **Claim 13** The system of claim 1, wherein the at least one electronic processor is configured to control an associated mechanical ventilation device to adjust one or more parameters of the mechanical ventilation therapy delivered to the patient based on the calculated diaphragm thickness metric.

14. The system of claim 13, further comprising a mechanical ventilation device configured to deliver mechanical ventilation therapy to the patient.

15. Using at least one electronic processor, Receiving ultrasonic image data of the patient's diaphragm over a time period including a plurality of breaths, Receiving the patient's respiratory data over the time period, Calculating a diaphragm thickness metric based on the received ultrasonic image data of the diaphragm and the received respiratory data, and Displaying a representation of the calculated diaphragm thickness metric on a display device A diaphragm measurement method comprising:

Images