Dynamically compressing a sensed physiological signal

Abstract

An example system includes a medical device includes one or more sensors configured to sense a physiological signal of a patient, the physiological signal including a first portion of the physiological signal and a second portion of physiological signal; processing circuitry of the medical device, the processing circuitry configured to: compress the first portion of the physiological signal at a first compression ratio; determine an indication of an occurrence of a medical condition; and in response to the determination of the indication of an occurrence of the medical condition, compress the second portion of the physiological signal at a second compression ratio, the second compression ratio being less than the first compression ratio; and communication circuitry of the IMD, the communication circuitry configured to output the compressed first portion of the physiological signal and the compressed second portion of the physiological signal to a computing device.

Description

Atty Ref. No.: A0012899W001DYNAMICALLY COMPRESSING A SENSED PHYSIOLOGICAL SIGNAL

[0001] This application claims the benefit of U.S. Provisional Patent Application Serial No. 63 / 736,985, filed 20 December 2024, the entire content of which is incorporated herein by reference.FIELD

[0002] The disclosure relates generally to medical device systems and, more particularly, medical device systems configured to sense a physiological signal.BACKGROUND

[0003] Medical devices may be used to monitor physiological signals of a patient. For example, some medical devices are configured to sense cardiac electrogram (EGM) signals indicative of the electrical activity of the heart via electrodes. Some medical devices are configured to sense electroencephalogram (EEG) signals indicative of the electrical activity of the brain via electrodes. Some medical devices are additionally or alternatively configured to sense other signals, such as heart sound signals indicative of the mechanical activity of the heart via a motion or vibration sensor, such as an accelerometer or microphone. Some medical devices may be configured to deliver a therapy in conjunction with or separate from the monitoring of physiological signals.SUMMARY

[0004] In general, this disclosure is directed to techniques for dynamically compressing sensed physiological signals and reconstructing the dynamically compressed physiological signals, e.g., as high-fidelity physiological signals. A medical device, e.g., an implantable medical device (IMD), that is configured to sense a physiological signal, such as an EGM signal, or a device that receives the signal from the medical device, may be configured to dynamically compress the sensed physiological signal. The device may determine whether the sensed physiological signal indicates a particular medical condition, such as an arrhythmia, and dynamically compress the sensed physiological signal at a particular compression rate based on whether the sensed physiological signal indicates a particular medical condition. In some examples, the device may compress portions of theAtty Ref. No.: A0012899W001 signal that do not indicate the particular medical condition at a greater compression rate than portions of the signal that do indicate the particular medical condition.

[0005] In some examples, the physiological signal may include a first physiological signal and a second physiological signal, the first physiological signal and the second physiological signal occurring during different periods of time. In some examples, the first physiological signal may be a first portion of the physiological signal and the second physiological signal may be a second portion of the physiological signal. In some examples, the physiological signal is an EGM signal of the patient, the first physiological signal is a first EGM signal, and the second physiological signal is a second EGM signal. The IMD may compress the first physiological signal at a first compression ratio, such as at least a 10 to 1 compression ratio.

[0006] The IMD may determine whether one or more features of the second physiological signal indicate an occurrence or pending occurrence of a particular medical condition, such as an arrhythmia. In response to a determination that the one or more features of the second physiological signal indicate an occurrence or a pending occurrence of a particular medication condition, the IMD may compress the second physiological signal at a second compression ratio, the second compression ratio being less than the first compression ratio.

[0007] The IMD may output the compressed first physiological signal and the compressed second physiological signal to a computing device for the computing device to apply the compressed first physiological signal and the compressed second physiological signal to a machine learning (ML) model, such as a deep neural network, to reconstruct the compressed first physiological signal and the compressed second physiological signal, e.g., to a reconstructed first physiological signal and a reconstructed second physiological signal. In some examples, the reconstructed first physiological signal may be a high-fidelity first physiological signal and the reconstructed second physiological signal may be a high-fidelity second physiological signal.

[0008] In some examples, using techniques as described in this disclosure to dynamically compress sensed physiological signals, such as an EGM signal, based on a determination of whether the physiological signals indicate an occurrence of a medical condition, such as an arrhythmia, may save power and / or memory of an IMD by compressing physiological signals at a high compression rates most of time (e.g., firstAtty Ref. No.: A0012899W001 physiological signals being compressed at a first compression ratio), but also achieve more reliable and acute reconstruction of physiological signals sensed during a medical condition by compressing physiological signals during a medical condition, such as an arrhythmia, (e.g. second physiological signals being compressed at a second compression ratio) at lower rate than the first physiological signals.

[0009] In one example, this disclosure describes a system comprising: a medical device comprising: one or more sensors configured to sense a physiological signal of a patient, the physiological signal including a first portion of the physiological signal and a second portion of physiological signal, the first portion of the physiological signal and the second portion of the physiological signal occurring during different periods of time; processing circuitry of the medical device, the processing circuitry configured to: compress the first portion of the physiological signal at a first compression ratio; determine an indication of an occurrence of a medical condition; and in response to the determination of the indication of an occurrence of the medical condition, compress the second portion of the physiological signal at a second compression ratio, the second compression ratio being less than the first compression ratio; and communication circuitry of the IMD, the communication circuitry configured to output the compressed first portion of the physiological signal and the compressed second portion of the physiological signal to a computing device.

[0010] In another example, this disclosure describes a method comprising: sensing a physiological signal of a patient, the physiological signal including a first portion of the physiological signal and a second portion of the physiological signal, the first portion of the physiological signal and the second portion of the physiological signal occurring during different periods of time compressing the first portion of the physiological signal at a first compression ratio; determining one or more features of the second portion of the physiological signal indicate an occurrence of a medical condition; and in response to the determination that the one or more features of the second portion of the physiological signal indicate an occurrence of a medical condition, compressing the second portion of the physiological signal at a second compression ratio, the second compression ratio being less than the first compression ratio.

[0011] The summary is intended to provide an overview of the subject matter described in this disclosure. It is not intended to provide an exclusive or exhaustiveAtty Ref. No.: A0012899W001 explanation of the systems, device, and methods described in detail within the accompanying drawings and description below. Further details of one or more examples of this disclosure are set forth in the accompanying drawings and in the description below. Other features, objects, and advantages will be apparent from the description and drawings, and from the claims.BRIEF DESCRIPTION OF THE DRAWINGS

[0012] FIG. 1 illustrates the environment of an example medical system in conjunction with a patient.

[0013] FIG. 2 is a functional block diagram illustrating an example configuration of the implantable medical device (IMD) of the medical system of FIG. 1.

[0014] FIG. 3 is a conceptual side-view diagram illustrating an example configuration of the IMD of FIGS. 1 and 2.

[0015] FIG. 4A is a conceptual perspective diagram illustrating an example configuration of the IMD of FIGS. 1-3.

[0016] FIG. 4B is a conceptual perspective diagram illustrating an example configuration of the IMD of FIGS. 1-3.

[0017] FIG. 5 is a functional block diagram illustrating an example configuration of the external device of FIGS. 1-4.

[0018] FIG. 6 is a block diagram illustrating an example system that includes an access point, a network, external computing devices, such as a server, and one or more other computing devices, which may be coupled to the IMD and external device of FIGS. 1-5.

[0019] FIGS. 7A-7C are graphs illustrating examples of dynamically compressing a sensed physiological signal.

[0020] FIG. 7D is a graph illustrating an example of segmenting a sensed physiological signal into segments.

[0021] FIG. 8 is a flow diagram illustrating an example technique for operating a system to dynamically compress sensed physiological signals and reconstruct the compressed physiological signals.

[0022] FIG. 9 is a conceptual diagram illustrating an example training process for an machine learning (ML) model, in accordance with examples of the current disclosure.Atty Ref. No.: A0012899W001

[0023] FIG. 10 is a conceptual diagram illustrating an example ML model configured to reconstruct compressed physiological signal(s) to high-fidelity physiological signal(s).

[0024] Like reference characters denote like elements throughout the description and figures.DETAILED DESCRIPTION

[0025] A variety of types of medical devices sense physiological signals such as cardiac EGMs, EEGs, electromyography (EMG) signals, heart sounds, respiration, blood pressure, temperature, mechanical motion, impedance signals, nerve signals or any of a number of other physiological signals or signals representative of physiological parameters of a patient. In some examples, cardiac EGMs may include electrocardiograms (ECGs or EKGs). Some medical devices that sense cardiac EGMs are non-invasive, e.g., using a plurality of electrodes placed in contact with external portions of the patient, such as at various locations on the skin of the patient. The electrodes used to monitor the cardiac EGM in these non-invasive processes may be attached to the patient using an adhesive, strap, belt, or vest, as examples, and electrically coupled to a monitoring device, such as an electrocardiograph, Holter monitor, or other electronic device. The electrodes are configured to sense electrical signals associated with the electrical activity of the heart or other cardiac tissue of the patient, and to provide these sensed electrical signals to the electronic device for further processing and / or display of the electrical signals. The non-invasive devices and methods may be utilized on a temporary basis, for example to monitor a patient during a clinical visit, such as during a doctor’s appointment, or for example for a predetermined period of time, for example for one day (twenty -four hours), or for a period of several days.

[0026] External devices that may be used to non-invasively sense and monitor cardiac EGMs include wearable devices with electrodes configured to contact the skin of the patient, such as patches, watches, or necklaces. One example of a wearable physiological monitor configured to sense a cardiac EGM is the SEEQ™ Mobile Cardiac Telemetry System, formerly available from Medtronic, Inc., of Minneapolis, Minnesota. Such external devices may facilitate relatively longer-term monitoring of patients during normal daily activities, and may periodically transmit collected data to a network service, such asAtty Ref. No.: A0012899W001 the Medtronic Carelink™ Network. Thus, the techniques described in any of the examples throughout this application may be utilized in external devices.

[0027] Some IMDs also sense and monitor cardiac EGMs. The electrodes used by HMDs to sense cardiac EGMs are typically integrated with a housing of the HMD and / or coupled to the HMD via one or more elongated leads. Example HMDs that monitor cardiac EGMs include pacemakers and implantable cardioverter-defibrillators, which may be coupled to intravascular or extravascular leads, as well as pacemakers with housings configured for implantation within the heart, which may be leadless. An example of pacemaker configured for intracardiac implantation is the Micra™ Transcatheter Pacing System, available from Medtronic, Inc. Some IMDs configured to sense cardiac EGMs may not provide therapy, e.g., implantable patient monitors. One example of such an IMD is the Reveal LINQ™ and LINQ II™ Insertable Cardiac Monitors (ICMs), available from Medtronic, Inc, which may be inserted subcutaneously. Such IMDs may facilitate relatively longer-term monitoring of patients during normal daily activities, and may periodically transmit collected data to a network service, such as the Medtronic Carelink™ Network. Thus, the techniques described in any of the examples throughout this application may be utilized in any of a number of HMDs.

[0028] In some examples, an IMD may sense one or more physiological signals of a patient and determine, based on physiological parameters of a sensed physiological signal of a patient, that the patient is experiencing or will experience a medical condition, such as an arrhythmia. The physiological signal(s) may include, but are not limited, an EGM signal, heart sound signal, accelerometer signal, an impedance signal, optical signal, EEG signal, EMG signal, and / or electrical signals in nerves of the patient. In some examples, the sensed physiological signals may indicate one or more of heart activity of the patient, blood pressure levels of the patient, oxygen saturation levels of the patient, nerve activity of the patient, or brain activity of the patient. IMD may compare values for one or more physiological parameters of the sensed physiological signal to threshold values corresponding to a medical condition and determine that the patient is experiencing or will experience the medical condition based on a determination that the physiological parameter value(s) of the sensed signal(s) satisfy the corresponding threshold value(s).

[0029] A limitation of IMDs is an amount of data that can be collected and transmitted, such as due to power or memory constraints, which may limit types, volumes,Atty Ref. No.: A0012899W001 and / or uses of data sensed by sensors of an IMD. In some examples, an IMD may compress sensed physiological signals at a compression ratio, such as at least a 10 to 1 compression ratio, to reduce power or memory usage.

[0030] In some examples, the IMD may be configured to transmit, via communication circuitry, compressed physiological signals to a computing device. In some examples, the computing device may be configured to receive the compressed physiological signals and apply the compressed physiological signals to a ML model, such as a deep neural network, to reconstruct the physiological signal, e.g., to a high-fidelity physiological signal.

[0031] As described herein, “normal operation physiological signals” may refer to sensed physiological signals that do not indicate a particular medical condition, such as an arrhythmia, is occurring or is about to occur. In some examples, normal operation physiological signals may include physiological signals that are highly compressible due to being able to be compressed at a high rate, such as at least a 10 to 1 compression ratio, and return reliable high-fidelity signals when the compressed signal is reconstructed. In some examples, physiological signals leading up to, during, and / or shortly after a particular medical condition, such as an EGM signal during atrial fibrillation or other atrial or ventricular tachyarrhythmia, may be referred to as “medical condition physiological signals.” In some examples, medical condition physiological signals may include physiological signals that are more chaotic, more variable, and / or more dense with morphological or other features of interest than normal operation physiological signals. In some examples, it may be more challenging to train a model to reconstruct medical condition physiological signals when compressed at a relatively higher rate, such as at least a 10 to 1 compression ratio, due to the above-discussed nature of the physiological signal during particular medical conditions, such as an EGM signal during tachyarrhythmia.

[0032] In accordance with techniques described herein, an IMD may be configured to dynamically compress sensed physiological signals, such as an EGM signal, based on a determination of whether the physiological signals indicate an occurrence of a medical condition, such as an arrhythmia, which may save power and / or memory by compressing physiological signals at a high compression rates most of time (e.g., during normal operation), but also achieve more reliable and acute reconstruction of medical conditionAtty Ref. No.: A0012899W001 physiological signals by compressing the medical condition physiological signals at lower rate than the normal operation physiological signals.

[0033] In some examples, a physiological signal may include a first physiological signal and a second physiological signal, where the first physiological signal and the second physiological signal occur during different periods of time, such as the second physiological signal occurring after the first physiological signal. In some examples, the first physiological signal may be a first portion of the physiological signal, and the second physiological signal may be a second portion of the physiological signal.

[0034] In some examples, IMD may compress a first physiological signal at a first compression ratio, such as at least a 10 to 1 compression ratio. In some examples, the first compression ratio may be based on sampling rate, such as IMD sensing a first physiological signal at a higher sampling rate may correspond to a first compression ratio being a higher compression ratio. In some examples, IMD 10 may dynamically compress the first physiological signal and a first compression ratio may correspond to a mean, median, or mode of the dynamic compressing of the first physiological signal. In some examples, IMD may determine whether the first physiological signal indicates an occurrence of or a pending occurrence of a particular medical condition of the patient (e.g., determine whether the first physiological signal is a medical condition physiological signal or a normal operation physiological signal). In some examples, in response to a determination that the first physiological signal does not indicate an occurrence or a pending occurrence of a medical condition of the patient (e.g., a determination that the first physiological signal is a normal operation signal), IMD may compress the first physiological signal at a first compression ratio. For example, in response first physiological signal may be a normal operation physiological signal and IMD may compress the normal operation physiological signal at a first compression ratio, such as at least a 10 to 1 compression ratio. In some examples, the first compression ratio may be at least a 20 to 1 compression ratio. In some examples, the first compression ratio may be at least a 50 to 1 compression ratio. The compression ratio may, in some instances, be selected based on sampling rate of IMD 10. Higher sampling rates may contain more redundant and highly compressible information. For a sampling rate of 128 Hz, IMD 10 may compress the normal operation physiological signal at a compression ratio of 10 to 1. HMDs using higher sampling rates may be compressed at higher ratios.Atty Ref. No.: A0012899W001

[0035] IMD 10 may compress the first physiological signal using any of a number of different compression techniques or combinations of compression techniques. For example, IMD may compress sensed physiological signals at a N to 1 compression ratio by storing only every Nth data sample of the physiological signal. In some examples, IMD 10 may randomly select which samples in time to take instead of every Nth sample. In some examples, IMD 10 may dynamically select points of the signal associated with information dense features of the signal (e.g., relevant complexes (QRS, P, and T portions) of an EGM). In this manner, an IMD 10 that senses an EGM signal could achieve the first compression ratio (e.g., N to 1 ratio) by selecting mores sample data points of an EGM signal near the P, QRS, and T portions and less sample data points of the remainder of the EGM signal.

[0036] In some examples, IMD may determine whether one or more features of the second physiological signal indicates an occurrence or a pending occurrence of a medical condition of the patient (e.g., determine whether the second physiological signal is a medical condition physiological signal or a normal operation physiological signal).

[0037] In some examples, based on a determination that the sensed physiological signal indicates an occurrence or a pending occurrence of a medical condition, IMD may compress the medical condition physiological signal at a second compression ratio, the second compression ratio being less than the first compression ratio. In some examples, IMD 10 may dynamically compress the second physiological signal, and a second compression ratio may correspond to a mean, median, or mode of the dynamic compressing of the second physiological signal. For example, during a period of time in which the sensed physiological signal, such as an EGM signal, during a particular period of time indicates a particular medical condition, such as an arrhythmia, processing circuitry of an IMD may be configured to compress the sensed physiological signal during the particular period of time at a lower compression ratio. In some examples, based on a determination that the physiological signal is a medical condition physiological signal, IMD may compress the medical condition physiological signal at a second compression ratio, the second compression ratio being less than the first compression ratio. In some examples, the second compression ratio is less than half of the first compression ratio. In some examples, the second compression ratio may be less than one-third of the first compression ratio. In some examples, the second compression ratio may be less than one-Atty Ref. No.: A0012899W001 quarter of the first compression ratio. In some examples, the second compression ratio may be less than one-tenth of the first compression ratio. For example, a first compression ratio may be at a 10 to 1 compression ratio while the second compression ratio may be at 2 to 1 ratio or the second compression ratio may be at a 1 to 1 ratio (e.g., the second physiological signal not being compressed). IMD 10 may compress the second physiological signal using any of a number of different compression techniques or combinations of compression techniques as described above.

[0038] IMD may be configured to dynamically compress sensed physiological signals, such as an EGM signal, based on a determination of whether the physiological signals indicate an occurrence or pending occurrence of a medical condition, such as an arrhythmia, which may save power and / or memory by compressing physiological signals at a high compression rates most of time (e.g., during normal operation), but also achieve more reliable and accurate reconstruction of medical condition physiological signals by compressing the medical condition physiological signals at lower rate than the normal operation physiological signals.

[0039] FIG. 1 illustrates the environment of an example medical system 2 in conjunction with a patient 4, in accordance with one or more techniques of this disclosure. The example techniques may be used with an IMD 10, which may be in wireless communication with at least one of external device 12 and other devices not pictured in FIG. 1. In some examples, IMD 10 is implanted outside of a thoracic cavity of patient 4 (e.g., subcutaneously in the pectoral location illustrated in FIG. 1). IMD 10 may be positioned near the sternum near or just below the level of the heart of patient 4, e.g., at least partially within the cardiac silhouette. IMD 10 includes a plurality of electrodes (not shown in FIG. 1), and is configured to sense a cardiac EGM via the plurality of electrodes. In some examples, IMD 10 takes the form of the Reveal LINQ™ or LINQ II ICM™, or another ICM similar to, e.g., a version or modification of, the LINQ™ ICMs.

[0040] External device 12 may be a computing device. For example, external device 12 may be a computing device with a display viewable by the user and an interface for providing input to external device 12 (i.e., a user input mechanism). In some examples, external device 12 may be a notebook computer, tablet computer, workstation, one or more servers, cellular phone, smartphone, personal digital assistant, or another computing device that may run an application that enables the computing device to interact with IMDAtty Ref. No.: A0012899W00110. External device 12 is configured to communicate with IMD 10 and, optionally, another computing device (not illustrated in FIG. 1), via wireless communication. External device 12, for example, may communicate via near-field communication technologies (e.g., inductive coupling, NFC or other communication technologies operable at ranges less than 10-20 cm) and far-field communication technologies (e.g., RF telemetry according to the 802.11 or Bluetooth® specification sets, or other communication technologies operable at ranges greater than near-field communication technologies).

[0041] In some examples, external device 12 may be or additionally include wearable computing device. A wearable computing device may include electrodes and other sensors to sense physiological signals of patient 4, and may collect and store physiological data and detect episodes based on such signals. Wearable computing device may be incorporated into the apparel of patient 4, such as within clothing, shoes, eyeglasses, a watch or wristband, a hat, etc. In some examples, a wearable device may be a smartwatch or other accessory or peripheral for external device 12, for example when external device 12 is a smartphone or tablet.

[0042] External device 12 may be used to receive compressed physiological signals (e.g., compressed and / or non-compressed signals) from IMD 10. External device 12 may apply the compressed physiological signal, such as a compressed first physiological signal and / or a compressed second physiological signal, to a ML model, such as a deep neural network, to reconstruct the physiological signal with a relatively high-fidelity to the precompressed physiological signal. For example, external device 12 may apply a compressed first physiological signal compressed at a first compression rate and apply a compressed second physiological signal compressed a second compression rate, the second compression rate being less than first compression rate, to a ML model to reconstruct the compressed first physiological signal and the compressed second physiological signal to a high-fidelity first physiological signal and a high-fidelity second physiological signal. As discussed in greater detail below with respect to FIG. 6, one or more computing devices may interact with IMD 10 in a manner similar to external device 12, e.g., to retrieve data from IMD 10, via a network.

[0043] In some examples, IMD 10 may include one or more sensors configured to sense a physiological signal of a patient, the physiological signal including a firstAtty Ref. No.: A0012899W001 physiological signal and a second physiological signal. In some examples, the first physiological signal and the second physiological signal occur during different periods of time. In some examples, the one or more sensors of IMD 10 may include a plurality of electrodes. In some examples, the physiological signal is an EGM signal of the patient, the first physiological signal is a first EGM signal, and the second physiological signal is a second EGM signal. In some examples, the physiological signal is a heart sound signal of the patient, the first physiological signal is a first heart sound signal, and the second physiological signal is a second heart sound signal. In some examples, the first heart sound signal is a first portion heart sound signal of the heart sound signal, and the second heart sound signal is a second portion of the heart sound signal.

[0044] In some examples, processing circuitry of IMD 10 may compress the first physiological signal at a first compression ratio. In some examples, processing circuitry of IMD 10 may determine whether one or more physiological parameters sensed by IMD 10 indicate an occurrence of a particular medical condition in patient 4. In some examples, processing circuitry of IMD 10 may determine whether an indication received from another device indicates an occurrence of a particular medical condition in patient 4. In some examples, processing circuitry of IMD 10 may determine whether one or more features of the first physiological signal indicate an occurrence of a particular medical condition. In some examples, in response to a determination that the first physiological signal does not indicate an occurrence or a pending occurrence of a particular medical condition, processing circuitry of IMD 10 may compress the first physiological signal at a first compression ratio. In some examples, in response to a determination that one or more physiological parameters sensed by IMD 10 does not indicate an occurrence or a pending occurrence of a particular medical condition during a particular period of time, processing circuitry of IMD 10 may compress the first physiological signal at a first compression ratio during the particular period of time. In some examples, the first compression ratio is at least a 10 to 1 compression ratio. In some examples, the medical condition includes a cardiac event. In some examples, the cardiac event includes an arrhythmia.

[0045] In some examples, processing circuitry of IMD 10 may determine whether one or more physiological parameters sensed by IMD 10 indicate an occurrence of a particular medical condition in patient 4. In some examples, in response to a determination that the one or more physiological parameters sensed by IMD 10 indicate an occurrence or aAtty Ref. No.: A0012899W001 pending occurrence of a particular medical condition, processing circuitry of IMD 10 may compress the second physiological signal at a second compression ratio, the second compression ratio being less than the first compression ratio. In some examples, the processing circuitry of IMD 10 may determine whether one or more features of the second physiological signal indicate an occurrence or pending occurrence of a particular medical condition. In some examples, in response to a determination that the one or more features of the second physiological signal indicate an occurrence or a pending occurrence of a particular medical condition, processing circuitry of IMD 10 may compress the second physiological signal at a second compression ratio, the second compression ratio being less than the first compression ratio. In some examples, the second compression ratio is less than half of the first compression ratio. In some examples, the second compression ratio may be at a 1 to 1 ratio (e.g., the second physiological signal not being compressed). In some examples, the second compression ratio being at a 1 to 1 ratio may include the second physiological signal not being compressed. In some examples, in response to a determination that the one or more physiological parameters sensed by IMD 10 indicate an occurrence or a pending occurrence of a particular medical condition, such as a fast arrhythmia, processing circuitry of IMD 10 may not compress the second physiological signal.

[0046] In some examples, communication circuitry of IMD 10 may output the compressed first physiological signal and the compressed second physiological signal to a computing device, such as external device 12. In some examples, external device 12 may be configured to receive the compressed first physiological signal and the compressed second physiological signal. In some examples, external device may be configured to apply the compressed first physiological signal and the compressed second physiological signal to a ML model to reconstruct the compressed first physiological signal and the compressed second physiological signal to a reconstructed first physiological signal and a reconstructed second physiological signal. In some examples, the reconstructed first physiological signal may be a high-fidelity first physiological signal and the reconstructed second physiological signal may be a high-fidelity second physiological signal. In some examples, a mean square error (MSE) or mean absolute error (MAE) may indicate a disparity between each predicted point in a reconstructed signal and a ground truth that corresponds to the original uncompressed signal. In some examples, a high-fidelityAtty Ref. No.: A0012899W001 reconstructed signal may be based, at least, on one or more of MSE or MAE satisfying a high-fidelity threshold (e.g., the disparity between each predicted point in a reconstructed signal and a ground truth being below a threshold).

[0047] In some examples, IMD 10 being configured to dynamically compress sensed physiological signals, such as an EGM signal, based on a determination of whether the physiological signals indicate an occurrence or pending occurrence of a medical condition, such as an arrhythmia, may help save power and / or memory by compressing physiological signals at a high compression rates most of time (e.g., during normal operation), while also achieving more reliable and accurate reconstruction of physiological signals during particular medical conditions, which results in an IMD 10 that has improved power and memory efficiency while providing compressed signals that may reconstructed with improved reliability and accuracy.

[0048] Although described in the context of examples in which IMD 10 that senses and compresses the physiological signal comprises an insertable cardiac monitor, example systems including one or more implantable or external devices of any type configured to sense a physiological signal may be configured to implement the techniques of this disclosure. In some examples, IMD 10 may also provide therapy, such as electrical stimulation therapy, drug therapy or other types of therapy. In some examples, the device that senses the physiological signal may be different device than the device that compresses the sensed physiological signal.

[0049] In some examples, IMD 10 may be configured to detect an indication of atrial fibrillation (AF) episodes and / or atrial tachycardia (AT) episodes based on the EGM signals. In some examples, IMD 10 may detect AF episodes and / or AT episodes as described in commonly assigned U.S. Publication No. 2022 / 0386930, the entire contents of which is incorporated herein by reference. For example, IMD 10 may detect an indication of an AF episode based on incoherence of RR intervals as well as evidence of single P-waves between two R- waves. In some examples, IMD 10 may be able to detect other tachyarrhythmias based on the cardiac EGM signals, including ventricular tachyarrhythmias (e.g., ventricular tachycardia (VT) or ventricular fibrillation (VF)).

[0050] FIG. 2 is a functional block diagram illustrating an example configuration of IMD 10 of FIG. 1 in accordance with one or more techniques described herein. In the illustrated example, IMD 10 includes electrodes 16A and 16B (collectively “electrodesAtty Ref. No.: A0012899W00116”), antenna 26, processing circuitry 50, sensing circuitry 52, communication circuitry 54, storage device 56, switching circuitry 58, sensors 62, and heart sound sensor(s) 62A. Although the illustrated example includes two electrodes 16, IMDs including or coupled to more than two electrodes 16 may implement the techniques of this disclosure in some examples.

[0051] Processing circuitry 50 may include fixed function circuitry and / or programmable processing circuitry. Processing circuitry 50 may include any one or more of a microprocessor, a controller, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or equivalent discrete or analog logic circuitry. In some examples, processing circuitry 50 may include multiple components, such as any combination of one or more microprocessors, one or more controllers, one or more DSPs, one or more ASICs, or one or more FPGAs, as well as other discrete or integrated logic circuitry. The functions attributed to processing circuitry 50 herein may be embodied as software, firmware, hardware or any combination thereof.

[0052] Sensing circuitry 52 may be selectively coupled to electrodes 16 via switching circuitry 58, e.g., to select the electrodes 16 and polarity, referred to as the sensing vector, used to sense a cardiac EGM, as controlled by processing circuitry 50. Sensing circuitry 52 may sense signals from electrodes 16, e.g., to produce a cardiac EGM, in order to facilitate monitoring the electrical activity of the heart. Sensing circuitry 52 may include components / modules for converting the raw EGM signal to a processed EGM signal that can be analyzed to detect sense events. Sensing circuitry 52 also may monitor signals from sensors 62, such as heart sound sensor(s) 62A or optical sensor. In some examples, heart sound sensor(s) 62A may be configured to sense cardiac vibrations. In some examples, heart sound sensor(s) 62A may include one or more accelerometers. In some examples, heart sound sensor(s) 62A may additionally or alternatively include one or more microphones and / or other vibration / motion sensors. Sensing circuitry 52 may receive raw cardiac vibrations monitored by heart sound sensors 62A. Sensing circuitry 52 may include components / modules for converting the raw cardiac vibrations to a processed heart sound beat signal that can be analyzed to detect sense events. In some examples, processing circuitry 50 may use signals received from sensors 62, including heart sound beat signals sensed by heart sound sensor(s) 62A, alternatively or in addition to a sensed cardiac EGM signal, to determine a medical condition. In some examples, sensingAtty Ref. No.: A0012899W001 circuitry 52 may include one or more filters and amplifiers for filtering and amplifying signals received from electrodes 16 and / or sensors 62.

[0053] Sensing circuitry 52 and / or processing circuitry 50 may be configured to detect cardiac depolarizations (e.g., P-waves of atrial depolarizations or R-waves of ventricular depolarizations) when the cardiac EGM amplitude crosses a sensing threshold. A cardiac EGM may include P-waves (depolarization of the atria), R-waves (depolarization of the ventricles), and T-waves (repolarization of the ventricles), among other events. Sensing circuitry 52 and / or processing circuitry 50 may be configured to detect one or more features of the P-waves, R-waves, and / or T-waves in a cardiac EGM. For cardiac depolarization detection, sensing circuitry 52 may include a rectifier, filter, amplifier, comparator, and / or analog-to-digital converter, in some examples. In some examples, sensing circuitry 52 may output an indication to processing circuitry 50 in response to sensing of a cardiac depolarization. In this manner, processing circuitry 50 may receive detected cardiac depolarization indicators corresponding to the occurrence of detected R-waves and P-waves in the respective chambers of heart. Processing circuitry 50 may use the indications of detected R-waves and P-waves for determining inter-depolarization intervals, heart rate, and detecting arrhythmias, such as tachyarrhythmias and asystole.

[0054] Sensing circuitry 52 may also provide one or more digitized EGM signals and / or heart sound beat signals to processing circuitry 50 for analysis, e.g., for use in cardiac rhythm discrimination. Sensing circuitry 52 may include one or more detection channels, each of which may include an amplifier. The detection channels may be used to sense cardiac signals, such as a cardiac EGM. Some detection channels may detect events, such as R-waves, P-waves, and T-waves and provide indications of the occurrences of such events to processing circuitry 50. One or more other detection channels may provide the signals to an analog-to-digital converter, for conversion into a digital signal for processing or analysis by processing circuitry 50. In some examples, processing circuitry 50 and / or sensing circuitry may store sensed cardiac signals, such as a digitized EGM signals, in storage device 56. In some examples, processing circuitry 50 may compress the digitized EGM signals, such as the digitized EGM signals stored in storage device 56, according to techniques described in this disclosure, and communication circuitry 54 may transmit the compressed digitized EGM signals to an external device, such as external device 12.Atty Ref. No.: A0012899W001

[0055] Communication circuitry 54 may include any suitable hardware, firmware, software or any combination thereof for communicating with another device, such as external device 12, another networked computing device, or another IMD or sensor. Under the control of processing circuitry 50, communication circuitry 54 may receive downlink telemetry from, as well as send uplink telemetry to external device 12 or another device with the aid of an internal or external antenna, e.g., antenna 26. In addition, processing circuitry 50 may communicate with a networked computing device via an external device (e.g., external device 12) and a computer network, such as the Medtronic CareLink™ Network. Antenna 26 and communication circuitry 54 may be configured to transmit and / or receive signals via inductive coupling, electromagnetic coupling, Near Field Communication (NFC), Radio Frequency (RF) communication, Bluetooth, WiFi, or other proprietary or non-proprietary wireless communication schemes.

[0056] In some examples, storage device 56 includes computer-readable instructions that, when executed by processing circuitry 50, cause IMD 10 and processing circuitry 50 to perform various functions attributed to IMD 10 and processing circuitry 50 herein. Storage device 56 may include any volatile, non-volatile, magnetic, optical, or electrical media, such as a random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), electrically-erasable programmable ROM (EEPROM), flash memory, or any other digital media. Storage device 56 may store, as examples, programmed values for one or more operational parameters of IMD 10 and / or data collected by IMD 10 for transmission to another device using communication circuitry 54. Data stored by storage device 56 and transmitted by communication circuitry 54 to one or more other devices may include digitized EGM signals, and / or digitized heart sound beat signals, as examples.

[0057] In some examples, processing circuitry 50 may compress the first physiological signal at a first compression ratio. In some examples, processing circuitry 50 may determine whether one or more features of the first physiological signal indicate an occurrence of a particular medical condition. In some examples, in response to a determination that the first physiological signal does not indicate an occurrence or a pending occurrence of a particular medical condition, processing circuitry 50 may compress the first physiological signal at a first compression ratio. In some examples, the first compression ratio is at least a 10 to 1 compression ratio. In some examples, theAtty Ref. No.: A0012899W001 medical condition includes a cardiac event. In some examples, the cardiac event includes an arrhythmia.

[0058] In some examples, the processing circuitry 50 may determine whether one or more features of the second physiological signal indicate an occurrence or pending occurrence of a particular medical condition. In some examples, in response to a determination that the one or more features of the second physiological signal indicate an occurrence or a pending occurrence of a particular medication condition, processing circuitry 50 may compress the second physiological signal at a second compression ratio, the second compression ratio being less than the first compression ratio. In some examples, the second compression ratio is less than half of the first compression ratio. In some examples, communication circuitry 54 may output the compressed first physiological signal and the compressed second physiological signal to a computing device.

[0059] FIG. 3 is a conceptual side-view diagram illustrating an example configuration of IMD 10 of FIGS. 1 and 2. In the example shown in FIG. 3, IMD 10 may include a leadless, subcutaneously-implantable monitoring device having a housing 15 and an insulative cover 76. Electrode 16A and electrode 16B may be formed or placed on an outer surface of cover 76. Circuitries 50-62, described above with respect to FIG. 2, may be formed or placed on an inner surface of cover 76, or within housing 15. In the illustrated example, antenna 26 is formed or placed on the inner surface of cover 76, but may be formed or placed on the outer surface in some examples. In some examples, one or more of sensors 62 may be formed or placed on the outer surface of cover 76. In some examples, insulative cover 76 may be positioned over an open housing 15 such that housing 15 and cover 76 enclose antenna 26 and circuitries 50-62, and protect the antenna and circuitries from fluids such as body fluids.

[0060] One or more of antenna 26 or circuitries 50-62 may be formed on the inner side of insulative cover 76, such as by using flip-chip technology. Insulative cover 76 may be flipped onto a housing 15. When flipped and placed onto housing 15, the components of IMD 10 formed on the inner side of insulative cover 76 may be positioned in a gap 78 defined by housing 15. Electrodes 16 may be electrically connected to switching circuitry 58 through one or more vias (not shown) formed through insulative cover 76. Insulative cover 76 may be formed of sapphire (i.e., corundum), glass, parylene, and / or any otherAtty Ref. No.: A0012899W001 suitable insulating material. Housing 15 may be formed from titanium or any other suitable material (e.g., a biocompatible material). Electrodes 16 may be formed from any of stainless steel, titanium, platinum, iridium, or alloys thereof. In addition, electrodes 16 may be coated with a material such as titanium nitride or fractal titanium nitride, although other suitable materials and coatings for such electrodes may be used.

[0061] FIG. 4A is a conceptual drawing illustrating an IMD 10A, which may be an example configuration of IMD 10 of FIGS. 1-3 as an ICM. In the example shown in FIG. 4A, IMD 10A may be embodied as a monitoring device having housing 15, proximal electrode 16A and distal electrode 16B. Housing 15 may further comprise first major surface 14, second major surface 18, proximal end 20, and distal end 22. Housing 15 encloses electronic circuitry located inside the IMD 10A and protects the circuitry contained therein from body fluids. Electrical feedthroughs provide electrical connection of electrodes 16A and 16B.

[0062] In the example shown in FIG. 4A, IMD 10A is defined by a length / ., a width W and thickness or depth D and is in the form of an elongated rectangular prism wherein the length L is much larger than the width W, which in turn is larger than the depth D. In one example, the geometry of the IMD 10A - in particular a width W greater than the depth D - is selected to allow IMD 10A to be inserted under the skin of the patient using a minimally invasive procedure and to remain in the desired orientation during and after insertion. For example, the device shown in FIG. 4 A includes radial asymmetries (notably, the rectangular shape) along the longitudinal axis that maintains the device in the proper orientation following insertion. For example, the spacing between proximal electrode 64 and distal electrode 66 may range from 30 millimeters (mm) to 55mm, 35mm to 55mm, and from 40mm to 55mm and may be any range or individual spacing from 25mm to 60mm. In addition, IMD 10A may have a length L that ranges from 30mm to about 70mm. In other examples, the length L may range from 5mm to 60mm, 15mm to 50mm, 40mm to 60mm, 45mm to 60mm and may be any length or range of lengths between about 5mm and about 80mm. In addition, the width W of major surface 14 may range from 5mm to 15mm, 3mm to 10mm, and may be any single or range of widths between 3mm and 15mm. The thickness of depth D of IMD 10A may range from 2mm to 9mm. In other examples, the depth D of IMD 10A may range from 2mm to 5mm, may range from 5mm to 15mm, and may be any single or range of depths from 2mm to 15mm.Atty Ref. No.: A0012899W001In addition, IMD 10A according to an example of the present disclosure is has a geometry and size designed for ease of implant and patient comfort. Examples of IMD 10A described in this disclosure may have a volume of three cubic centimeters (cm) or less, 1.5 cubic cm or less or any volume between three and 1.5 cubic cm.

[0063] In the example shown in FIG. 4A, once inserted within the patient, the first major surface 14 faces outward, toward the skin of the patient while the second major surface 18 is located opposite the first major surface 14. In addition, in the example shown in FIG. 4 A, proximal end 20 and distal end 22 are rounded to reduce discomfort and irritation to surrounding tissue once inserted under the skin of the patient. IMD 10A, including instrument and method for inserting IMD 10 is described, for example, in U.S. Patent Publication No. 2014 / 0276928, incorporated herein by reference in its entirety.

[0064] Proximal electrode 16A and distal electrode 16B are used to sense cardiac signals, e.g. EGM signals, intra-thoracically or extra-thoracically, which may be sub- muscularly or subcutaneously. EGM signals may be stored in a memory of IMD 10A, and data may be transmitted via integrated antenna 30 A to another medical device, which may be another implantable device or an external device, such as external device 12. In some example, electrodes 16A and 16B may additionally or alternatively be used for sensing any bio-potential signal of interest, which may be, for example, an ECG, EGM, EEG, EMG, or a nerve signal, from any implanted location.

[0065] In the example shown in FIG. 4A, proximal electrode 16A is in close proximity to the proximal end 20 and distal electrode 16B is in close proximity to distal end 22. In this example, distal electrode 16B is not limited to a flattened, outward facing surface, but may extend from first major surface 14 around rounded edges 24 and / or end surface 25 and onto the second major surface 18 so that the electrode 16B has a three-dimensional curved configuration. In some examples, electrode 16B is an uninsulated portion of a metallic, e.g., titanium, part of housing 15.

[0066] In the example shown in FIG. 4A, proximal electrode 16A is located on first major surface 14 and is substantially flat, and outward facing. However, in other examples proximal electrode 16A may utilize the three dimensional curved configuration of distal electrode 16B, providing a three dimensional proximal electrode (not shown in this example). Similarly, in other examples distal electrode 16B may utilize aAtty Ref. No.: A0012899W001 substantially flat, outward facing electrode located on first major surface 14 similar to that shown with respect to proximal electrode 16 A.

[0067] The various electrode configurations allow for configurations in which proximal electrode 16A and distal electrode 16B are located on both first major surface 14 and second major surface 18. In other configurations, such as that shown in FIG. 4 A, only one of proximal electrode 16A and distal electrode 16B is located on both major surfaces 14 and 18, and in still other configurations both proximal electrode 16A and distal electrode 16B are located on one of the first major surface 14 or the second major surface 18 (e.g., proximal electrode 16A located on first major surface 14 while distal electrode 16B is located on second major surface 18). In another example, IMD 10A may include electrodes on both major surface 14 and 18 at or near the proximal and distal ends of the device, such that a total of four electrodes are included on IMD 10 A. Electrodes 16A and 16B may be formed of a plurality of different types of biocompatible conductive material, e.g. stainless steel, titanium, platinum, iridium, or alloys thereof, and may utilize one or more coatings such as titanium nitride or fractal titanium nitride.

[0068] In the example shown in FIG. 4A, proximal end 20 includes a header assembly 28 that includes one or more of proximal electrode 16A, integrated antenna 30A, antimigration projections 32, and / or suture hole 34. Integrated antenna 30A is located on the same major surface (i.e., first major surface 14) as proximal electrode 16A and is also included as part of header assembly 28. Integrated antenna 30A allows IMD 10A to transmit and / or receive data. In other examples, integrated antenna 30A may be formed on the opposite major surface as proximal electrode 16 A, or may be incorporated within the housing 15 of IMD 10A. In the example shown in FIG. 4 A, anti-migration projections 32 are located adjacent to integrated antenna 30A and protrude away from first major surface 14 to prevent longitudinal movement of the device. In the example shown in FIG. 4A, anti-migration projections 32 include a plurality (e.g., nine) small bumps or protrusions extending away from first major surface 14. As discussed above, in other examples anti -migration projections 32 may be located on the opposite major surface as proximal electrode 16A and / or integrated antenna 30A. In addition, in the example shown in FIG. 4A, header assembly 28 includes suture hole 34, which provides another means of securing IMD 10A to the patient to prevent movement following insertion. In the example shown, suture hole 34 is located adjacent to proximal electrode 16A. In one example,Atty Ref. No.: A0012899W001 header assembly 28 is a molded header assembly made from a polymeric or plastic material, which may be integrated or separable from the main portion of IMD 10A.

[0069] FIG. 4B is a perspective drawing illustrating another IMD 10B, which may be another example configuration of IMD 10 from FIGS. 1-3. IMD 10B of FIG. 4B may be configured substantially similarly to IMD 10A of FIG. 4A, with differences between them discussed herein.

[0070] IMD 10B may include a leadless, subcutaneously-implantable monitoring device, e.g. an ICM. IMD 10B includes housing having a base 40 and an insulative cover 42. Proximal electrode 16C and distal electrode 16D may be formed or placed on an outer surface of cover 42. Various circuitries and components of IMD 10B, e.g., described below with respect to FIG. 3, may be formed or placed on an inner surface of cover 42, or within base 40. In some examples, a battery or other power source of IMD 10B may be included within base 40. In the illustrated example, antenna 30B is formed or placed on the outer surface of cover 42, but may be formed or placed on the inner surface in some examples. In some examples, insulative cover 42 may be positioned over an open base 40 such that base 40 and cover 42 enclose the circuitries and other components and protect them from fluids such as body fluids.

[0071] Circuitries and components may be formed on the inner side of insulative cover 42, such as by using flip-chip technology. Insulative cover 42 may be flipped onto a base 40. When flipped and placed onto base 40, the components of IMD 10B formed on the inner side of insulative cover 42 may be positioned in a gap 44 defined by base 40. Electrodes 16C and 16D and antenna 30B may be electrically connected to circuitry formed on the inner side of insulative cover 42 through one or more vias (not shown) formed through insulative cover 42. Insulative cover 42 may be formed of sapphire (i.e., corundum), glass, parylene, and / or any other suitable insulating material. Base 40 may be formed from titanium or any other suitable material (e.g., a biocompatible material). Electrodes 16C and 16D may be formed from any of stainless steel, titanium, platinum, iridium, or alloys thereof. In addition, electrodes 16C and 16D may be coated with a material such as titanium nitride or fractal titanium nitride, although other suitable materials and coatings for such electrodes may be used.

[0072] In the example shown in FIG. 4B, the housing of IMD 10B defines a length / ., a width W and thickness or depth D and is in the form of an elongated rectangular prismAtty Ref. No.: A0012899W001 wherein the length L is much larger than the width W, which in turn is larger than the depth D, similar to IMD 10A of FIG. 4B. For example, the spacing between proximal electrode 64 and distal electrode 66 may range from 30mm to 50mm, from 35mm to 45mm, or be approximately 40mm. In addition, IMD 10B may have a length L that ranges from 30mm to about 70mm. In other examples, the length L may range from 5mm to 60mm, 40mm to 60mm, 45mm to 55mm, or be approximately 45mm. In addition, the width may range from 3mm to 15mm, such as approximately 8mm. The thickness of depth D of IMD 10B may range from 2mm to 15mm, from 3 to 5mm, or be approximately 4mm. IMD 10B may have a volume of three cubic centimeters (cm) or less, or 1.5 cubic cm or less, such as approximately 1.4 cubic cm.

[0073] In the example shown in FIG. 4B, once inserted subcutaneously within the patient, outer surface of cover 42 faces outward, toward the skin of the patient. In addition, as shown in FIG. 4B, proximal end 46 and distal end 48 are rounded to reduce discomfort and irritation to surrounding tissue once inserted

[0074] FIG. 5 is a block diagram illustrating an example configuration of components of external device 12. In the example of FIG. 5, external device 12 includes processing circuitry 80, communication circuitry 82, storage device 84, and user interface 86.

[0075] Processing circuitry 80 may include one or more processors that are configured to implement functionality and / or process instructions for execution within external device 12. For example, processing circuitry 80 may be capable of processing instructions stored in storage device 84. Processing circuitry 80 may include, for example, microprocessors, DSPs, ASICs, FPGAs, or equivalent discrete or integrated logic circuitry, or a combination of any of the foregoing devices or circuitry. Accordingly, processing circuitry 80 may include any suitable structure, whether in hardware, software, firmware, or any combination thereof, to perform the functions ascribed herein to processing circuitry 80.

[0076] Communication circuitry 82 may include any suitable hardware, firmware, software or any combination thereof for communicating with another device, such as IMD 10. Under the control of processing circuitry 80, communication circuitry 82 may receive downlink telemetry from, as well as send uplink telemetry to, IMD 10, or another device. Communication circuitry 82 may be configured to transmit or receive signals via inductive coupling, electromagnetic coupling, Near Field Communication (NFC), Radio Frequency (RF) communication, Bluetooth, WiFi, or other proprietary or non-proprietary wirelessAtty Ref. No.: A0012899W001 communication schemes. Communication circuitry 82 may also be configured to communicate with devices other than IMD 10 via any of a variety of forms of wired and / or wireless communication and / or network protocols.

[0077] Storage device 84 may be configured to store information within external device 12 during operation. Storage device 84 may include a computer-readable storage medium or computer-readable storage device. In some examples, storage device 84 includes one or more of a short-term memory or a long-term memory. Storage device 84 may include, for example, RAM, DRAM, SRAM, magnetic discs, optical discs, flash memories, or forms of EPROM or EEPROM. In some examples, storage device 84 is used to store data indicative of instructions for execution by processing circuitry 80. Storage device 84 may be used by software or applications running on external device 12 to temporarily store information during program execution. In some examples, storage device 84 may store a ML model, such as ML model 85.

[0078] Data exchanged between external device 12 and IMD 10 may include operational parameters. External device 12 may transmit data including computer readable instructions which, when implemented by IMD 10, may control IMD 10 to change one or more operational parameters and / or export collected data. For example, processing circuitry 80 may transmit an instruction to IMD 10 which requests IMD 10 to export collected data (e.g., compressed physiological signals, such as compressed first physiological signal and compressed second physiological signal) to external device 12. In turn, external device 12 may receive the collected data from IMD 10 and store the collected data in storage device 84. Processing circuitry 80 may implement any of the techniques described herein to apply the compressed first physiological signal and the compressed second physiological signal to ML model 85, such as a deep neural network, to reconstruct the compressed first physiological signal and the compressed second physiological signal to a high-fidelity first physiological signal and a high-fidelity second physiological signal.

[0079] A user, such as a clinician or patient 4, may interact with external device 12 through user interface 86. User interface 86 includes a display (not shown), such as a liquid crystal display (LCD) or a light emitting diode (LED) display or other type of screen, with which processing circuitry 80 may present information related to IMD 10, e.g., reconstructed high-fidelity first physiological signal and a high-fidelity secondAtty Ref. No.: A0012899W001 physiological signal. In addition, user interface 86 may include an input mechanism to receive input from the user. The input mechanisms may include, for example, any one or more of buttons, a keypad (e.g., an alphanumeric keypad), a peripheral pointing device, a touch screen, or another input mechanism that allows the user to navigate through user interfaces presented by processing circuitry 80 of external device 12 and provide input. In other examples, user interface 86 also includes audio circuitry for providing audible notifications, instructions or other sounds to the user, receiving voice commands from the user, or both.

[0080] FIG. 6 is a block diagram illustrating an example system that includes an access point 90, a network 92, external computing devices, such as a server 94, and one or more other computing devices 100A-100N (collectively, “computing devices 100”), which may be coupled to IMD 10 and external device 12 via network 92, in accordance with one or more techniques described herein. In this example, IMD 10 may use communication circuitry 54 to communicate with external device 12 via a first wireless connection, and to communicate with an access point 90 via a second wireless connection. In the example of FIG. 6, access point 90, external device 12, server 94, and computing devices 100 are interconnected and may communicate with each other through network 92.

[0081] Access point 90 may include a device that connects to network 92 via any of a variety of connections, such as telephone dial-up, digital subscriber line (DSL), or cable modem connections. In other examples, access point 90 may be coupled to network 92 through different forms of connections, including wired or wireless connections. In some examples, access point 90 may be a user device, such as a tablet or smartphone, that may be co-located with the patient. IMD 10 may be configured to transmit data, such as compressed physiological signals (e.g., compressed first physiological signal and compressed second physiological signal) to access point 90. Access point 90 may then communicate the retrieved data to server 94 via network 92. In some examples, access point 90 may be external device 12 or configured to provide the functionality ascribed to external device 12 herein, e.g., with respect to receipt and reconstruction of compressed physiological signals.

[0082] In some cases, server 94 may be configured to provide a secure storage site for data that has been collected from IMD 10 and / or external device 12. In some cases, serverAtty Ref. No.: A0012899W00194 may assemble data in web pages or other documents for viewing by trained professionals, such as clinicians, via computing devices 100. One or more aspects of the illustrated system of FIG. 6 may be implemented with general network technology and functionality, which may be similar to that provided by the Medtronic CareLink™ Network. In some examples, server 94 may communicate with computing device 100 via network 92. For example, server 94 may communicate an analysis of data, such as analysis of a reconstructed high-fidelity first physiological signal and high-fidelity second physiological signal, to computing device 100, external device 12, or any other computing device via network 92.

[0083] In some examples, one or more of computing devices 100 may be a tablet or other smart device located with a clinician, by which the clinician may program, receive alerts from, and / or interrogate IMD 10. For example, the clinician may access data collected by IMD 10 through a computing device 100, such as when patient 4 is in in between clinician visits, to check on a status of a medical condition. In some examples, the clinician may enter instructions for a medical intervention for patient 4 into an application executed by computing device 100, such as based on a status of a patient condition determined by IMD 10, external device 12, server 94, or any combination thereof, or based on other patient data known to the clinician. Device 100 then may transmit the instructions for medical intervention to another of computing devices 100 located with patient 4 or a caregiver of patient 4. For example, such instructions for medical intervention may include an instruction to change a drug dosage, timing, or selection, to schedule a visit with the clinician, or to seek medical attention. In further examples, a computing device 100 may generate an alert to patient 4 based on a status of a medical condition of patient 4, which may enable patient 4 proactively to seek medical attention prior to receiving instructions for a medical intervention. In this manner, patient 4 may be empowered to take action, as needed, to address his or her medical status, which may help improve clinical outcomes for patient 4.

[0084] In the example illustrated by FIG. 6, server 94 includes a storage device 96, e.g., to store data retrieved from IMD 10, and processing circuitry 98. Although not illustrated in FIG. 6 computing devices 100 may similarly include a storage device and processing circuitry. Processing circuitry 98 may include one or more processors that are configured to implement functionality and / or process instructions for execution withinAtty Ref. No.: A0012899W001 server 94. For example, processing circuitry 98 may be capable of processing instructions stored in storage device 96. In some examples, storage device 96 may comprise a memory. Processing circuitry 98 may include or be coupled to communication circuitry that may include any suitable hardware, firmware, software or any combination thereof for communicating with another device. In some examples, a description of processing circuitry 98 outputting a signal, such as a classification, may include processing circuitry 98 causing communication circuitry of server 94 to output the signal. Processing circuitry 98 may include, for example, microprocessors, DSPs, ASICs, FPGAs, or equivalent discrete or integrated logic circuitry, or a combination of any of the foregoing devices or circuitry. Accordingly, processing circuitry 98 may include any suitable structure, whether in hardware, software, firmware, or any combination thereof, to perform the functions ascribed herein to processing circuitry 98. Processing circuitry 98 of server 94 and / or the processing circuity of computing devices 100 may implement any of the techniques described herein to apply the compressed first physiological signal and the compressed second physiological signal to ML model 85 to reconstruct the compressed first physiological signal and the compressed second physiological signal to a high-fidelity first physiological signal and a high-fidelity second physiological signal.

[0085] Storage device 96 may include a computer-readable storage medium or computer-readable storage device. In some examples, storage device 96 includes one or more of a short-term memory or a long-term memory. Storage device 96 may include, for example, RAM, DRAM, SRAM, magnetic discs, optical discs, flash memories, or forms of EPROM or EEPROM. In some examples, storage device 96 is used to store data indicative of instructions for execution by processing circuitry 98. In some examples, storage device 96 may store a ML model, such as ML model 85.

[0086] FIGS. 7A-7C show examples of processing circuitry 50 of HMD 10 dynamically compressing a sensed physiological signal, such as a cardiac EGM signal. For example, in FIG. 7A, IMD 10 is configured to sense physiological signal 700. In some examples, physiological signal 700 may be a cardiac EGM signal. In some examples, processing circuitry 50 of IMD 10 may determine an occurrence of a medical condition, such as an arrhythmia, that may occur between the event onset 712 and the event offset 722. In some examples, the first physiological signal 710 may refer to the sensed physiological signal before event onset 712. In some examples, the second physiologicalAtty Ref. No.: A0012899W001 signal 715 may refer to the sensed physiological signal after the event onset 712. In some examples, the second physiological signal 715 may refer to the sensed physiological signal between the event onset 712 and the event offset 722.

[0087] FIG. 7C shows an example of a sensed physiological signal 700 that is similar to the sensed physiological signal 700 as shown in FIG. 7A. In some examples, as shown in FIG. 7C, the second physiological signal 715 may refer to the sensed physiological signal from a period of time T1 before the event onset 712 to a period of time T2 after the event offset 722. In some examples, the second physiological signal 715 may refer to the sensed physiological signal from a period of time T1 before the event onset 712 to a period of time before the event offset 722. In some examples, the second physiological signal 715 may refer to the sensed physiological signal from a period of time T1 before the event onset 712 to the event offset 722. In some examples, the period of time T1 before the event onset 712 may be based on the particular medical condition that is determined. In some examples, the period of time before or after T2 the event offset 722 may be based on the particular medical condition that is determined. In some examples, the second physiological signal 715 may refer to a portion of time of the physiological signal in which that particular portion of time of the physiological signal indicates a medical condition, such as AF.

[0088] In some examples, processing circuitry 50 of IMD 10 may be configured to compress the physiological signal 700 at a particular compression ratio 730. For example, processing circuitry 50 of IMD 10 may be configured to compress the first physiological signal 710 at a first compression ratio 732 and be configured to compress the second physiological signal 720 at a second compression ratio 734. As shown in FIG. 7A, the second compression ratio 734 is less than the first compression ratio 732. In some examples, the first compression ratio 732 is at least a 10 to 1 compression ratio. In some examples, the first compression ratio 732 is at least a 20 to 1 compression ratio. In some examples, the first compression ratio 732 is at least a 50 to 1 compression ratio.

[0089] In some examples, after event offset 722, processing circuitry 50 of IMD 10 may compress the physiological signal at a third compression ratio 736. The third compression ratio is greater than the second compression ratio. In some examples, the third compression ratio may be equivalent to the first compression ratio. In some examples, communication circuitry 54 may output an indication of a value of the firstAtty Ref. No.: A0012899W001 compression ratio 732, a value of the second compression ratio 734, and / or a value of the third compression ratio 736.

[0090] FIG. 7A also shows a transmitted sampling rate 740 of the compressed physiological signal. For example, the higher the compression ratio of the physiological signal, the lower the sampling rate will be of the transmitted signal. For example, the first transmitted sampling rate 742 of the first physiological signal 710 is lower than the second transmitted sampling rate 744 of the second physiological signal 715. In some examples, after event offset 722, processing circuitry 50 may transmit the compressed physiological signal at third transmitted sampling rate 746. In some examples, the third transmitted sampling rate 746 of the physiological signal is lower than the second transmitted sampling rate 744 of the second physiological signal 715. In some examples, a transmitted sampling rate may indicate a value of a corresponding compression ratio. In some examples, communication circuitry 54 may output an indication of first transmitted sampling rate 742, second transmitted sampling rate 744, and / or third transmitted sampling rate 746 which may respectively correspond to a value of the first compression ratio 732, a value of the second compression ratio 734, and a value of the third compression ratio 736.

[0091] In some examples, medical condition physiological signals may include physiological signals that are more chaotic, more variable, and / or more dense with morphological or other features of interest than normal operation physiological signals. During such events, such as second physiological signal 715, compressing the physiological signal at a lower compression ratio, such as second compression ratio 734, leads to outputting the physiological signal during a medical condition at a higher sampling rate, which may help improve the accuracy of the reconstruction of the physiological signal.

[0092] FIG. 7B shows an example of a sensed physiological signal 700 that is similar to the sensed physiological signal 700 as shown in FIG. 7A. In some examples, physiological signal 700 may be a cardiac EGM signal. In some examples, processing circuitry 50 of IMD 10 may determine an occurrence of a medical condition, such as an arrhythmia, that may occur between the event onset 712 and the event offset 722. In some examples, the first physiological signal 710 may refer to the sensed physiological signal before event onset 712. In some examples, the second physiological signal 715 may referAtty Ref. No.: A0012899W001 to the sensed physiological signal after the event onset 712. In some examples, the second physiological signal 715 may refer to the sensed physiological signal between the event onset 712 and the event offset 722. In some examples, processing circuitry 50 of IMD 10 may be configured to compress the physiological signal 700 at a particular compression ratio 730. For example, processing circuitry 50 of IMD 10 may be configured to compress the first physiological signal 710 at a first compression ratio 732 that comprises a first staggered compression ratio 732A and a second staggered compression ratio 732B, the second staggered compression ratio 732B being less than the first staggered compression ratio 732A. As shown in FIG. 7B, the second staggered compression ratio 732B may be closer in time to the event onset 712 than the first staggered compression ratio 732A is to the event onset 712. Processing circuitry 50 of IMD 10 may be configured to compress the second physiological signal 720 at a second compression ratio 734. As shown in FIG. 7B, the second compression ratio 734 is less than the first staggered compression ratio 732A and the second staggered compression ratio 732B. As shown in FIG. 7B, a value of the second staggered compression ratio 732B is between the first staggered compression ratio 732A and the second compression ratio 734. In some examples, communication circuitry 54 may output an indication of a value of the first staggered compression ratio 732A, a value of the second staggered compression ratio 732B, and / or a value of the second compression ratio 734.

[0093] FIG. 7B shows a transmitted sampling rate 740 of the compressed physiological signal. For example, the higher the compression ratio of the physiological signal, the lower the sampling rate will be of the transmitted signal. For example, the first transmitted sampling rate 742 of the first physiological signal 710 is lower than the second transmitted sampling rate 744 of the second physiological signal 715. In some examples, the first transmitted sampling rate 742 comprises a first staggered transmitted sampling rate 742A and a second staggered transmitted sampling rate 742B. For example, the first staggered transmitted sampling rate 742A is lower than the second staggered transmitted sampling rate 742B. In some examples, communication circuitry 54 may output an indication of first staggered transmitted sampling rate 742A, a second staggered transmitted sampling rate 742B, and / or second transmitted sampling rate 744, which may respectively correspond to a value of the first staggered compression ratio 732A, a valueAtty Ref. No.: A0012899W001 of the second staggered compression ratio 732B, and a value of the second compression ratio 734.

[0094] FIG. 7D shows an example of a sensed physiological signal 700 that is similar to the sensed physiological signal 700 as shown in FIG. 7A. In some examples, as shown in FIG. 7D, IMD 10 may analyze physiological signal 700 in segments 750A-750F, (collectively “segments 750”). IMD 10 may segment physiological signal 700 into segments 750 based on time. For example, IMD 10 may analyze physiological signal segments 750 that are pre-determined over a period of time. In some examples segments 750 may be segments of greater than or equal to 10 seconds. In some examples segments 750 may be segments of greater than or equal to 30 seconds. In some examples segments 750 may be segments of greater than or equal to 1 minute. In some examples segments 750 may be segments of greater than or equal to 2 minutes. In other instances, IMD 10 may segment physiological signal 700 into segments 750 based on particular features in respective portions of the signal 700. For example, IMD 10 may segment physiological signal 700 into segments 750 that include a certain number of detected R-waves, a certain number of zero-crossings, or other characteristics of physiological signal 700.

[0095] Processing circuitry 50 of IMD 10 may be configured to characterize whether one or more respective segments of segments 750 indicate a medical condition. For example, processing circuitry 50 of IMD 10 may be configured to determine whether one or more respective segments 750 respectively include features that indicate an arrhythmia, such as atrial fibrillation, atrial tachycardia, ventricular fibrillation, ventricular tachycardia or other arrhythmia. In the example of FIG. 7D, processing circuitry 50 of IMD 10 may characterize the portions of physiological signal 700 respectively in segments 750A, 750B, 750E and 750F as being normal (e.g., not arrhythmia) while characterizing the portions of physiological signal 700 respectively in segments 750C and 750D as indicating or being associated with an arrhythmia. Processing circuitry 50 of IMD 10 may be configured to compress the portions of physiological signal 700 respectively in segments 750A, 750B, 750E and 750F at a first compression ratio 732 and be configured to compress portions of physiological signal 700 respectively in segments 750C and 750D at a second compression ratio 734. In some examples, processing circuitry 50 of IMD 10 may not detect an actual arrythmia, until a number of segments 750 are characterized as including a portion of a physiological signa indicating or being associated with an arrythmia (e.g.,Atty Ref. No.: A0012899W001 greater than 2 segments, greater than 3 segments, X of Y segments, etc.), but may still use the dynamic compression techniques of this disclosure on particular segments 750 of physiological signal 700 that are more dense with relevant information associated with a potential arrythmia, noise, oversensing, or other relevant signal information.

[0096] FIG. 8 is a flow diagram illustrating an example technique for operation of IMD 10 to dynamically compress sensed physiological signals and external device 12 to reconstruct the dynamically compressed physiological signals as high-fidelity physiological signals. As indicated by FIG. 8, IMD 10 may be configured to sense a physiological signal, the physiological signal including a first physiological signal and a second physiological signal (800). In some examples, the first physiological signal and the second physiological signal occur during different periods of time. For example, the second physiological signal may occur after the first physiological signal. In some examples, IMD 10 may sense a physiological signal via one or more sensors. In some examples, the one or more sensors may include a plurality of electrodes 16, such as a plurality of electrodes positioned on a housing of IMD 10. In some examples, IMD 10 may sense a physiological signal via one or more sensors 62, such as an accelerometer or optical sensor. In some examples, the physiological signal is an EGM signal of the patient, the first physiological signal is a first EGM signal, and the second physiological signal is a second EGM signal. In some examples, processing circuitry, such as processing circuitry 50 of IMD 10, may identify times of occurrence or pending occurrence of a medical condition, such as an arrhythmia, and identify portions of the physiological signal that correspond to the occurrence or pending occurrence of the medical condition, such as the second physiological signal, and compress that portion of the physiological signal at a lower compression ratio than portions of the physiological signal that were determined to be normal operation physiological signals

[0097] Processing circuitry 50 of IMD 10 may be configured to compress the first physiological signal at a first compression ratio (810). In some examples, the first compression ratio is at least a 10 to 1 compression ratio. In some examples, the first compression ratio is at least a 20 to 1 compression ratio. In some examples, the first compression ratio is at least a 50 to 1 compression ratio.

[0098] Processing circuitry 50 of IMD 10 may be configured to determine that one or more features of the second physiological signal indicate an occurrence or pendingAtty Ref. No.: A0012899W001 occurrence of a medical condition (820). In some examples, medical condition physiological signals may include physiological signals that are more chaotic, more variable, and / or more dense with morphological or other features of interest than normal operation physiological signals. In some examples, reconstruction of physiological signals that are more chaotic, more variable, and / or more dense and are compressed at a high compression ratio, such as at least a 10 to 1 compression ratio, may lead to inaccurate reconstruction of the physiological signal. In some examples, the medical condition may be a cardiac event, such as an arrhythmia. In some examples, an EGM signal during an arrhythmia may be more chaotic, more variable, and / or more dense with morphological or other features of interest than an EGM during normal rhythm. In some examples, compressing an arrhythmia EGM signal at a high compression ratio, such as at least a 10 to 1 compression ratio, may lead to inaccurate reconstruction of the arrhythmia EGM signal due to the nature of an arrhythmia EGM signal being more chaotic, more variable, and / or more dense with morphological or other features of interest.

[0099] In response to a determination that the one or more features of the second physiological signal indicate an occurrence of a medical condition, processing circuitry 50 of IMD 10 may be configured to compress the second physiological signal at a second compression ratio (830). The second compression ratio is less than the first compression ratio. In some examples, the second compression ratio is less than half of the first compression ratio. In some examples, the second compression ratio may be based, at least in part, on a type of medical condition the medical condition physiological signal indicates. In some examples, processing circuitry 50 of IMD 10 may linearly decrease a compression ratio from the first compression ratio to the second compression ratio. In some examples, in response to an occurrence of a medical condition being completed, processing circuitry 50 of IMD 10 may linearly increase a compression ratio from the second compression ratio to the first compression ratio or to a compression ratio amount that is similar to the first compression ratio.

[0100] Communication circuitry 54 of IMD 10 may be configured to output the compressed first physiological signal and the compressed second physiological signal to a computing device, such as external device 12, server 94, and / or computing device 100 (840). In some examples, communication circuitry 54 of IMD 10 may be configured to output indications of a value of the compression ratio of the first compressed physiologicalAtty Ref. No.: A0012899W001 signal (e.g., first compression ratio) and a value of the compression ratio of the second physiological signal (e.g., second compression ratio) to the computing device. In some examples, computing device, such as external device 12, server 94, and / or computing device 100, may be configured to receive the compressed first physiological signal and the compressed second physiological signal. In some examples, computing device, such as external device 12, server 94, and / or computing device 100, may be configured to receive the values of the compression ratio of the first compressed physiological signal (e.g., first compression ratio) and the value of the compression ratio of the second physiological signal (e.g., second compression ratio). In some examples, computing device, such as external device 12, server 94, and / or computing device 100, may be a remote computing device.

[0101] In some examples, computing device, such as one or more of external device 12, server 94, and / or computing device 100, may utilize machine learning, such as a deep learning algorithm or model (e.g., a deep neural network or deep belief network), to reconstruct the compressed first physiological signal and the compressed second physiological signal to a high-fidelity first physiological signal and a high-fidelity second physiological signal. In some examples, computing device may be configured to apply the compressed first physiological signal and the compressed second physiological signal to a ML model to reconstruct the compressed first physiological signal and the compressed second physiological signal to a high-fidelity first physiological signal and a high-fidelity second physiological signal (850). In some examples, computing device may be configured to apply the compressed first physiological signal, the compressed second physiological signal, a value of the first compression ratio, and a value of the second compression ratio to a ML model reconstruct the compressed first physiological signal and the compressed second physiological signal to a high-fidelity first physiological signal and a high-fidelity second physiological signal. In some examples, the value of the respective compression ratio may indicate to the ML model the particular compression ratio applied at particular timepoints of the respective physiological signal.

[0102] In some examples, computing device, such as such as one or more of external device 12, server 94, and / or computing device 100, may be configured to execute an artificial intelligence (Al) engine that operates according to one or more models, such as ML models. ML models may include any number of different types of machine learningAtty Ref. No.: A0012899W001 models, such as neural networks, deep neural networks, convolution neural networks, recurrent neural networks, such as long short term memory networks, dense neural networks, and the like. In some examples, various feature inputs to the Al engine may be fed as direct inputs to different layers in a network and not necessarily prior to the convolution layers. Although described with respect to machine learning models, the techniques described in this disclosure are also applicable to other types of Al models, including rule-based models, finite state machines, and the like. For example, the techniques described in this disclosure are also applicable to Bayesian Belief Networks (BBN) or Bayesian machine learning models (these sometimes referred to as Bayesian Networks or Bayesian frameworks herein), Markov random fields, graphical models, Al models (e.g., Naive Bayes classifiers or deep learning models), and / or other belief networks, such as sigmoid belief networks, deep belief networks (DBNs), etc. In other examples, the disclosed technology may leverage non-Bayesian prediction or probability modeling, such as frequentist inference modeling or other statistical models.

[0103] Machine learning may generally enable a computing device to analyze input data and identify an action to be performed responsive to the input data. Each machine learning model may be trained using training data that reflects likely input data. The training data may be labeled or unlabeled (meaning that the correct action to be taken based on a sample of training data is explicitly stated or not explicitly stated, respectively).

[0104] The training of the machine learning model may be guided (in that a designer, such as a computer programmer, may direct the training to guide the machine learning model to identify the correct action in view of the input data) or unguided (in that the machine learning model is not guided by a designer to identify the correct action in view of the input data). In some instances, the machine learning model is trained through a combination of labeled and unlabeled training data, a combination of guided and unguided training, or possibly combinations thereof. Examples of machine learning include nearest neighbor, naive Bayes, decision trees, linear regression, support vector machines, neural networks, k-Means clustering, Q-leaming, temporal difference, deep adversarial networks, evolutionary algorithms or other supervised, unsupervised, semi-supervised, or reinforcement learning algorithms to train one or more models.

[0105] In some examples, a computing device, such as one or more of external device 12, server 94, and / or computing device 100, may be configured to utilize machineAtty Ref. No.: A0012899W001 learning, such as a deep learning algorithm or model (e.g., a deep neural network or deep belief network), to generate a high-fidelity first physiological signal and a high-fidelity second physiological signal based, at least in part, on the compressed first physiological signal and the compressed second physiological signal. Computing device may train a deep learning model to represent a relationship of the compressed physiological signals to high-fidelity physiological signals. For example, processing circuitry 50 may train the deep learning model using compressed physiological signals and high-fidelity physiological signals from other patients. In some examples, processing circuitry 50 may train the deep leaning model by adjusting the weights of a hidden layer of a neural network model to balance the contribution of each input (e.g., characteristics of the compressed physiological signals) to generating respective high-fidelity physiological signals. Once the deep learning model is trained, computing device, such as one or more of external device 12, server 94, and / or computing device 100, may obtain and apply data, such as the compressed first physiological signal and the compressed second physiological signal to the trained deep learning model.

[0106] FIG. 9 is an example of a machine learning model 902 and / or machine learning model 1100 being trained using supervised and / or reinforcement learning techniques, such as machine learning model 1100. Machine learning model 902 and / or machine learning model 1100 may correspond to any ML model described herein. The machine learning model 902 may be implemented using any number of models for supervised and / or reinforcement learning, such as but not limited to, an artificial neural network, a decision tree, naive Bayes network, support vector machine, or k-nearest neighbor model, to name only a few examples. In some examples, one or more of external device 12, server 94, and / or computing device(s) 100 initially trains the machine learning model 902 based on a training set of metrics and corresponding to a high-fidelity physiological signal. The training set 900 may include a set of feature vectors, where each feature in the feature vector represents a value for a particular metric. One or more of external device 12, server 94, and / or computing device(s) 100 may select a training set comprising a set of training instances, each training instance comprising an association between compressed physiological signals and decompressed high-fidelity physiological signals. A prediction or classification by the machine learning model 902 may be compared 904 to the target output 903, and an error signal and / or machine learning model weights modification mayAtty Ref. No.: A0012899W001 sent / applied to the machine learning model 902 based on the comparison to leam / train 905 the machine learning model to modify / update the machine learning model 902. For example, one or more of external device 12, server 94, and / or computing device(s) 100 may, for each training instance in the training set, modify, based on the respective input based on compressed physiological signals and / or decompressed high-fidelity physiological signals of the training instance, the machine learning model 902 to change a score generated by the machine learning model 902 in response to subsequent compressed physiological signals applied to the machine learning model 902.

[0107] FIG. 10 is a conceptual diagram illustrating an example machine learning model 1100 configured to reconstruct one or more decompressed high-fidelity physiological signals based on compressed physiological signals, e.g., sensed and compressed by an IMD and / or other devices as described herein. Machine learning model 1100 is an example of a deep learning model, or deep learning algorithm. One or more of external device 12, or server 94 may train, store, and / or utilize machine learning model 1100, but other devices may apply inputs associated with a particular patient to machine learning model 1100 in other examples. Some non-limiting examples of machine learning techniques include Bayesian probability models, Support Vector Machines, K- Nearest Neighbor algorithms, and Multi-layer Perceptron.

[0108] As shown in the example of FIG. 10, machine learning model 1100 may include three layers. These three layers include input layer 1102, hidden layer 1104, and output layer 1106. Output layer 1106 comprises the output from the transfer function 1105 of output layer 1106. Input layer 1102 represents each of the input values XI through X4 provided to machine learning model 1100. The number of inputs may be less than or greater than 4, including much greater than 4, e.g., hundreds or thousands. In some examples, the input values may be any of the compressed physiological signals described herein.

[0109] Each of the input values for each node in the input layer 1102 is provided to each node of hidden layer 1104. In the example of FIG. 10, hidden layers 1104 include two layers, one layer having four nodes and the other layer having three nodes, but fewer or greater number of nodes may be used in other examples. Each input from input layer 1102 is multiplied by a weight and then summed at each node of hidden layers 1104. During training of machine learning model 1100, the weights for each input are adjusted toAtty Ref. No.: A0012899W001 establish the relationship between a compressed physiological signal and one or more output values indicative of a high-fidelity physiological signal. In some examples, one hidden layer may be incorporated into machine learning model 1100, or three or more hidden layers may be incorporated into machine learning model 1100, where each layer includes the same or different number of nodes.

[0110] The result of each node within hidden layers 1104 is applied to the transfer function of output layer 1106. The transfer function may be liner or non-linear, depending on the number of layers within machine learning model 1100. Example non-linear transfer functions may be a sigmoid function or a rectifier function. The output 1107 of the transfer function may be a reconstructed physiological signal, such as a high-fidelity reconstructed physiological signal. By applying the compressed physiological signals and / or data of the compressed physiological signal to a machine learning model, such as machine learning model 1100, processing circuitry of system 2 is able to reconstruct a high-fidelity physiological signal with great accuracy, specificity, and sensitivity.[oni] The techniques described in this disclosure may be implemented, at least in part, in hardware, software, firmware, or any combination thereof. For example, various aspects of the techniques may be implemented within one or more microprocessors, DSPs, ASICs, FPGAs, or any other equivalent integrated or discrete logic QRS circuitry, as well as any combinations of such components, embodied in external devices, such as physician or patient programmers, stimulators, or other devices. The terms “processor” and “processing circuitry” may generally refer to any of the foregoing logic circuitry, alone or in combination with other logic circuitry, or any other equivalent circuitry, and alone or in combination with other digital or analog circuitry.

[0112] For aspects implemented in software, at least some of the functionality ascribed to the systems and devices described in this disclosure may be embodied as instructions on a computer-readable storage medium such as RAM, DRAM, SRAM, magnetic discs, optical discs, flash memories, or forms of EPROM or EEPROM. The instructions may be executed to support one or more aspects of the functionality described in this disclosure.

[0113] In addition, in some aspects, the functionality described herein may be provided within dedicated hardware and / or software modules. Depiction of different features as modules or units is intended to highlight different functional aspects and does not necessarily imply that such modules or units must be realized by separate hardware orAtty Ref. No.: A0012899W001 software components. Rather, functionality associated with one or more modules or units may be performed by separate hardware or software components, or integrated within common or separate hardware or software components. Also, the techniques could be fully implemented in one or more circuits or logic elements. The techniques of this disclosure may be implemented in a wide variety of devices or apparatuses, including an IMD, an external programmer, a combination of an IMD and external programmer, an integrated circuit (IC) or a set of ICs, and / or discrete electrical circuitry, residing in an IMD and / or external programmer.

[0114] Various aspects of the techniques may enable the following examples.

[0115] Example 1 : A system includes a medical device includes one or more sensors configured to sense a physiological signal of a patient, the physiological signal including a first portion of the physiological signal and a second portion of physiological signal, the first portion of the physiological signal and the second portion of the physiological signal occurring during different periods of time; processing circuitry of the medical device, the processing circuitry configured to: compress the first portion of the physiological signal at a first compression ratio; determine an indication of an occurrence of a medical condition; and in response to the determination of the indication of an occurrence of the medical condition, compress the second portion of the physiological signal at a second compression ratio, the second compression ratio being less than the first compression ratio; and communication circuitry of the IMD, the communication circuitry configured to output the compressed first portion of the physiological signal and the compressed second portion of the physiological signal to a computing device.

[0116] Example 2: The system of example 1, wherein the physiological signal is a cardiac electrogram (EGM) of the patient, the first portion of the physiological signal is a first portion of the cardiac EGM signal, and the second portion of the physiological signal is a second portion of the cardiac EGM signal.

[0117] Example 3: The system of example 2, wherein the medical condition includes a cardiac event.

[0118] Example 4: The system of example 3, wherein the cardiac event includes an arrhythmia.

[0119] Example 5: The system of any of examples 1-4, wherein the processing circuitry is further configured to determine the indication of an occurrence of the medicalAtty Ref. No.: A0012899W001 condition based on at least one or more features of the second portion of the physiological signal.

[0120] Example 6: The system of any of examples 1-5, wherein the second portion of the physiological signal occurs from a first time point to a second time point, the first time point occurring at first period of time before an onset of the medical condition.

[0121] Example 7: The system of any of examples 1-5, wherein the second portion of the physiological signal occurs from a first time point to a second time point, the first time point occurring at an onset of the medical condition.

[0122] Example 8: The system of any of examples 1-7, wherein the first portion of the physiological signal occurs before the second portion of the physiological signal.

[0123] Example 9: The system of any of examples 6-8, wherein the second time point occurs a second period of time after an offset of the medical condition.

[0124] Example 10: The system of any of examples 6-8, wherein the second time point occurs at one of: a second period of time before an offset of the medical condition, or at the offset of the medical condition.

[0125] Example 11 : The system of any of examples 1-10, wherein the system further comprises the computing device, the computing device configured to: receive the compressed first portion of the physiological signal and the compressed second portion of the physiological signal; and apply the compressed first portion of the physiological signal and the compressed second portion of the physiological signal to a machine learning model to reconstruct the compressed first portion of the physiological signal and the compressed second portion of the physiological signal to a reconstructed first portion of the physiological signal and a reconstructed second portion of the physiological signal.

[0126] Example 12: The system of any of examples 1-11, wherein the communication circuitry is further configured to output an indication of a value of the first compression ratio and a value of the second compression ratio.

[0127] Example 13: The system of example 12, wherein the system further comprises the computing device, the computing device configured to: receive the compressed first portion of the physiological signal, the compressed second portion of the physiological signal, the indication of the value of the first compression ratio and the indication of the value of the second compression ratio; and apply the compressed first portion of the physiological signal, the compressed second portion of the physiological signal, the valueAtty Ref. No.: A0012899W001 of the first compression ratio, and the value of the second compression ratio to a machine learning model to reconstruct the compressed first portion of the physiological signal and the compressed second portion of the physiological signal to a reconstructed first portion of the physiological signal and a reconstructed second portion of the physiological signal.

[0128] Example 14: The system of any of examples 1-13, wherein the second compression ratio is less than half of the first compression ratio.

[0129] Example 15: The system of any of examples 1-4, wherein the first compression ratio is at least a 10 to 1 compression ratio.

[0130] Example 16: The system of any of examples 1-14, wherein the first compression ratio comprises a first staggered compression ratio and a second staggered compression ratio, the second staggered compression ratio being less than the first staggered compression ratio.

[0131] Example 17: The system of any of examples 1-16, wherein the medical device is an implantable medical device (IMD).

[0132] Example 18: The system of example 17, wherein the IMD further comprises a housing for subcutaneous implantation within the patient, and the one or more sensors includes a plurality of electrodes positioned on the housing.

[0133] Example 19: The system of any of examples 11 or 13, wherein the machine learning model is a deep neural network.

[0134] Example 20: The system of any of examples 1-19, wherein computing device is a remote computing device.

[0135] Example 21 : A method includes sensing a physiological signal of a patient, the physiological signal including a first portion of the physiological signal and a second portion of the physiological signal, the first portion of the physiological signal and the second portion of the physiological signal occurring during different periods of time compressing the first portion of the physiological signal at a first compression ratio; determining one or more features of the second portion of the physiological signal indicate an occurrence of a medical condition; and in response to the determination that the one or more features of the second portion of the physiological signal indicate an occurrence of a medical condition, compressing the second portion of the physiological signal at a second compression ratio, the second compression ratio being less than the first compression ratio.Atty Ref. No.: A0012899W001

[0136] Example 22: The method of example 21, wherein the physiological signal is a cardiac electrogram (EGM) of the patient, the first portion of the physiological signal is a first portion of the EGM signal, and the second portion of the physiological signal is a second portion of the EGM signal.

[0137] Example 23: The method of example 22, wherein the medical condition includes a cardiac event.

[0138] Example 24: The method of example 23, wherein the cardiac event includes an arrhythmia.

[0139] Example 25: The method of any of examples 21-24 further includes determining the indication of an occurrence of the medical condition based on at least one or more features of the second portion of the physiological signal.

[0140] Example 26: The method of any of examples 21-25, wherein the second portion of the physiological signal occurs from a first time point to a second time point, the first time point occurring a first period of time before an onset of the medical condition.

[0141] Example 27: The method of any of examples 21-25, wherein the second portion of the physiological signal occurs from a first time point to a second time point, the first time point occurring at an onset of the medical condition.

[0142] Example 28: The method of any of examples 21-27, wherein the first portion of the physiological signal occurs before the second portion of the physiological signal.

[0143] Example 29: The method of any of examples 26-28, wherein the second time point occurs a second period of time after an offset of the medical condition.

[0144] Example 30: The method of any of examples 26-28, wherein the second time point occurs at one of: a second period of time before an offset of the medical condition, or at the offset of the medical condition.

[0145] Example 31 : The method of any of examples 21-30, wherein the method further comprises: applying the compressed first portion of the physiological signal and the compressed second portion of the physiological signal to a machine learning model to reconstruct the compressed first portion of the physiological signal and the compressed second portion of the physiological signal to a reconstructed first portion of the physiological signal and a reconstructed second portion of the physiological signal.Atty Ref. No.: A0012899W001

[0146] Example 32: The method of any of examples 21-31, wherein the method further comprises: generating an indication of a value of the first compression ratio and a value of the second compression ratio.

[0147] Example 33: The method of example 32, wherein the method further comprises: apply the compressed first portion of the physiological signal, the compressed second portion of the physiological signal, the value of the first compression ratio, and the value of the second compression ratio to a machine learning model to reconstruct the compressed first portion of the physiological signal and the compressed second portion of the physiological signal to a reconstructed first portion of the physiological signal and a reconstructed second portion of the physiological signal.

[0148] Example 34: The method of any of examples 21-33, wherein the second compression ratio is less than half of the first compression ratio.

[0149] Example 35: The method of any of examples 21-34, wherein the first compression ratio is at least a 10 to 1 compression ratio.

[0150] Example 36: The method of any of examples 21-34, wherein the first compression ratio comprises a first staggered compression ratio and a second staggered compression ratio, the second staggered compression ratio being less than the first staggered compression ratio.

[0151] Various examples have been described. These and other examples are within the scope of the following claims.

Claims

Atty Ref. No.: A0012899W001CLAIMSWhat is claimed is:

1. A system comprising: a medical device comprising: one or more sensors configured to sense a physiological signal of a patient, the physiological signal including a first portion of the physiological signal and a second portion of physiological signal, the first portion of the physiological signal and the second portion of the physiological signal occurring during different periods of time; processing circuitry of the medical device, the processing circuitry configured to: compress the first portion of the physiological signal at a first compression ratio; determine an indication of an occurrence of a medical condition; and in response to the determination of the indication of an occurrence of the medical condition, compress the second portion of the physiological signal at a second compression ratio, the second compression ratio being less than the first compression ratio; and communication circuitry of the IMD, the communication circuitry configured to output the compressed first portion of the physiological signal and the compressed second portion of the physiological signal to a computing device.

2. The system of claim 1, wherein the physiological signal is a cardiac electrogram (EGM) of the patient, the first portion of the physiological signal is a first portion of the cardiac EGM signal, and the second portion of the physiological signal is a second portion of the cardiac EGM signal.

3. The system of claim 2, wherein the medical condition includes a cardiac event.Atty Ref. No.: A0012899W0014. The system of any of claims 1-3, wherein the processing circuitry is further configured to determine the indication of an occurrence of the medical condition based on at least one or more features of the second portion of the physiological signal.

5. The system of any of claims 1-4, wherein the second portion of the physiological signal occurs from a first time point to a second time point, the first time point occurring at a first period of time before an onset of the medical condition.

6. The system of any of claims 1-4, wherein the second portion of the physiological signal occurs from a first time point to a second time point, the first time point occurring at an onset of the medical condition.

7. The system of any of claims 1-6, wherein the first portion of the physiological signal occurs before the second portion of the physiological signal.

8. The system of any of claims 1-7, wherein the system further comprises the computing device, the computing device configured to: receive the compressed first portion of the physiological signal and the compressed second portion of the physiological signal; and apply the compressed first portion of the physiological signal and the compressed second portion of the physiological signal to a machine learning model to reconstruct the compressed first portion of the physiological signal and the compressed second portion of the physiological signal to a reconstructed first portion of the physiological signal and a reconstructed second portion of the physiological signal.

9. The system of any of claims 1-8, wherein the communication circuitry is further configured to output an indication of a value of the first compression ratio and a value of the second compression ratio.

10. The system of claim 9, wherein the system further comprises the computing device, the computing device configured to:Atty Ref. No.: A0012899W001 receive the compressed first portion of the physiological signal, the compressed second portion of the physiological signal, the indication of the value of the first compression ratio and the indication of the value of the second compression ratio; and apply the compressed first portion of the physiological signal, the compressed second portion of the physiological signal, the value of the first compression ratio, and the value of the second compression ratio to a machine learning model to reconstruct the compressed first portion of the physiological signal and the compressed second portion of the physiological signal to a reconstructed first portion of the physiological signal and a reconstructed second portion of the physiological signal.

11. The system of any of claims 1-10, wherein the second compression ratio is less than half of the first compression ratio.

12. The system of any of claims 1-11, wherein the first compression ratio comprises a first staggered compression ratio and a second staggered compression ratio, the second staggered compression ratio being less than the first staggered compression ratio.

13. The system of any of claims 1-12, wherein the medical device is an implantable medical device (IMD).

14. The system of any of claims 1-13, wherein computing device is a remote computing device.

15. A method compri sing : sensing a physiological signal of a patient, the physiological signal including a first portion of the physiological signal and a second portion of the physiological signal, the first portion of the physiological signal and the second portion of the physiological signal occurring during different periods of time compressing the first portion of the physiological signal at a first compression ratio; determining one or more features of the second portion of the physiological signal indicate an occurrence of a medical condition; andAtty Ref. No.: A0012899W001 in response to the determination that the one or more features of the second portion of the physiological signal indicate an occurrence of a medical condition, compressing the second portion of the physiological signal at a second compression ratio, the second compression ratio being less than the first compression ratio.

Images