Selectively filtering noise from cardiac signals

Abstract

An example medical device includes a memory; and processing circuitry coupled to the memory, the processing circuitry configured to: receive cardiac signals from one or more electrodes coupled to the medical device; determining that the noise risk is greater than or equal to a noise risk threshold or the active noise amount is greater than or equal to an active noise threshold; and in response to determining that the noise risk is greater than or equal to the noise risk threshold or the amount of active noise is greater than or equal to the active noise threshold, activating a filter to filter the noise from the cardiac signal.

Description

[0001] This application claims the benefit of U.S. Provisional Patent Application Serial No. 63 / 376,691, filed on September 22, 2022, the entire contents of which are incorporated herein by reference. Technical Field

[0002] The present application relates to an implantable medical device, and more particularly to an implantable cardioverter-defibrillator. Background Art

[0003] Sudden cardiac death (SCD) affects more than 300,000 patients each year and accounts for nearly 6% of annual mortality in the United States, the vast majority of which are due to fatal arrhythmias. Implantable cardioverter-defibrillators (ICDs) are used to prevent SCD by applying low-voltage electrical stimulation (e.g., antitachycardia pacing [ATP]) and / or high-voltage (e.g., defibrillation) shocks to the heart when a life-threatening arrhythmia is detected. Intracardiac delivery of ATP can minimize patient pain and discomfort by reducing the number of defibrillation shocks delivered.

[0004] Implantation of a transvenous lead for intracardiac pacing and defibrillation is not always possible due to anatomical abnormalities, vascular obstructions, or other issues. For these patients, an extravascular ICD (EV-ICD) system may provide the opportunity to receive a lifesaving implantable pacing / defibrillator system. An EV-ICD system may include an extravascular lead that can be implanted in the substernal space and a device that is implanted on the chest. Summary of the invention

[0005] Noise events such as electromagnetic interference (EMI) may result in false tachyarrhythmia detection and result in the subsequent unnecessary delivery of a shock or other therapeutic electrical signal to a patient with an ICD and / or inhibition of pacing therapy. Additionally, some ICDs may not filter noise signals because the filters have a significant current draw, which may reduce the life of the ICD, reduce the sensitivity of the ICD's sensing and detection, and / or have conflicting feature interactions with other devices.

[0006] The technology of the present disclosure relates to selectively filtering noise such as EMI from cardiac signals without compromising detection sensitivity while minimizing reduction in ICD life and conflicting feature interactions with other devices. According to the technology of the present disclosure, the ICD can be configured to enable a noise filter (such as a notch filter) when needed or when it is more likely to be needed and disable the noise filter when it is no longer needed or less likely to be needed. Therefore, the technology described herein can help mitigate the potential for an increase in inappropriate shock rates for ICDs that are susceptible to noise, while also minimizing the current consumption of the active filter to minimize the potential reduction in ICD life and minimize conflicting interactions with other devices.

[0007] In one example, the present disclosure describes a medical device comprising: a memory; and a processing circuit coupled to the memory, the processing circuit being configured to: receive a cardiac signal from one or more electrodes coupled to the medical device; determine that a noise risk is greater than or equal to a noise risk threshold or that an active noise amount is greater than or equal to an active noise threshold; and in response to determining that the noise risk is greater than or equal to the noise risk threshold or that the active noise amount is greater than or equal to the active noise threshold, activate a filter to filter the noise from the cardiac signal.

[0008] In another example, the present disclosure describes a medical device system comprising: a medical device configured to sense a cardiac signal with a sensor; and a processing circuit configured to: determine that a noise risk is greater than or equal to a noise risk threshold or that an active noise amount is greater than or equal to an active noise threshold; and in response to determining that the noise risk is greater than or equal to the noise risk threshold or that the active noise amount is greater than or equal to the active noise threshold, activate a filter to filter the noise from the cardiac signal.

[0009] In another example, the present disclosure describes a method comprising: receiving a cardiac signal from one or more electrodes coupled to a medical device; determining, by a processing circuit, that a noise risk is greater than or equal to a noise risk threshold or that an active noise amount is greater than or equal to an active noise threshold; and in response to determining that the noise risk is greater than or equal to the noise risk threshold or the active noise amount is greater than or equal to the active noise threshold, activating, by the processing circuit, a filter to filter the noise from the cardiac signal.

[0010] This summary is intended to provide an overview of the subject matter described in this disclosure. It is not intended to provide an exclusive or exhaustive explanation of the systems, devices, and methods described in detail in the drawings and the following description. Further details of one or more examples are set forth in the following drawings and description. Other features, objects, and advantages will be apparent from the description and drawings and from the statements provided below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1A Anterior view of a patient with an extravascular ICD system implanted in the chest.

[0012] Figure 1B A side view of a patient with an extravascular ICD system implanted in the chest.

[0013] Figure 1C A lateral view of a patient with an extravascular ICD system implanted in the chest.

[0014] Figure 2 is a functional block diagram of an exemplary configuration of electronic components of an exemplary ICD.

[0015] Figure 3 is a flow chart illustrating an example method that may be performed by one or more medical devices to selectively activate a filter in accordance with one or more techniques disclosed herein. DETAILED DESCRIPTION

[0016] Oversensing may cause painful inappropriate shocks in patients with implantable cardioverter defibrillators (ICDs). Leads for ICDs, such as right ventricular (RV) leads, substernal leads, subcutaneous leads, or other cardiovascular external leads, are susceptible to noise and / or interference, such as electromagnetic interference (EMI). In some examples, integrated bipolar leads (e.g., where a coil electrode or a portion thereof is used as one of the electrodes of a bipolar sensing pair) may be more susceptible to noise and interference than true bipolar leads because the distance between the tip electrode and the ring or sensing electrode is greater in integrated bipolar leads than in true bipolar leads. For example, an EMI event may result in an erroneous detection of ventricular fibrillation (VF), and result in the subsequent unnecessary delivery of shocks or other therapeutic electrical signals and / or inhibition of pacing therapy to patients with ICDs. However, due to the need for high sensitivity in rapid arrhythmia sensing and detection, some ICDs may not reject EMI signals. In some examples, the EMI source that a patient may encounter comes from an alternating current (AC) power source. Some examples of frequencies of EMI from those AC sources are 50 Hertz (Hz) to 60 Hz. In some examples, these EMI frequencies may be close enough to the passband range to be sensed after being attenuated by the device sense amplifiers, which may be designed to reject higher frequency EMI sources in modern environments. Additionally, some ICDs may not reject EMI signals because the filters have intensive current draws that adversely affect battery life, which may reduce the life of the ICD. Additionally, the filters may reduce the sensitivity of the ICD's sensing and detection, and / or have conflicting feature interactions with other devices.

[0017] In general, the present disclosure relates to techniques that facilitate avoiding oversensing due to noise without compromising the detection sensitivity or battery life of an ICD. According to the techniques of the present disclosure, an ICD can be configured to selectively enable a noise filter (such as a notch filter) when needed or when it is more likely to be needed and disable the noise filter when it is no longer needed or less likely to be needed. Thus, the techniques described herein can help mitigate the potential for an increase in the rate of inappropriate shocks for ICDs that are susceptible to noise, while also minimizing current consumption due to active filters to minimize reductions in ICD life and minimize conflicting feature interactions with some devices.

[0018] Although the noise detection techniques of the present disclosure are primarily described herein with respect to detecting EMI, these techniques may be utilized to detect other types of noise. For example, the noise detection techniques of the present disclosure may detect noise due to muscle or other motion artifacts, lead breakage or disconnection, magnetic resonance imaging, and other non-physiological noise. In some examples, the techniques described herein may be applied to detect noise in a ventricular electrogram to avoid inappropriate detection of ventricular tachyarrhythmias (e.g., ventricular tachycardia (VT) or VF), to an atrial electrogram to avoid inappropriate detection of an atrial tachyarrhythmia (e.g., atrial tachycardia, fibrillation, or flutter), and / or to detect noise in a surface electrocardiogram.

[0019] As used herein, relational terms such as "first" and "second", "above" and "below", "front" and "back", etc. may be used solely to distinguish one entity or element from another entity or element without necessarily requiring or implying any physical or logical relationship or order between such entities or elements.

[0020] Although the techniques of the present disclosure are primarily described herein with respect to extravascular ICD systems, these techniques may be used with transvenous ICD systems or any ICD system, a leadless pacemaker (such as the Micra available from Medtronic plc), or a pacing device. TM Utilization with a leadless pacemaker), or any pacemaker, or any device that senses cardiac or other physiological signals that may be affected by EMI or other noise sources.

[0021] Figures 1A to 1C is a conceptual diagram illustrating an exemplary system 8 that may be used to sense physiological parameters of patient 12 and / or provide therapy to heart 26 of patient 12. System 8 includes ICD 9 coupled to lead 10. Although Figures 1A to 1C ICD 9 is shown coupled to lead 10, but ICD 9 may be coupled to multiple leads. ICD 9 may be, for example, an implantable pacemaker, cardioverter, and / or defibrillator that provides electrical signals to heart 26 via electrodes coupled to lead 10. Patient 12 is typically, but not necessarily, a human patient.

[0022] Figure 1A 1 is a front view of a patient 12 having an extravascular ICD system 8 implanted in the chest cavity. Referring now to the drawings in which like reference designators refer to like elements, Figures 1A to 1C A conceptual diagram illustrating various views of an exemplary extravascular ICD system 8 is shown in FIG. The ICD system 8 includes an ICD 9 connected to implantable medical leads 10. Figure 1A is a front view of a patient implanted with an extravascular ICD system 8 . Figure 1B is a side view of a patient implanted with an extravascular ICD system 8 . Figure 1Cis a lateral view of a patient implanted with an extravascular ICD system 8 .

[0023] The ICD 9 may include an outer shell that forms an airtight seal that protects the internal components of the ICD 9. The outer shell of the ICD 9 may be formed of a conductive material such as titanium or a titanium alloy, which can be used as an outer shell electrode (sometimes referred to as a can electrode). In some embodiments, the ICD 9 may be formed to have or may include multiple electrodes on the outer shell. The ICD 9 may also include a connector assembly 34 (also referred to as a connector block or plug), which includes electrical feedthroughs through which electrical connections are made between the conductors of the leads 10 and the electronic components contained in the outer shell of the ICD 9. As will be described in further detail herein, the outer shell may accommodate one or more processors, memories, transmitters, receivers, sensors, sensing circuits, treatment circuits, power supplies, and other appropriate components. The outer shell is configured to be implanted in a patient (such as patient 12).

[0024] ICD 9 can be implanted outside the left thorax of the patient, for example, under the skin and outside the chest cavity (subcutaneous or submuscular). In some cases, ICD 9 can be implanted between the left posterior axillary line and the left anterior axillary line of the patient. However, as described later, ICD 9 can be implanted at other extrathoracic locations of the patient.

[0025] Lead 10 may include an elongated lead body 13 having a distal portion 16 sized to be implanted in an extravascular location proximal to the heart, such as within the thorax (eg, Figures 1A to 1C For example, lead 10 may extend from ICD 9 toward the center of the patient's torso, e.g., toward the patient's xiphoid process 23, under the skin and outside the chest cavity (e.g., subcutaneously or submuscularly) to outside the chest. At a location near xiphoid process 23, lead body 13 may be bent or otherwise rotated upward and extended. The bend may be preformed and / or lead body 13 may be flexible to facilitate the bend. Figures 1A to 1C In the illustrated example, the lead body 13 extends upward within the chest cavity below the sternum in a direction substantially parallel to the sternum.

[0026] The distal portion 16 of the lead 10 can be located in a substernal position such that the distal portion 16 of the lead 10 extends substantially upward along the posterior side of the sternum within the anterior mediastinum 36. The anterior mediastinum 36 can be considered to be bounded laterally by the pleura 39, posteriorly by the pericardium 38, and anteriorly by the sternum 22. In some cases, the anterior wall of the anterior mediastinum 36 can also be formed by the transverse thoracic muscle and one or more costal cartilages. The anterior mediastinum 36 includes a certain amount of loose connective tissue (such as cellulite), adipose tissue, some lymphatic vessels, lymph glands, substernal muscle tissue (e.g., transverse thoracic muscle), thymus, branches of the internal thoracic artery, and the internal thoracic vein (ITV).

[0027] The lead body 13 may extend upwardly outside the thorax (rather than into the thorax), such as subcutaneously or submuscularly above the thorax / sternum. The lead 10 may be implanted at other locations, such as above the sternum, offset to the right of the sternum, angled laterally from the proximal or distal end of the sternum, etc. In some examples, the lead 10 may be implanted in an extracardiac vessel within the thorax, such as the ITV, intercostal veins, superior epigastric veins or the azygos, hemiazygos, and accessory hemiazygos veins. In some examples, the orientation of the distal portion 16 of the lead 10 may be different from that of the distal portion 16 of the lead 10. Figures 1A to 1C The illustrated orientations are such as orthogonal to or otherwise transverse to the sternum 22 and / or inferior to the heart 26. In such examples, the distal portion 16 of the lead 10 can be at least partially within the anterior mediastinum 36. In some examples, the distal portion 16 of the lead 10 can be placed between the heart and the lungs and within the pleural cavity.

[0028] The lead body 13 may have a generally tubular or cylindrical shape and may define a diameter of approximately 3 to 9 French (Fr). However, lead bodies less than 3 Fr and greater than 9 Fr may also be utilized. In another configuration, the lead body 13 may have a flat, ribbon-like or paddle-like shape along at least a portion of the length of the lead body 13, with a solid woven filament or metal mesh structure. In such examples, the width across the lead body 13 may be between 1 mm and 3.5 mm. Other lead body designs may be used without departing from the scope of the present application.

[0029] The lead body 13 may be formed of a non-conductive material including silicone, polyurethane, fluoropolymer, mixtures thereof, and other suitable materials, and shaped to form one or more cavities (not shown), however, the technology is not limited to such a configuration. The distal portion 16 may be manufactured to be biased in a desired configuration, or alternatively, may be manipulated by a user into a desired configuration. For example, the distal portion 16 may be constructed of a ductile material so that the user can manipulate the distal portion into a desired configuration that remains unchanged until manipulated into a different configuration.

[0030] The lead body 13 may include a proximal portion 14 and a distal portion 16, the distal portion including an electrode configured to deliver electrical energy to the heart or sense electrical signals of the heart. The distal portion 16 may be anchored to a desired location in the patient's body, such as under the sternum or subcutaneously, by, for example, suturing the distal portion 16 to the patient's muscle tissue, tissue, or bone at the xiphoid process entry site. In some examples, the distal portion 16 may be anchored to the patient or by using rigid tines, prongs, barbs, clips, screws, and / or other protruding elements or flanges, discs, compliant tines, flaps, porous structures such as mesh elements, and metal or non-metal stents that promote tissue growth for engagement, bioadhesive surfaces, and / or any other non-piercing elements.

[0031] The lead body 13 may define a substantially linear portion 20 ( Figure 1A ). In some examples, at least a portion of distal portion 16 may define a three-dimensional wavy pattern as it extends toward the distal end of lead 10, such as a sawtooth, zigzag, sinusoidal, serpentine, or other pattern.

[0032] The distal portion 16 includes one or more defibrillation electrodes configured to deliver an anti-tachyarrhythmia, such as cardioversion / defibrillation, electric shock to the heart 26 of the patient 12. In some examples, the distal portion 16 includes a plurality of defibrillation electrodes spaced a distance apart from one another along the length of the distal portion 16. Figures 1A to 1C In the illustrated example, the distal portion 16 includes two defibrillation electrodes 28a and 28b (collectively referred to as “defibrillation electrodes 28 ”).

[0033] The defibrillation electrodes 28 may be disposed around or within the lead body 13 of the distal portion 16, or alternatively, may be embedded within the wall of the lead body 13. In one configuration, the defibrillation electrodes 28 may be coil electrodes formed of a conductor. The conductor may be formed of one or more conductive polymers, ceramics, metal-polymer composites, semiconductors, metals, or metal alloys, including but not limited to one of platinum, tantalum, titanium, niobium, zirconium, ruthenium, indium, gold, palladium, iron, zinc, silver, nickel, aluminum, molybdenum, stainless steel, MP35N, carbon, copper, polyaniline, polypyrrole, and other polymer combinations. In another configuration, each of the defibrillation electrodes 28 may be a flat ribbon electrode, a paddle electrode, a braided or woven electrode, a mesh electrode, a directional electrode, a patch electrode, or another type of electrode configured to deliver a cardioversion / defibrillation shock to the heart 26 of the patient 12.

[0034] The defibrillation electrodes 28 may be electrically connected to one or more conductors that may be disposed in a body wall of the lead body 13 or in one or more insulating lumens (not shown) defined by the lead body 13. In an exemplary configuration, each of the defibrillation electrodes 28 is connected to a common conductor so that a voltage may be applied to all of the defibrillation electrodes 28 simultaneously to deliver an anti-tachyarrhythmia shock to the heart 26. In other configurations, the defibrillation electrodes 28 may be attached to separate conductors so that each defibrillation electrode 28 may have a voltage applied to it independently of the other defibrillation electrodes 28. In such a case, the ICD 9 or lead 10 may include one or more switches or other mechanisms to electrically connect the defibrillation electrodes together to serve as common polarity electrodes so that, in addition to being able to apply voltage independently, a voltage may be applied to all of the defibrillation electrodes 28 simultaneously.

[0035] The distal portion 16 may also include one or more pacing and / or sensing electrodes configured to deliver pacing pulses to the heart 26 and / or sense electrical activity of the heart 26. Such electrodes may be referred to as pacing electrodes, sensing electrodes, or pacing / sensing electrodes. Figures 1A to 1C In the illustrated example, the distal portion 16 includes two pacing / sensing electrodes 32a and 32b (collectively referred to as “pacing / sensing electrodes 32 ”).

[0036] In some examples, the electrode 32 may be configured to deliver low voltage electrical pulses to the heart and / or may sense cardiac electrical activity, such as depolarization and repolarization of the heart. Therefore, the electrode 32 may be referred to herein as a pacing / sensing electrode 32. In one configuration, the electrode 32 is a ring electrode. However, in other configurations, the electrode 32 may be any of a variety of different types of electrodes, including a ring electrode, a short coil electrode, a paddle electrode, a hemispherical electrode, an electrode segment extending circumferentially around less than half of the circumference of the lead body, or a directional electrode. Each electrode in the electrode 32 may be an electrode of the same or different type as the other electrodes in the electrode 32. The electrode 32 may be electrically isolated from the adjacent defibrillation electrode 28 by accommodating an electrically insulating layer of material between the electrode 32 and the adjacent defibrillation electrode 28. Each electrode 32 may have its own separate conductor so that a voltage may be applied to each electrode or sensed via each electrode independently of another electrode 32.

[0037] Electrode 28 is referred to as a defibrillation electrode, and electrode 32 is referred to as a pacing / sensing electrode, because they may have different physical structures, thereby achieving different functions. Defibrillation electrode 28 may be larger than pacing / sensing electrode 32, for example, having a larger surface area, and thus may be configured to deliver an anti-tachyarrhythmia shock having a relatively higher voltage than a pacing pulse. The relatively smaller size of pacing / sensing electrode 32 may provide advantages over defibrillation electrodes for delivering pacing pulses and sensing intrinsic cardiac activity, for example, a lower pacing capture threshold and / or better sensing signal quality. However, defibrillation electrode 28 may be used to deliver pacing pulses and / or sense electrical activity of the heart, such as in combination with pacing / sensing electrode 32. In some examples, sensing of electrical activity of the heart may be between sensing electrode 32b and all or a portion of one of defibrillation electrodes 28a, 28b.

[0038] The proximal portion 14 of the lead body 13 may include one or more connectors 34 to electrically couple the lead 10 to the ICD 9. The ICD 9 may also include a connector assembly including electrical feedthroughs through which electrical connections are made between the one or more connectors 34 of the lead 10 and the electronic components included in the housing. The housing of the ICD 9 may house one or more processors, memories, transmitters, receivers, sensors, sensing circuits, treatment circuits, power sources (capacitors and batteries), and / or other components. The components of the ICD 9 may generate and deliver electrical therapies, such as anti-tachycardia pacing, cardioversion or defibrillation shocks, post-shock pacing, and / or bradycardia pacing.

[0039] The three-dimensional wavy configuration of the distal portion 16 and the inclusion of the electrodes 32 between the defibrillation electrodes 28 can provide multiple therapy vectors for delivering electrical therapy to the heart. For example, at least a portion of the defibrillation electrodes 28 and one of the electrodes 32 can be disposed over the right ventricle or any chamber of the heart so that pacing pulses and anti-tachyarrhythmia shocks can be delivered to the heart. The housing of the ICD 9 can be charged or used as a polarity different from the polarity of one or more of the defibrillation electrodes 28 and / or electrodes 32 so that electrical energy can be delivered to the heart between the housing and the defibrillation electrodes 28 and / or electrodes 32.

[0040] When voltage is applied to each defibrillation electrode 28, each defibrillation electrode may have the same polarity as each other defibrillation electrode 28 so that a defibrillation shock may be delivered together from all defibrillation shocks. In examples where the defibrillation electrodes 28 are electrically connected to a common conductor within the lead body 13, this is the configuration of the defibrillation electrodes 28. However, in other examples, the defibrillation electrodes 28 may be coupled to separate conductors within the lead body 13, and therefore may each have a different polarity, so that electrical energy may flow between the defibrillation electrodes 28, or between one of the defibrillation electrodes 28 and one of the pacing / sensing electrodes 32 or housing electrodes to provide an anti-tachyarrhythmia shock, pacing therapy, and / or sense cardiac depolarization. In this case, the defibrillation electrodes 28 may still be electrically coupled together, for example, via one or more switches within the ICD 9, to have the same polarity.

[0041] ICD 9 may wirelessly communicate with another implanted medical device and / or may wirelessly communicate with one or more patient computing devices (e.g., patient computing device 18). Patient computing device 18 is configured for wireless communication with ICD 9. Computing device 18 retrieves sensed physiological data collected and stored by ICD 9 from ICD 9. In some examples, computing device 18 takes the form of a personal computing device of patient 12. For example, computing device 18 may take the form of a smartphone, smart watch, or other smart garment of patient 12. In some examples, computing device 18 may be any computing device configured for wireless communication with ICD 9, such as a desktop computer, laptop computer, or tablet computer. Computing device 18 may be configured for wireless communication with ICD 9, such as a desktop computer, laptop computer, or tablet computer. Computing device 18 may be configured for wireless communication with ICD 9, such as a wireless communication device ... or The computing device 18 may be configured to communicate with various other devices or systems via a network. For example, one or more of the computing devices 18 may be configured to communicate with one or more computing systems that may be managed by the manufacturers of the ICD 9 and computing device 18, respectively, to provide, for example, cloud storage and analysis of the collected data, maintenance and software services, or other networking capabilities for their respective devices and their users. In some examples, the computing system may include the Medtronic Carelink TM Online or through Medtronic Carelink TM Network to implement.

[0042] Although shown as a stand-alone device in FIG. 1 for purposes of example, the computing device 18 may be any component or system that includes processing circuitry or other suitable computing environment for executing software instructions, and need not, for example, include one or more of the elements shown in FIG. 1 . The computing device 18 may include communication circuitry for communicating with other devices by sending and receiving data. The computing device 18 may receive data from the ICD 9, such as cardiac signals, noise, and / or interference from the communication circuitry in the ICD 9. The computing device may send data to the ICD 9, such as data related to noise / interference history or noise / interference events. The computing device 18 may include a network interface card, such as an Ethernet card, an optical transceiver, a radio frequency transceiver, or any other type of device that can send and receive information. For example, the computing device 18 may include a radio transceiver configured for use in accordance with a wireless communication protocol such as 3G, 4G, 5G, Wi-Fi (e.g., 802.11 or 802.15 ZigBee), or Low Energy (BLE) and other standards or protocols.

[0043] The computing device 18 may be configured to execute an AI engine that operates according to one or more models, such as a machine learning model. The machine learning model may include any number of different types of machine learning models, such as a neural network, a convolutional neural network, a deep neural network, a dense neural network, etc. Although described with respect to a machine learning model, the techniques described in the present disclosure may also be applicable to other types of AI models, including rule-based models, finite state machines, etc.

[0044] Machine learning generally enables a computing device to analyze input data and identify actions to be performed in response to the input data. Each machine learning model can be trained using training data that reflects possible input data. The training data can be labeled or unlabeled (meaning that the correct action to be taken based on a sample of the training data is explicitly stated or not, respectively).

[0045] The training of the machine learning model may be directed (in that a designer, such as a computer programmer, may direct the training to direct the machine learning model to identify the correct action given the input data) or undirected (in that the designer does not direct the machine learning model to identify the correct action given the input data). In some instances, the machine learning model is trained by a combination of labeled and unlabeled training data, a combination of directed and undirected training, or possibly a combination thereof. Examples of machine learning include nearest neighbors, naive Bayes, decision trees, linear regression, support vector machines, neural networks, k-means clustering, Q-learning, temporal differences, deep adversarial networks, evolutionary algorithms, or other supervised, unsupervised, semi-supervised, or reinforcement learning algorithms for training one or more models.

[0046] Computing device 18 may utilize machine learning, such as a deep learning algorithm or model (e.g., a neural network or a deep belief network), to generate a score indicating whether noise is present in the cardiac signal and / or a risk score determining that the noise will be predominantly present for a period of time, such as the next hour, the next day, the next week, the next month, the next 6 months, etc. The generated score may be output as an indication of whether the noise risk is greater than or equal to a risk threshold.

[0047] For example, a deep learning algorithm or machine learning model may be trained using a clean heart signal and a heart signal with different levels of noise at different frequencies (e.g., 50 Hz, 60 Hz, and 16.7 Hz, etc.). For example, 16.7 Hz corresponds to European subway system noise. The output of the deep learning algorithm or machine learning model may be a score indicating whether noise is present. Thus, the computing device 18 is able to determine very accurately whether noise is present because noise may have unique characteristics that are very different from the heart signal. The deep learning algorithm or machine learning model may also generate a score indicating that noise will exist for a period of time based on a score indicating the presence of noise, a historical pattern of noise occurrence (day, time, etc.), patient activity level, GPS location, patient notes, etc., which may be input into the model to predict how long the noise will exist.

[0048] The deep learning algorithm or machine learning model can also generate a score indicating that the noise will be present for a period of time based on the score indicating the presence of noise, historical patterns of noise occurrence (day, time, etc.), patient activity level, GPS location, patient's notes, etc., which can be fed into the model to predict how long the noise will last.

[0049] The techniques of the present disclosure may be applied to implantable systems other than ICD 9, including but not limited to bradycardia pacemaker systems, and external stimulation devices, such as permanent or temporary external pacemakers or defibrillators.

[0050] In some examples, the lead 10 may include a first defibrillation electrode 28a and a second defibrillation electrode 28b configured to deliver an anti-tachyarrhythmia shock. In this example, the pacing electrode 32b may be configured to deliver a pacing pulse that generates an electric field near the pacing electrode.

[0051] As mentioned above, in Figures 1A to 1C In an example of , lead 10 can sense electrical activity of heart 26 , such as via electrodes 32 that can sense cardiac electrical activity (e.g., depolarization and repolarization of the heart), and / or deliver electrical stimulation to heart 26 , such as via defibrillation electrodes 28 and / or pacing / sensing electrodes 32 .

[0052] Figure 2is a functional block diagram of an exemplary configuration of electronic components and other components of ICD 9. ICD 9 includes processing circuitry 202, sensing circuitry 204, therapy delivery circuitry 206, sensor 208, communication circuitry 210, and memory 212. In some examples, ICD 9 may include more or fewer components. The described circuits and other components may be implemented together on shared hardware components, or separately as discrete but interoperable hardware or software components. The depiction of different features is intended to highlight different functional aspects and does not necessarily imply that such circuits and other components must be implemented by separate hardware or software components. Instead, functions associated with one or more circuits and components may be performed by separate hardware or software components, or integrated within shared or separate hardware or software components.

[0053] The sensing circuit 204 may be electrically coupled to some or all of the electrodes 216, which may correspond to any of the defibrillation electrodes, pacing / sensing electrodes, and housing electrodes described herein. The sensing circuit 204 may be coupled to some or all of the sensors 208. The sensing circuit 204 is configured to obtain signals sensed via one or more combinations of the electrodes 216 and / or the sensors 208 and process the obtained signals. The sensing circuit 204 may include a filter 214. In some examples, the sensing circuit 204 may include a plurality of filters 214. In some examples, the sensing circuit 204 may be implemented in the processing circuit 202 of the ICD 9.

[0054] The components of the sensing circuit 204 may be analog components, digital components, or a combination thereof. The sensing circuit 204 may, for example, include one or more sensing amplifiers, filters, rectifiers, threshold detectors, analog-to-digital converters (ADCs), and the like. The sensing circuit 204 may convert the sensed signal into digital form and provide the digital signal to the processing circuit 202 for processing or analysis. For example, the sensing circuit 204 may amplify the signal from the sensing electrode and convert the amplified signal into a multi-bit digital signal through the ADC. The sensing circuit 204 may also compare the processed signal with a threshold value to detect the presence of atrial depolarization or ventricular depolarization (e.g., a P wave or an R wave) and indicate the presence of atrial depolarization (e.g., a P wave) or ventricular depolarization (e.g., an R wave) to the processing circuit 202. Figure 2 As shown, the ICD 9 may additionally include one or more sensors 208, such as one or more accelerometers, which may be configured to provide signals to the processing circuit 202 indicative of other parameters of the patient, such as activity or posture.

[0055] The processing circuitry 202 may process signals from the sensing circuitry 204 to monitor electrical activity of the heart 26 of the patient 12. The processing circuitry 202 may store the signals obtained by the sensing circuitry 204 and any generated EGM waveforms, marker channel data, or other data derived based on the sensed signals in the memory 212. The processing circuitry 202 may analyze the EGM waveforms and / or marker channel data to detect arrhythmias (e.g., bradycardia or tachycardia).

[0056] In response to detecting a cardiac event, processing circuitry 202 may control therapy delivery circuitry 206 to deliver a desired therapy to treat the cardiac event, such as a defibrillation shock, a cardioversion shock, ATP, post-shock pacing, or bradycardia pacing.

[0057] The therapy delivery circuit 206 is configured to generate electrical therapy and deliver the electrical therapy to the heart 26. The therapy delivery circuit 206 may include one or more pulse generators, capacitors, and / or other components capable of generating and / or storing energy for delivery as pacing therapy, defibrillation therapy, cardioversion therapy, cardiac resynchronization therapy, other therapy, or a combination of therapies. In some cases, the therapy delivery circuit 206 may include a first set of components configured to provide pacing therapy and a second set of components configured to provide defibrillation therapy. In some cases, the therapy delivery circuit 206 may utilize the same set of components to provide both pacing therapy and defibrillation therapy. In still other cases, the therapy delivery circuit 206 may share some of the defibrillation therapy components and the pacing therapy components, while using other components only for defibrillation or pacing. The processing circuit 202 may control the therapy delivery circuit 206 to deliver the generated therapy to the heart 26 via one or more combinations of electrodes 216. Although Figure 2 Not shown, but ICD 9 may include switching circuitry that is configurable by processing circuitry 202 to control which of electrodes 216 is connected to therapy delivery circuitry 206 and sensing circuitry 204 .

[0058] The processing circuit 202 may receive one or more cardiac signals of the patient 12 from one or more sensing electrodes 32 coupled to the ICD 9. In some examples, the one or more sensing electrodes may be positioned in a lead coupled to the ICD or in a leadless ICD. The processing circuit 202 may also receive noise from the one or more sensing electrodes 32. A non-limiting example of noise is electromagnetic interference (EMI). The cardiac signals may include noise and may be corrupted by the noise. Noise that corrupts the cardiac signals may result in false detection of ventricular fibrillation (VF) and result in subsequent unnecessary shock delivery by the ICD 9.

[0059] Processing circuit 202 may determine that the noise risk is above a noise risk threshold and / or that the active noise is above an active noise threshold, and in response to determining that the noise risk is greater than or equal to the noise risk threshold and / or that the active noise is greater than or equal to the active noise threshold, processing circuit 202 may activate filter 214 to filter noise from the cardiac signal, which may reduce unnecessary shock delivery by ICD 9. In some examples, processing circuit 202 may determine that the noise risk is above a noise risk threshold, and in response to determining that the noise risk is greater than or equal to the noise risk threshold, processing circuit 202 may activate filter 214 to filter noise from the cardiac signal, which may reduce unnecessary shock delivery by ICD 9.

[0060] In some examples, noise risk may be indicated based on noise history. For example, if the occupancy and / or living quarters of patient 12 are in a location with strong noise signals, the cardiac signal received from one or more sensing electrodes 32 will likely include noise and be corrupted. If the processing circuit determines that the noise risk is greater than or equal to a threshold, such as a predetermined threshold indicating that a corrupted cardiac signal may result in unnecessary shock delivery by ICD 9, the processing circuit 202 activates filter 214 to filter the noise. The risk score may indicate noise risk or noise likelihood. In some examples, the threshold may be a signal-to-noise ratio, which is a ratio of the noise level to the cardiac signal level. In some examples, the ratio threshold may be selected to be a value such that, once exceeded, the noise will be over-sensed or the processing circuit 202 may not accurately classify the corrupted signal as VT or VF.

[0061] In some examples, processing circuit 202 may determine a noise type corresponding to the detected noise risk, such as a noise frequency (e.g., 50 Hz, 60 Hz, 16.7 Hz), and adjust filter 214 to filter a signal corresponding to the detected noise type. For example, when processing circuit 202 detects that the noise frequency is 50 Hz, filter 214 may be adjusted to filter a 50 Hz signal.

[0062] In some examples, the processing circuit 202 may initially determine the spectrum of a true clean cardiac signal and use this spectrum as a reference. The processing circuit 202 may determine that frequency points on the spectrum of the cardiac signal having additional energy above a threshold compared to the reference spectrum may be considered noise. The processing circuit 202 may tune the filter 214 for the noise frequency and apply the tuned filter 214 to filter out noise with that particular frequency. For example, if the cardiac signal has a certain level of 60Hz EMI noise, there may be significant energy on the spectrum at 60Hz compared to its adjacent frequency components (e.g., the reference frequency), and then the processing circuit 202 may determine that the cardiac signal is corrupted by 60Hz EMI. In response, the processing circuit 202 may then apply a 60Hz filter such as a notch filter to filter out the noise. Similar techniques can be applied to other frequencies of EMI, such as 16.7Hz, 50Hz, etc.

[0063] The ICD 9 may send the received cardiac signal to a computing device 18, which may apply the cardiac signal to a machine learning model to determine a noise risk. In some examples, a clinician may determine that the received cardiac signal includes noise and that the noise risk is above a risk threshold. In some examples, the noise risk may be determined based on a number of short VV interval counts in the cardiac signal over a period of time. If the number of short VV interval counts over a period of time is above an interval count threshold, then it may be determined that the noise risk is above the noise risk threshold.

[0064] Processing circuit 202 may determine whether the noise risk becomes less than one or more of a noise risk threshold or whether the active noise becomes less than an active noise threshold when filter 214 is activated. In response to determining that the noise risk is less than the noise risk threshold or the active noise is less than one or more of the active noise threshold, processing circuit 202 may deactivate filter 214. In some examples, when filter 214 is activated, filter 214 may have a large current consumption that may negatively affect battery life, thereby reducing the life of ICD 9. In some examples, processing circuit 202 may determine whether the noise risk becomes less than a noise risk threshold when filter 214 is activated. In response to determining that the noise risk is less than the noise risk threshold, processing circuit 202 may deactivate filter 214. Therefore, selectively activating filter 214 according to these techniques can help reduce unnecessary shock delivery by ICD 9 while minimizing the impact of activating filter 214 on the battery life of ICD 9.

[0065] In some examples, in response to determining that the noise risk is greater than or equal to the noise risk threshold, the processing circuit 202 may activate the filter 214, causing the filter to be turned on for a time period greater than the noise risk time threshold. The time period may correspond to the time period during which the noise risk is determined to be greater than the noise risk threshold. In some examples, the processing circuit 202 may determine a time period during which the noise risk may be greater than the noise risk threshold, such as by applying the cardiac signal to the machine learning model and receiving a time period during which the noise risk generated by the machine learning model will be greater than the noise risk threshold. The processing circuit 202 may then activate and deactivate the filter 214 to correspond to the time period during which the determined noise risk is greater than the noise risk threshold.

[0066] In some examples, processing circuit 202 may automatically deactivate filter 214 at the end of the time period. In some examples, in response to the end of the time period, processing circuit 202 may compare the noise risk to a noise risk threshold. In response to the noise risk being less than the noise risk threshold, processing circuit 202 may deactivate filter 214. In response to the noise risk being greater than or equal to the noise risk threshold, processing circuit 202 may maintain filter 214 in an activated state.

[0067] In response to determining that the active noise is greater than or equal to the active noise threshold, the processing circuit 202 may activate the filter 214. The processing circuit 202 may determine whether the active noise becomes less than the active noise threshold, and deactivate the filter 214 in response to the active noise becoming less than the active noise threshold. In some examples, the processing circuit 202 may determine a noise type corresponding to the detected active noise, such as an active noise frequency (e.g., 50 Hz, 60 Hz, 16.7 Hz), and adjust the filter 214 to filter a signal corresponding to the detected noise type. For example, when the processing circuit 202 detects that the noise frequency is 50 Hz, the filter 214 may be adjusted to filter a 50 Hz signal. In some examples, the filter 214 may be a notch filter.

[0068] In some examples, the processing circuit 202 may initially determine the spectrum of a true clean cardiac signal and use this spectrum as a reference. The processing circuit 202 may determine that frequency points on the spectrum of the cardiac signal having additional energy above a threshold compared to the reference spectrum may be considered noise. The processing circuit 202 may tune the filter 214 for the noise frequency and apply the tuned filter 214 to filter out noise with that particular frequency. For example, if the cardiac signal has a certain level of 60Hz EMI noise, there may be significant energy on the spectrum at 60Hz compared to its adjacent frequency components (e.g., the reference frequency), and then the processing circuit 202 may determine that the cardiac signal is corrupted by 60Hz EMI. In response, the processing circuit 202 may then apply a 60Hz filter such as a notch filter to filter out the noise. Similar techniques can be applied to other frequencies of EMI, such as 16.7Hz, 50Hz, etc.

[0069] Processing circuit 202 may determine active EMI based on one or more of the following: 1) identifying a possible detection state of noise, 2) one or more of the ventricular depolarization VV interval or RR interval is less than an interval timing threshold, or 3) the noise is above a noise threshold. In some examples, a fast Fourier transform may be used to determine the active noise frequency.

[0070] In response to detecting a cardiac event, processing circuitry 202 may control therapy delivery circuitry 206 to deliver a desired therapy to treat the cardiac event, such as a defibrillation shock, a cardioversion shock, ATP, post-shock pacing, or bradycardia pacing.

[0071] The therapy delivery circuit 206 is configured to generate electrical therapy and deliver the electrical therapy to the heart 26. The therapy delivery circuit 206 may include one or more pulse generators, capacitors, and / or other components capable of generating and / or storing energy for delivery as pacing therapy, defibrillation therapy, cardioversion therapy, cardiac resynchronization therapy, other therapy, or a combination of therapies. In some cases, the therapy delivery circuit 206 may include a first set of components configured to provide pacing therapy and a second set of components configured to provide defibrillation therapy. In some cases, the therapy delivery circuit 206 may utilize the same set of components to provide both pacing therapy and defibrillation therapy. In still other cases, the therapy delivery circuit 206 may share some of the defibrillation therapy components and the pacing therapy components while using other components only for defibrillation or pacing. The processing circuit 202 may control the therapy delivery circuit 206 to deliver the generated therapy to the heart 26 via one or more combinations of electrodes 216. Although Figure 2 Not shown, but ICD 9 may include switching circuitry that is configurable by processing circuitry 202 to control which of electrodes 216 is connected to therapy delivery circuitry 206 and sensing circuitry 204 .

[0072] Communication circuitry 210 may include any suitable hardware, firmware, software, or any combination thereof for communicating with another device, such as a clinician programmer, a patient monitoring device, etc. For example, communication circuitry 210 may include appropriate modulation components, demodulation components, frequency conversion components, filtering components, and amplifier components for transmitting and receiving data via an antenna.

[0073] The various components of ICD 9 may include any one or more processors, controllers, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or equivalent discrete or integrated circuits, including analog circuits, digital circuits, or logic circuits. Processing circuitry 202 may include fixed function circuitry and / or programmable processing circuitry. The functions attributed to processing circuitry 202 herein may be embodied in software, firmware, hardware, or any combination thereof.

[0074] Memory 212 may include computer readable instructions that, when executed by processing circuit 202 or other components of ICD 9, cause one or more components of ICD 9 to perform various functions attributed to those components in the present disclosure. Memory 212 may include any volatile, nonvolatile, magnetic, optical, or electronic media, such as random access memory (RAM), read-only memory (ROM), nonvolatile RAM (NVRAM), static nonvolatile RAM (SRAM), electrically erasable programmable ROM (EEPROM), flash memory, or any other nonvolatile computer readable storage medium.

[0075] Figure 3 This is an example based on Figure 2 Flowchart of an exemplary technique for ICD 9 to activate a filter to filter EMI from a cardiac signal as shown in . In some examples, processing circuit 202 may receive one or more cardiac signals from one or more sensing electrodes 32 coupled to a medical device (302). In some examples, processing circuit 202 may determine that a noise risk is greater than or equal to a noise risk threshold or that active noise is greater than or equal to one or more of an active noise threshold (304). In response to determining that the noise risk is greater than or equal to the noise risk threshold or that active noise is greater than or equal to one or more of the active noise threshold, processing circuit 202 may activate filter 214 to filter noise from the cardiac signal (306). In some examples, processing circuit 202 may adjust filter 214 to filter a frequency of noise corresponding to one or more of the noise risk or the active noise (308). In response to determining that the noise risk is less than the risk threshold or that the active noise is less than one or more of the active noise threshold, processing circuit 202 may deactivate filter 214 (310).

[0076] It should be understood that the various aspects disclosed herein may be combined in combinations different from those specifically presented in the specification and drawings. It should also be understood that, depending on the example, certain actions or events of any of the processes or methods described herein may be performed in a different order, may be added, merged, or omitted entirely (e.g., not all described actions or events may be required to perform these techniques). In addition, although certain aspects of the present disclosure are described as being performed by a single module, unit, or circuit for clarity, it should be understood that the techniques of the present disclosure may be performed by a combination of units, modules, or circuits associated with, for example, a medical device.

[0077] In one or more examples, the described techniques can be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions can be stored as one or more instructions or codes on a computer-readable medium and executed by a hardware-based processing unit. The computer-readable medium may include a non-transitory computer-readable medium that corresponds to a tangible medium, such as a data storage medium (e.g., RAM, ROM, EEPROM, flash memory, or any other medium that can be used to store desired program code in the form of instructions or data structures and can be accessed by a computer).

[0078] Instructions may be executed by one or more processors, such as one or more digital signal processors (DSPs), general purpose microprocessors, application specific integrated circuits (ASICs), field programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuits. Thus, the terms "processor" or "processing circuitry" as used herein may refer to any of the foregoing structures or any other physical structure suitable for implementing the described techniques. Additionally, these techniques may be fully implemented in one or more circuits or logic elements.

[0079] The following examples are illustrative of the techniques described herein.

[0080] Embodiment 1: A medical device, comprising: a memory; and a processing circuit coupled to the memory, the processing circuit being configured to: receive a cardiac signal from one or more electrodes coupled to the medical device; determine that a noise risk is greater than or equal to a noise risk threshold or that an active noise amount is greater than or equal to an active noise threshold; and in response to determining that the noise risk is greater than or equal to the noise risk threshold or that the active noise amount is greater than or equal to the active noise threshold, activate a filter to filter the noise from the cardiac signal.

[0081] Embodiment 2: A medical device according to embodiment 1, wherein the processing circuit is further configured to: when the filter is activated, determine whether the noise risk becomes less than the noise risk threshold or whether the active noise amount becomes less than the active noise threshold; and in response to determining that the noise risk is less than the noise risk threshold or the active noise amount is less than the active noise threshold, deactivate the filter.

[0082] Embodiment 3: The medical device according to any one of Embodiments 1 to 2, wherein the processing circuit is further configured to: activate the filter in response to determining that the noise risk is greater than or equal to the noise risk threshold.

[0083] Embodiment 4: The medical device according to any one of Embodiments 1 to 3, wherein the processing circuit is further configured to: determine a noise frequency corresponding to the noise risk; and adjust the filter to filter the noise frequency corresponding to the noise risk.

[0084] Embodiment 5: A medical device according to any one of Embodiments 1 to 4, wherein the processing circuit is further configured to: in response to determining that the noise risk is greater than or equal to the noise risk threshold, activate the filter so that the filter is turned on and lasts for a time period greater than the noise risk time threshold.

[0085] Embodiment 6: A medical device according to Embodiment 5, wherein the processing circuit is further configured to: in response to the end of the time period, compare the noise risk with the noise risk threshold; in response to the noise risk being less than the noise risk threshold, deactivate the filter; and in response to the noise risk being greater than or equal to the noise risk threshold, maintain the filter in an activated state.

[0086] Embodiment 7: A medical device according to any one of Embodiments 1 to 6, wherein the processing circuit is further configured to: activate the filter in response to determining that the active noise amount is greater than or equal to the active noise threshold; determine whether the active noise amount becomes less than the active noise threshold; and deactivate the filter in response to the active noise amount becoming less than the active noise threshold.

[0087] Embodiment 8: A medical device according to any one of Embodiments 1 to 7, wherein the processing circuit is further configured to: determine a noise frequency corresponding to the active noise amount; and adjust the filter to filter the noise frequency corresponding to the active noise amount.

[0088] Embodiment 9: A medical device according to any one of embodiments 1 to 8, wherein the processing circuit determines noise risk based on one or more of the following: 1) one or more RR intervals of high frequency episodes are below an interval threshold, 2) one or more short interval counts (SICs) are greater than or equal to a SIC threshold, or 3) AI-determined classification determines that EMI risk is increased.

[0089] Embodiment 10: A medical device according to any one of embodiments 1 to 9, wherein the processing circuit determines the amount of active noise based on one or more of the following: 1) identifying a possible detection state of noise, 2) one or more of the ventricular depolarization VV interval or RR interval is less than an interval timing threshold, or 3) the noise is greater than or equal to a noise threshold.

[0090] Embodiment 11: The medical device according to any one of embodiments 1 to 10, wherein the filter is a notch filter.

[0091] Embodiment 12: The medical device according to any one of Embodiments 1 to 11, wherein the noise is electromagnetic interference (EMI).

[0092] Embodiment 13: The medical device according to any one of embodiments 1 to 12, wherein the processing circuit is further configured to: detect a tachyarrhythmia based on the filtered signal; and deliver a tachyarrhythmia shock in response to detecting the tachyarrhythmia.

[0093] Example 13A: A medical device according to any one of claims 1 to 11, further comprising a therapy delivery circuit configured to generate electrical therapy, wherein the processing circuit is further configured to: detect a tachyarrhythmia based on a filtered signal; and in response to detecting the tachyarrhythmia, control the therapy delivery circuit to generate and deliver a tachyarrhythmia shock.

[0094] Example 13B. A medical device system, the medical device system comprising a medical device according to any one of Examples 1 to 12; and a lead, the lead comprising: a lead body having a proximal portion and a distal portion; one or more connectors, the one or more connectors being located at the proximal portion of the lead body and configured to electrically couple the lead to the medical device; and the one or more electrodes, the one or more electrodes being configured to sense the cardiac signal.

[0095] Embodiment 14: A medical device system comprises: a medical device configured to sense a cardiac signal with a sensor; and a processing circuit configured to: determine that a noise risk is greater than or equal to a noise risk threshold or that an active noise amount is greater than or equal to an active noise threshold; and in response to determining that the noise risk is greater than or equal to the noise risk threshold or that the active noise amount is greater than or equal to the active noise threshold, activate a filter to filter the noise from the cardiac signal.

[0096] Embodiment 15: A medical device system according to Embodiment 14, wherein the processing circuit is further configured to: when the filter is activated, determine whether the noise risk becomes less than the noise risk threshold or whether the active noise amount becomes less than the active noise threshold; in response to determining that the noise risk is less than the noise risk threshold or the active noise amount is less than the active noise threshold, deactivate the filter.

[0097] Embodiment 16: The medical device system according to any one of Embodiments 14 to 15, wherein the processing circuit is further configured to: activate the filter in response to determining that the noise risk is greater than or equal to the noise risk threshold.

[0098] Embodiment 17: A medical device system according to any one of Embodiments 14 to 16, wherein the processing circuit is further configured to: determine a noise frequency corresponding to the noise risk; and adjust the filter to filter the noise frequency corresponding to the noise risk.

[0099] Embodiment 18: A medical device system according to embodiments 14 to 17, wherein the processing circuit is further configured to: in response to determining that the noise risk is greater than or equal to the noise risk threshold, activate the filter so that the filter is turned on and lasts for a time period greater than the noise risk time threshold.

[0100] Embodiment 19: A medical device system according to Embodiment 18, wherein the processing circuit is further configured to: in response to the end of the time period, compare the noise risk with the noise risk threshold; in response to the noise risk being less than the noise risk threshold, deactivate the filter; and in response to the noise risk being greater than or equal to the noise risk threshold, maintain the filter in an activated state.

[0101] Embodiment 20: A medical device system according to any one of Embodiments 14 to 19, wherein the processing circuit is further configured to: activate the filter in response to determining that the active noise amount is greater than or equal to the active noise threshold; determine whether the active noise amount becomes less than the active noise threshold; and deactivate the filter in response to the active noise amount becoming less than the active noise threshold.

[0102] Embodiment 21: A medical device system according to any one of Embodiments 14 to 20, wherein the processing circuit is further configured to: determine a noise frequency corresponding to the active noise amount; and adjust the filter to filter the noise frequency corresponding to the active noise amount.

[0103] Embodiment 22: A medical device system according to any one of embodiments 14 to 21, wherein the processing circuit determines the noise risk based on one or more of the following: 1) one or more RR intervals of high frequency episodes are below an interval threshold, 2) one or more short interval counts (SICs) are greater than or equal to a SIC threshold, or 3) an AI-determined classification determines that the noise risk is increased.

[0104] Embodiment 23: A medical device system according to any one of embodiments 14 to 22, wherein the processing circuit determines the amount of active noise based on one or more of the following: 1) identifying a possible detection state of noise, 2) one or more of the ventricular depolarization VV interval or RR interval is less than an interval timing threshold, or 3) the noise is greater than or equal to a noise threshold.

[0105] Embodiment 24: The medical device system of any one of Embodiments 14 to 23, wherein the filter is a notch filter.

[0106] Embodiment 25: The medical device system of any one of Embodiments 14 to 24, wherein the noise is electromagnetic interference (EMI).

[0107] Embodiment 26: According to the medical device system described in any one of Embodiments 14 to 25, the processing circuit is further configured to: detect a tachyarrhythmia based on the filtered signal; and deliver a tachyarrhythmia shock in response to detecting the tachyarrhythmia.

[0108] Example 27: A method includes: receiving a cardiac signal from one or more electrodes coupled to a medical device; and determining, by a processing circuit, that a noise risk is greater than or equal to a noise risk threshold or that an active noise amount is greater than or equal to an active noise threshold; and in response to determining that the noise risk is greater than or equal to the noise risk threshold or that the active noise amount is greater than or equal to the active noise threshold, activating, by the processing circuit, a filter to filter the noise from the cardiac signal.

[0109] Embodiment 28: According to the method described in Embodiment 27, the method also includes, when the filter is activated, determining by the processing circuit whether the noise risk becomes less than the noise risk threshold or whether the active noise amount becomes less than the active noise threshold; in response to determining that the noise risk is less than the noise risk threshold or the active noise amount is less than the active noise threshold, deactivating the filter by the processing circuit.

[0110] Embodiment 29: The method according to any one of Embodiments 27 to 28, further comprising activating the filter by the processing circuit in response to determining that the noise risk is greater than or equal to the noise risk threshold.

[0111] Embodiment 30: According to the method described in any one of Embodiments 27 to 29, the method further includes determining, by the processing circuit, a noise frequency corresponding to the noise risk; and adjusting, by the processing circuit, the filter to filter the noise frequency corresponding to the noise risk.

[0112] Embodiment 31: According to the method described in any one of Embodiments 27 to 30, the method further includes, in response to determining that the noise risk is greater than or equal to the noise risk threshold, activating the filter by the processing circuit so that the filter is turned on and lasts for a time period greater than the noise risk time threshold.

[0113] Embodiment 32: According to the method described in Embodiment 31, the method also includes, in response to the end of the time period, comparing, by the processing circuit, the noise risk with the noise risk threshold; in response to the noise risk being less than the noise risk threshold, deactivating the filter by the processing circuit; and in response to the noise risk being greater than or equal to the noise risk threshold, maintaining the filter in an activated state by the processing circuit.

[0114] Embodiment 33: According to the method described in any one of Embodiments 27 to 32, the method further includes activating the filter by the processing circuit in response to determining that the active noise amount is greater than or equal to the active noise threshold; determining by the processing circuit whether the active noise amount becomes less than the active noise threshold; and deactivating the filter by the processing circuit in response to the active noise amount becoming less than the active noise threshold.

[0115] Embodiment 34: According to the method described in any one of Embodiments 27 to 33, the method further includes determining a noise frequency corresponding to the active noise amount; and adjusting the filter to filter the noise frequency corresponding to the active noise amount.

[0116] Embodiment 35: A method according to any one of embodiments 27 to 34, wherein the determined noise risk is based on one or more of the following: 1) one or more RR intervals of high frequency episodes are below an interval threshold, 2) one or more short interval counts (SIC) are greater than or equal to a SIC threshold, or 3) AI-determined classification determines that the noise risk is increased.

[0117] Embodiment 36: A method according to any one of embodiments 27 to 35, wherein the determined amount of active noise is based on one or more of the following: 1) identifying a possible detection state of noise, 2) one or more of the ventricular depolarization VV interval or RR interval is less than an interval timing threshold, or 3) the noise is greater than or equal to a noise threshold.

[0118] Embodiment 37: A method according to any one of embodiments 27 to 36, wherein the filter is a notch filter.

[0119] Embodiment 38: A method according to any one of Embodiments 27 to 37, wherein the noise is electromagnetic interference (EMI).

[0120] Embodiment 39: The method according to any one of embodiments 27 to 38, further comprising detecting a tachyarrhythmia based on the filtered signal; and delivering a tachyarrhythmia shock in response to detecting the tachyarrhythmia.

[0121] It should be understood by those skilled in the art that the present application is not limited to the contents specifically shown and described above. In addition, unless otherwise indicated above, it should be noted that all drawings are not drawn to scale. Without departing from the scope and spirit of the present application, various modifications and variations are possible according to the above teachings, and the scope and spirit of the present application are limited only by the appended claims.

Claims

1. A medical device, comprising: Memory; and a processing circuit coupled to the memory, the processing circuit being configured to: receiving a cardiac signal from one or more electrodes coupled to the medical device; determining that the noise risk is greater than or equal to a noise risk threshold or that the amount of active noise is greater than or equal to an active noise threshold; as well as In response to determining that the noise risk is greater than or equal to the noise risk threshold or the active noise amount is greater than or equal to the active noise threshold, a filter is activated to filter noise from the cardiac signal.

2. The medical device of claim 1, wherein the processing circuit is further configured to: when the filter is activated, determining whether the noise risk becomes less than the noise risk threshold or whether the active noise amount becomes less than the active noise threshold; and In response to determining that the noise risk is less than the noise risk threshold or the active noise amount is less than the active noise threshold, the filter is deactivated.

3. The medical device according to any one of claims 1 to 2, wherein the processing circuit is further configured to: determining a noise frequency corresponding to the noise risk; and The filter is adjusted to filter the noise frequency corresponding to the noise risk.

4. The medical device according to any one of claims 1 to 3, wherein the processing circuit is further configured to: In response to determining that the noise risk is greater than or equal to the noise risk threshold, the filter is activated so that the filter is turned on for a time period greater than a noise risk time threshold.

5. The medical device of claim 4, wherein the processing circuit is further configured to: responsive to the time period ending, comparing the noise risk to the noise risk threshold; In response to the noise risk being less than the noise risk threshold, deactivating the filter; and In response to the noise risk being greater than or equal to the noise risk threshold, maintaining the filter in an activated state.

6. The medical device according to any one of claims 1 to 5, wherein the processing circuit is further configured to: activating the filter in response to determining that the active noise amount is greater than or equal to the active noise threshold; determining whether the active noise amount becomes less than the active noise threshold; as well as In response to the active noise amount becoming less than the active noise threshold, the filter is deactivated.

7. The medical device according to any one of claims 1 to 6, wherein the processing circuit is further configured to: determining a noise frequency corresponding to the amount of active noise; and The filter is adjusted to filter the noise frequency corresponding to the active noise amount.

8. A medical device according to any one of claims 1 to 7, wherein the processing circuit determines noise risk based on one or more of the following: 1) one or more RR intervals of high frequency episodes are below an interval threshold, 2) one or more short interval counts (SICs) are greater than or equal to a SIC threshold, or 3) an AI-determined classification determines that EMI risk is elevated.

9. The medical device of any one of claims 1 to 8, wherein the processing circuit determines the amount of active noise based on one or more of: 1) identifying a possible detection state of noise, 2) one or more of a ventricular depolarization VV interval or a RR interval being less than an interval timing threshold, or 3) the noise being greater than or equal to a noise threshold.

10. The medical device according to any one of claims 1 to 9, wherein the filter is a notch filter.

11. The medical device according to any one of claims 1 to 10, wherein the noise is electromagnetic interference (EMI).

12. The medical device of any one of claims 1 to 11, further comprising a therapy delivery circuit configured to generate electrical therapy, wherein the processing circuit is further configured to: detecting a tachyarrhythmia based on the filtered signal; and In response to detecting the tachyarrhythmia, the therapy delivery circuit is controlled to generate and deliver a tachyarrhythmia shock.

13. A medical device system, comprising: The medical device according to any one of claims 1 to 12; and A lead, the lead comprising: a lead body having a proximal portion and a distal portion; one or more connectors located at the proximal portion of the lead body and configured to electrically couple the lead to the medical device; and The one or more electrodes are configured to sense the cardiac signal.

14. A method comprising: Receive heart signals; determining that the noise risk is greater than or equal to a noise risk threshold or that the amount of active noise is greater than or equal to an active noise threshold; as well as In response to determining that the noise risk is greater than or equal to the noise risk threshold or the active noise amount is greater than or equal to the active noise threshold, a filter is activated to filter the noise from the cardiac signal.

Images