Detection of ambient noise to reduce cardiac events

Abstract

The medical device system comprises a medical device having one or more sound sensors configured to generate an audio signal containing noise experienced by a patient, and a processing circuit. The processing circuit is configured to determine one or more noise levels experienced by the patient based on the audio signal, to determine the patient's risk of cardiac disease based at least in part on one or more noise levels, and to generate an output corresponding to the cardiac disease risk for the patient or another user's computing device.

Description

Technical Field

[0004] , , ,

[0003] , , ,

[0001] This application claims the benefit of U.S. Provisional Patent Application No. 63 / 381,452, filed Oct. 28, 2022, the entire contents of which are incorporated herein by reference.

[0002] (Field of the Invention) The present disclosure generally relates to systems including medical devices, and more particularly to monitoring a patient's health state using such systems.

Background Art

[0003] Various devices are configured to monitor a patient's physiological signals. Some types of devices can also be used to monitor one or more environmental conditions about the environment in which the patient is located. Such devices include implantable medical devices or wearable medical devices, as well as various wearable health state tracking devices or fitness tracking devices. Physiological signals sensed by such devices include, by way of example, electrocardiogram (ECG) signals, electroencephalogram (EEG) signals, respiratory signals, perfusion signals, activity and / or posture signals, pressure signals, blood oxygen saturation signals, body composition, and blood glucose or other blood component signals. Generally, by using these signals, such devices facilitate monitoring and evaluating a patient's health state outside of a clinical setting over months or years.

Summary of the Invention

[0004] Generally, the present disclosure is directed to techniques for patient health management and risk management. More particularly, the present disclosure describes techniques for recording (and in some examples, processing) ambient noise levels in a patient's environment using, for example, a medical device, such as an implantable medical device (IMD). The techniques further include determining a risk of heart disease based on the noise levels.

[0005] Excessive noise in a patient's environment may be associated with the onset or exacerbation of various cardiovascular diseases, such as heart failure, arrhythmias, and coronary artery disease, or with other patient conditions that are risk factors for cardiovascular disease, such as hypertension, diabetes, and obesity. Examples of situations in which patients may be exposed to excessive noise include traffic and certain occupations. Some people may live or work in areas where they are frequently and / or chronically exposed to significant environmental noise. Excessive noise levels can activate the stress response, leading to dysregulated cardiovascular function, cardiovascular tissue remodeling, and / or cell death.

[0006] The techniques of this disclosure can improve the functionality of medical device systems to monitor a patient's cardiovascular health. For example, a medical device in a system, such as an implantable cardiac monitor or other implantable medical device, may be configured to continuously and / or chronically monitor a patient's noise exposure, recording the magnitude and impact of the patient's exposure to excessive noise more comprehensively than would otherwise be possible. In this way, the system may be able to monitor the patient over time, for example, for several months or years, without requiring instructions or intervention from a clinician, patient, or others. In addition, the system may provide several analyses to determine the risk level of cardiac disease based on applying criteria or predictive models (e.g., machine learning models) to noise levels, and possibly other physiological data. In this way, the techniques of the present invention may enable a medical device system to more quickly and completely identify exposure to potentially harmful excessive noise and communicate the resulting risk of cardiac disease to the patient, the patient's clinician, or other relevant parties. In some cases, the communication of cardiac disease risk may, advantageously, facilitate or even include recommendations / instructions for taking measures to mitigate excessive noise exposure and / or reduce the risk level of cardiac disease. Reducing or eliminating exposure to excessive murmurs may help reduce or prevent cardiac disease, or delay disease progression. The ability to continuously monitor murmur levels and determine cardiac disease risk based on murmur levels is lacking in conventional medical devices, and the devices and techniques of this disclosure represent an improvement in the functionality of medical devices and systems for the benefit of patients by improving the ability of such devices and systems to monitor cardiac health.

[0007] In some examples, a medical device system comprises a medical device having one or more sound sensors configured to generate an audio signal containing noise experienced by a patient. The medical device system further comprises a processing circuit configured to determine one or more noise levels experienced by the patient based on the audio signal, determine the patient's risk of cardiac disease based at least in part on one or more noise levels, and generate an output corresponding to the cardiac disease risk for the patient or another user's computing device.

[0008] In some examples, the method includes: a processing circuit of a medical device system including a medical device determining one or more noise levels experienced by a patient based on sound signals generated by a sound sensor of the medical device; the processing circuit determining the patient's risk of cardiac disease based at least in part on one or more noise levels; and the processing circuit generating an output corresponding to the cardiac disease risk for the patient or another user's computing device.

[0009] In some examples, a non-temporary computer-readable storage medium includes instructions, when executed, that cause a processing circuit of a medical device system to perform one of the methods described herein.

[0010] This summary is intended to provide an overview of the subject matter described herein. It is not intended to provide an exclusive or comprehensive description of the systems, devices, and methods described in detail in the accompanying drawings and the following description. Further details of one or more examples of this disclosure are provided in the accompanying drawings and the following description. Other features, subject matter, and advantages will become apparent from the description and drawings and the claims. [Brief explanation of the drawing]

[0011] [Figure 1] Block diagram shows an exemplary system configured to detect and respond to noise levels experienced by a patient using one or more techniques of the present disclosure.

[0012] [Figure 2] This is a conceptual diagram illustrating an exemplary device of the system shown in Figure 1 for sensing ambient noise levels using one or more techniques described herein.

[0013] [Figure 3A] This is a perspective view showing an implantable cardiac monitor.

[0014] [Figure 3B] A perspective view showing another implantable heart monitor.

[0015] [Figure 4] A block diagram showing an exemplary configuration of a medical device operating in accordance with one or more techniques of the present disclosure.

[0016] [Figure 5] A block diagram showing an exemplary configuration of a computing device operating in accordance with one or more technologies of the present disclosure.

[0017] [Figure 6] A block diagram showing a logical view of an exemplary service operating by an exemplary system of FIG. 5 according to one or more examples of the present disclosure.

[0018] [Figure 7] A flowchart showing exemplary operations for generating an output of a heart disease risk caused by ambient noise in a patient's environment according to one or more techniques of the present disclosure.

[0019] [Figure 8] A flowchart showing exemplary operations for generating a noise profile of a patient over a period of time according to one or more techniques described herein.

[0020] Like reference characters denote like elements throughout the description and the drawings.

Best Mode for Carrying Out the Invention

[0021] Evidence suggests a link between excessive noise in the environment and cardiovascular disease. For example, individuals with bilateral high-frequency hearing loss may be about twice as likely to have coronary heart disease compared to the normal population. Individuals exposed to higher decibel traffic noise may correspondingly have a higher risk of cardiovascular disease. According to the techniques of the present disclosure, an implantable medical device (IMD) or other medical device may be configured to continuously determine the ambient ambient noise level, and an IMD or another component of the system may be able to determine a heart disease risk level based on the noise level.

[0022] FIG. 1 is a conceptual diagram showing the environment of an exemplary medical device system 2 in communication with a patient 4 according to one or more techniques of the present disclosure. System 2 includes an IMD 10. In some examples, IMD 10 is implanted outside the patient's chest cavity (e.g., subcutaneously at the chest position shown in FIG. 1). IMD 10 may be positioned near or just below the sternum at the level of the patient's heart, for example, at least partially within the contour of the heart. In some examples, IMD 10 is in the form of a LINQ™ Insertable Cardiac Monitor (ICM) available from Medtronic plc (Dublin, Ireland). According to the techniques of the present disclosure, IMD 10 includes one or more sound sensors for continuously recording sound / noise in the environment of patient 4 over a long period of time. IMD 10 can determine the ambient noise level to which patient 4 is exposed.

[0023] In one example, IMD10 is in the form of an ICM, but in other examples, IMD10 is in the form of any of the various implantable cardiac devices (ICDs) equipped with intravascular or extravascular leads, such as a pacemaker, intracardiac or extracardiac defibrillator, cardiac resynchronization therapy device (CRT-D), neuromodulatory device, implantable sensor, or drug pump. In addition, or alternatively, the techniques of the present disclosure may be used to determine the ambient noise level to which patient 4 is exposed based on signals collected by one or more external medical devices, such as a patch device, a wearable device (e.g., a smartwatch or fitness tracking device), a wearable sensor, or a smartphone, a smart home device, another Internet of Things (IoT) device, or any combination thereof, or other external devices in the patient 4 or the patient's environment.

[0024] Clinicians may diagnose patients exhibiting symptoms or monitor the progression of a disease based on one or more observed physiological signals collected by physiological sensors such as electrodes, optical sensors, chemical sensors, temperature sensors, acoustic sensors, and motion sensors. In some cases, clinicians may apply non-invasive sensors to patients during their visit or hospital stay to sense one or more physiological signals while the patient is at the clinic for an appointment. In addition, clinicians may question patients, for example, verbally or by examination, to determine symptoms and environmental / behavioral factors that may be affecting the patient's health.

[0025] However, in some cases, physiological markers of a patient's condition occur when the patient is outside the clinic. Therefore, in these cases, clinicians may not be able to observe the physiological markers necessary to diagnose a patient exhibiting a condition. Furthermore, it may be beneficial to monitor one or more patient parameters over a long period (e.g., days, weeks, or months) so that one or more parameters can be analyzed to identify patient-specific physiological markers associated with symptoms or conditions. Moreover, patients often provide incomplete information when responding to questions about symptoms and environmental / behavioral factors. In the example shown in Figure 1, the IMD10 is implanted in patient 4 to continuously record one or more physiological signals of patient 4 over a long period. Furthermore, according to the technique of this disclosure, the IMD10 includes one or more sound sensors to continuously record sounds / noise in patient 4's environment over a long period (e.g., several months or several years). To continuously monitor noise in the environment of patient 4, the IMD10 can measure noise periodically and / or continuously on a trigger basis, without requiring intervention or instructions from a clinician, patient 4, or another user, and determine the noise level, cardiac disease risk, or other metrics described herein.

[0026] In addition to the sound sensor, the IMD10 may include one or more electrodes, optical sensors, motion sensors (e.g., accelerometers), temperature sensors, chemical sensors, pressure sensors, or any combination thereof, and any additional sensors that may be part of the IMD10. Such sensors may sense one or more signals indicating one or more physiological parameters of a patient. One or more physiological parameters of a patient may indicate a patient condition, including symptoms or disease. Various features may be extracted from the sensor signals, such as the amount of deviation from baseline, the timing of the deviation, and absolute values ​​corresponding to the patient's physiological parameters at a particular point in time (e.g., a heart rate of 80 bpm).

[0027] IMD10 may be configured to wirelessly communicate with one or more computing devices 12, such as patient computing devices 12A and 12B shown in Figure 1. The computing devices 12 may be patient computing devices or clinician programming devices configured for use in environments such as a home, clinic, or hospital. In some examples, the computing devices 12 may include programmers, external monitors, or consumer devices such as smartphones, smartwatches, or tablets.

[0028] As shown in Figure 1, the computing device 12 may be coupled to a remote health monitoring system (HMS) 26 via a network 16. As shown in Figure 1, the HMS 26 may be implemented by processing circuits 22 and memory 24 of a cloud computing system, such as Carelink®, available from Medtronic plc (Dublin, Ireland). The computing device 12 can transmit data, such as data received from the IMD 10 and data collected by the computing device 12, to the computing system 20 via the network 16. The computing device 12 can communicate via near-field communication technologies (e.g., inductive coupling, near-field communication (NFC), or other communication technologies that can operate within a range of less than 10-20 cm) and far-field communication technologies (e.g., cellular network communication via 802.11 or Bluetooth® specification sets, 3G, 4G, or 5G protocols, or other communication technologies that can operate over a wider range than near-field communication technologies).

[0029] When HMS26 is implemented, the processing circuit 22 of the computing system 20 can collect and process noise level and other patient parameter data received from IMD10 as described herein. Based on the analysis, the processing circuit 22 can determine the risk of cardiovascular disease, including the risk of diseases contributing to cardiovascular disease such as risk heart failure, arrhythmia, or hypertension. The processing circuit 22 can generate outputs such as messages, alerts, reports, network communications, or other communications of noise level, parameter data, risk level, or other patient health metrics to patient 4 via computing device 12, and to other stakeholders via computing devices 14A and 14B (collectively, "Computing Device 14"). Other stakeholders may include clinicians, caregivers, and the family of patient 4. In some cases, the information provided by the processing circuit 22 may identify the time and location (determined, for example, based on global position system (GPS) data from the computing device 12) in which the patient 4 was exposed to excessive noise levels, thereby identifying the source of the noise levels, which may be mitigated or avoided.

[0030] In some examples, the IMD10's sound sensor and one or more other sensors (e.g., electrodes, motion sensors, light sensors, temperature sensors, or any combination thereof) can detect one or more signals, where each signal value represents a measurement taken at a given time interval, e.g., a periodic measurement. Multiple values ​​may represent a series of parameter values ​​measured at repeated time intervals.

[0031] In another example, the IMD10 may perform measurements in response to a patient notification that measurements should be initiated. In yet another example, the IMD10 may perform parameter measurements frequently. In this way, the IMD10 is configured to perform parameter measurements according to time intervals or other time intervals that are embedded within the patient 4 and repeat without missing any time intervals, so that the patient does not need to be in the clinic to track the parameters, and the IMD10 may be configured to track the patient's condition more effectively. In some examples, values ​​may be measured based on specific times of day, or measurements may be grouped together; for example, values ​​may be measured during daytime window hours or nighttime window hours. In addition to time periods, the IMD10 may measure noise levels or other parameters in response to triggers such as determining that a physiological parameter or metric of the patient's condition has changed beyond a threshold from a baseline or recent mean, or receiving an indication of such a change, or determining that the patient 4 has entered or left a geofence based on the location indicated by the computing device 12 (for example, based on the Global Positioning System (GPS) functionality of the computing device 12).

[0032] In general, the techniques of this disclosure may be performed by processing circuits of one or more devices of System 2, such as one or more processing circuits of IMD 10, computing device 12, or processing circuits 22 of computing system 20.

[0033] Figure 2 is a conceptual diagram showing the IMD 10 and computing device 12 of Figure 1 for sensing ambient noise levels using one or more techniques described herein. The IMD 10 includes one or more sound sensors configured to generate signals in response to ambient noise 30, thereby sensing the noise 30 in the environment of patient 4. As will be described in more detail below, the IMD 10 processes the signals generated by one or more sound sensors to determine the noise level to which patient 4 is exposed.

[0034] Figure 2 shows the source 32 of the noise 30. Exemplary sources 32 include traffic, machinery, aircraft, explosions, or other events, and musical performances. In some embodiments, one or more components of System 2 can enable the identification of the noise source 32, or the conditions (e.g., circumstances) under which Patient 4 is exposed to the noise source 32. For example, one or both of IMD 10 and the computing device 12 may identify the time period and / or Patient 4's location associated with the noise level. By presenting such information to Patient 4 or other stakeholders, System 2 may enable Patient 4 to avoid the noise source in the future. By presenting such information to Patient 4 or other stakeholders, System 2 may enable Patient 4 to take other measures to mitigate exposure to the noise source 32 when exposure to the noise source 32 cannot be avoided, for example, by wearing hearing protection equipment. In some cases, Patient 4 may not recognize that their noise exposure is excessive or poses a health risk. In some cases, if patient 4 is exposed to environmental noise for a longer period, for example over 30 days, measures may be recommended including adding soundproofing materials to the home or other environment where patient 4 is exposed to the noise source, or moving to a less populated area. In some cases, through monitoring noise levels (and possibly assessing the risk of cardiac disease) after measures have been taken to reduce exposure to noise, system 2 may provide feedback to patient 4 or other users indicating the effectiveness of such measures.

[0035] In some examples, one or both of the computing devices 12, or another computing device, may also include one or more sound sensors. In such examples, both the IMD 10 and the other devices may be configured to determine a noise level, for example, simultaneously, based on their sensing of the same noise 30. The processing circuits of one or both of the IMD 10 and the computing devices 12 may calibrate one or more sound sensors of the IMD 10 or the noise level determination by the IMD 10 based on signals sensed or determined by the computing devices 12. Such calibration may enable the IMD 10 to determine the decibel level of the noise 30 at the location of patient 4 outside patient 4, based on signals sensed by one or more sensors of the IMD 10 inside patient 4. In some examples, one or both of the computing devices 12 are configured to emit one or more sounds having a known noise level, e.g., a decibel level. The processing circuit of System 2, for example, IMD10 and / or computing device 12, can calibrate one or more sound sensors of IMD10 or calibrate the noise level determination by IMD10 based on the noise level of the signal emitted by computing device 12.

[0036] Figure 3A is a perspective view showing an implantable cardiac monitor 10A, which may be an example configured as an ICM in the IMD 10 of Figure 1. In the example shown in Figure 3A, the IMD 10A may be embodied as a monitoring device having a housing 42, a proximal electrode 46A, and a distal electrode 46B. The housing 42 may further comprise a first main surface 44, a second main surface 48, a proximal end 50, and a distal end 52. The housing 42 surrounds the electronic circuitry located inside the IMD 10A and protects the circuitry housed within from body fluids. The housing 42 is sealed and may be configured for subcutaneous implantation. An electrical feedthrough provides an electrical connection between electrode 46A and electrode 46B.

[0037] In the example shown in Figure 3A, the IMD10A is defined by length L, width W, and thickness or depth D, and is in the form of an elongated right-angle prism, where length L is much greater than width W, and width W is greater than depth D. In one example, the geometric shape of the IMD10A, particularly the width W being greater than depth D, is chosen to allow the IMD10A to be inserted under the patient's skin using a minimally invasive procedure and to remain in the desired orientation during insertion. For example, the device shown in Figure 3A may have radial asymmetry along the longitudinal axis (particularly a rectangular shape) to maintain the device in the appropriate orientation after insertion. For example, the spacing between the proximal electrode 46A and the distal electrode 46B may range from 5 mm to 55 mm, 30 mm to 55 mm, 35 mm to 55 mm, and 40 mm to 55 mm, and may be any range or individual spacing from 5 mm to 60 mm. In addition, the IMD10A may have a length L ranging from 30 mm to approximately 70 mm. In other examples, the length L may be in the range of 5mm to 60mm, 40mm to 60mm, 45mm to 60mm, or any length or range between approximately 30mm and approximately 70mm. In addition, the width W of the main surface 14 may be in the range of 3mm to 15mm, 3mm to 10mm, or 5mm to 15mm, or any single width or range between 3mm and 15mm. The thickness D of the IMD10A may be in the range of 2mm to 15mm, 2mm to 9mm, 2mm to 5mm, or 5mm to 15mm, or any single depth or range between 2mm and 15mm. In addition, the IMD10A according to an example of this disclosure has a geometric shape and size designed for ease of implantation and patient comfort. The example of the IMD10A described in this disclosure may have a volume of 3 cubic centimeters (cm) or less, 1.5 cubic centimeters or less, or any volume between 3 and 1.5 cubic centimeters.

[0038] In the example shown in Figure 3A, when inserted into the patient, the first principal surface 44 faces outward toward the patient's skin, and the second principal surface 48 is located opposite the first principal surface 44. In addition, in the example shown in Figure 3A, the proximal end 50 and distal end 52 are rounded to reduce discomfort and irritation to surrounding tissues when inserted under the patient's skin. The IMD10A, including the instrument and method for inserting the IMD10A, is described, for example, in U.S. Patent Application No. 2014 / 0276928, which is incorporated herein by reference in its entirety.

[0039] The proximal electrode 46A is located at or near the proximal end 50, and the distal electrode 46B is located at or near the distal end 52. The proximal electrode 46A and the distal electrode 46B are used to sense electrocardiogram (ECG) signals thoracically outside the thoracic cavity, which may be submuscular or subcutaneous. The ECG signals may be stored in the memory of the IMD 10A, and the data may be transmitted to another device via the integrated antenna 60A, which may be another implantable device or an external device such as a computing device 12. In some examples, electrodes 46A and 46B may be used, in addition to or alternatively, to sense any biopotential signal of interest from any implantation site, which may be, for example, an electrogram (EGM), electroencephalogram (EEG), electromyogram (EMG), or nerve signal, or to measure impedance.

[0040] In the example shown in Figure 3A, the proximal electrode 46A is located at or very close to the proximal end 50, and the distal electrode 46B is located at or very close to the distal end 52. In this example, the distal electrode 46B is not limited to a flat outward surface, but may extend from the first principal surface 44 onto the second principal surface 48 around a rounded edge 54 and / or end face 56, so that the electrode 46B has a three-dimensional curved configuration. In some examples, the electrode 46B is an uninsulated portion of the metal (e.g., titanium) part of the housing 42.

[0041] As shown in Figure 3A, the proximal electrode 46A is located on the first principal surface 44 and is substantially flat and outward-facing. However, in other examples, the proximal electrode 46A may utilize the three-dimensional curved configuration of the distal electrode 46B to provide a three-dimensional proximal electrode (not shown in this example). Similarly, in other examples, the distal electrode 46B may utilize a substantially flat outward-facing electrode located on the first principal surface 44, similar to the electrode shown with respect to the proximal electrode 46A.

[0042] These various electrode configurations allow for configurations in which the proximal electrode 46A and the distal electrode 46B are located on both the first principal surface 44 and the second principal surface 48. In other configurations, such as that shown in Figure 3A, only one of the proximal electrode 46A or the distal electrode 46B is located on both principal surfaces 44 and 48, and in yet another configuration, both the proximal electrode 46A and the distal electrode 46B are located on either the first principal surface 44 or the second principal surface 48 (for example, the proximal electrode 46A is located on the first principal surface 44 and the distal electrode 46B is located on the second principal surface 48). In another example, the IMD10A may include electrodes on both principal surfaces 44 and 48, at or near the proximal and distal ends of the device, so that a total of four electrodes are included in the IMD10A. Electrodes 16A and 16B may be formed from several different types of biocompatible conductive materials, such as stainless steel, titanium, platinum, iridium, or alloys thereof, and may utilize one or more coatings such as titanium nitride or fractal titanium nitride.

[0043] In the example shown in Figure 3A, the proximal end 50 includes a header assembly 58 which includes one or more of the proximal electrode 46A, an integrated antenna 60A, an anti-movement projection 62, and / or suture holes 64. The integrated antenna 60A is located on the same principal surface as the proximal electrode 46A (i.e., the first principal surface 44) and is included as part of the header assembly 58. The integrated antenna 60A enables the IMD 10A to transmit and / or receive data. In other examples, the integrated antenna 60A may be formed on the principal surface opposite to the electrode 46A or incorporated within the housing 42 of the IMD 10A. In the example shown in Figure 3A, the anti-movement projection 62 is located adjacent to the integrated antenna 60A and protrudes away from the first principal surface 44 to prevent longitudinal movement of the device. In the example shown in Figure 3A, the anti-movement projection 62 includes a plurality (e.g., nine) of small bumps or projections that extend away from the first principal surface 44. As described above, in other examples, the anti-movement projection 62 may be located on the main surface opposite to the proximal electrode 46A and / or integrated antenna 60A. In addition, in the example shown in Figure 3A, the header assembly 58 includes a suture hole 64 that provides another means of securing the IMD 10A to the patient to prevent movement after insertion. In the illustrated example, the suture hole 64 is located adjacent to the proximal electrode 46A. In some examples, the header assembly 58 is a molded header assembly made of polymer or plastic material, which may be integrated with or detachable from the main portion of the IMD 10A.

[0044] Figure 3B is a perspective view showing another IMD10B, which may be another exemplary configuration of IMD10 in Figure 1 as an ICM. IMD10B in Figure 3B may be configured substantially similarly to IMD10A in Figure 3A, and the differences between them are described herein.

[0045] IMD10B may include a leadless subcutaneous implantable monitoring device, such as an ICM. IMD10B includes a housing having a base 70 and an insulating cover 72. Proximal electrodes 46C and distal electrodes 46D may be formed on or positioned on the outer surface of the cover 72. For example, the various circuits and components of IMD10B described below with respect to Figure 3 may be formed on or positioned on the inner surface of the cover 72 or within the base 70. In some examples, the battery or other power source of IMD10B may be included within the base 70. In the illustrated example, the antenna 60B may be formed on or positioned on the outer surface of the cover 72, but in some examples, it may be formed on or positioned on the inner surface. In some examples, the insulating cover 72 may be positioned above the open base 70 so that the base 70 and cover 72 surround the circuits and other components and protect them from fluids such as bodily fluids. The housing including the base 70 and insulating cover 72 may be sealed and configured for subcutaneous implantation.

[0046] Circuits and components may be formed inside the insulating cover 72, for example, by using flip-chip technology. The insulating cover 72 may be inverted on the base 70. When inverted and placed on the base 70, the components of the IMD 10B formed inside the insulating cover 72 may be positioned within a gap 74 defined by the base 70. Electrodes 46C and 46D and the antenna 60B may be electrically connected to the circuits formed inside the insulating cover 72 through one or more vias (not shown) formed through the insulating cover 72. The insulating cover 72 may be formed of sapphire (i.e., corundum), glass, parylene, and / or any other suitable insulating material. The base 70 may be formed of titanium or any other suitable material (e.g., biocompatible material). Electrodes 46C and 46D may be formed from stainless steel, titanium, platinum, iridium, or an alloy thereof. In addition, electrodes 46C and 46D may be coated with materials such as titanium nitride or fractal titanium nitride, but other suitable materials and coatings may be used on such electrodes.

[0047] In the example shown in Figure 3B, the housing of the IMD10B defines a length L, a width W, and a thickness or depth D, and, similar to the IMD10A in Figure 3A, it is in the form of an elongated right-angle prism where the length L is much greater than the width W and W is greater than the depth D. For example, the distance between the proximal electrode 46C and the distal electrode 46D may be in the range of 5mm to 50mm, 30mm to 50mm, 35mm to 45mm, or any single distance or range of distances between 5mm and 50mm, such as about 40mm. In addition, the IMD10B can have a length L in the range of 5mm to about 70mm. In other examples, the length L may be in the range of 30mm to 70mm, 40mm to 60mm, 45mm to 55mm, or any single length or range of lengths between 5mm and 50mm, such as about 45mm. In addition, the width W may be in the range of 3mm to 15mm, 5mm to 15mm, 5mm to 10mm, or any single width or range of widths between 3mm and 15mm, such as approximately 8mm. The thickness or depth D of IMD10B may be in the range of 2mm to 15mm, 5mm to 15mm, or 3mm to 5mm, or any single depth or range of depths between 2mm and 15mm, such as approximately 4mm. IMD10B may have a volume of 3 cubic centimeters (cm) or less, or 1.5 cubic centimeters or less, for example, approximately 1.4 cubic centimeters.

[0048] In the example shown in Figure 3B, when inserted subcutaneously into the patient, the outer surface of the cover 72 faces outward toward the patient's skin. In addition, as shown in Figure 3B, the proximal end 76 and distal end 78 are rounded to reduce discomfort and irritation to surrounding tissues when inserted subcutaneously into the patient's skin. Furthermore, the edges of the IMD 10B may also be rounded.

[0049] Figure 4 is a block diagram showing an exemplary configuration of an IMD 10 according to one or more techniques described herein. In the illustrated example, the IMD 10 includes electrodes 46 (for example, corresponding to any of electrodes 46A to 46D), a processing circuit 100, a memory 102, a sensing circuit 104, one or more patient parameter sensors 106, one or more sound sensors 108, and a communication circuit 110 which may be connected to an antenna 60 (Figures 3A and 3B). The processing circuit 100 may be operably coupled to the memory 102, the sensing circuit 104, one or more patient parameter sensors 106, one or more sound sensors 108, and the communication circuit 110. Although the illustrated example includes two electrodes 46, in some examples, an IMD including or coupled to three or more electrodes 46 can perform the techniques of the present disclosure. The IMD10 further comprises a processing circuit 100, a memory 102, a sensing circuit 104, one or more patient parameter sensors 106, one or more sound sensors 108, and a power supply 109 that supplies operating power to the communication circuit 110.

[0050] The processing circuit 100 may include fixed-function circuits and / or programmable processing circuits. The processing circuit 100 may include one or more of the following: a microprocessor, a controller, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or equivalent individual or analog logic circuits. In some examples, the processing circuit 100 may include multiple components such as one or more microprocessors, one or more controllers, one or more DSPs, one or more ASICs, or one or more FPGAs, and other individual or integrated logic circuits. The functions attributed to the processing circuit 100 herein may be embodied as software, firmware, hardware, or any combination thereof.

[0051] The sensing circuit 104 may be coupled to the electrode 46 to sense, for example, the electrical signals of the patient 4's heart, e.g., an ECG, as controlled by the processing circuit 100. In some examples, the sensing circuit 104 may include one or more filters and amplifiers for filtering and amplifying signals received from the electrode 46, the patient parameter sensor 106, and / or the sound sensor 108. The sensing circuit 104 may include an analog-to-digital conversion circuit for converting the signals into digital samples for analysis by the processing circuit 100 and / or storage in the memory 102.

[0052] The ECG sensed via electrode 46 may represent one or more physiological electrical signals corresponding to the patient's heart. For example, the ECG may show, among other events, ventricular depolarization (QRS sequence including the R wave), atrial depolarization (P wave), and ventricular repolarization (T wave). Information about the aforementioned events, such as the time to isolate one or more of the events, or the form of such events, may be applied for several purposes, including determining whether an arrhythmia is occurring, predicting whether there is a tendency for arrhythmias to occur, and / or determining the risk level of cardiac disease status of patient 4. In some examples, the sensing circuit 104 is configured to measure tissue impedance signals via electrode 46. Tissue impedance may be measured for several purposes, including determining perfusion, edema, respiratory rate, effort and pattern, and / or the level of heart failure.

[0053] Sensor 106 may include an optical sensor. The optical sensor may optionally include two or more photoemitters and one or more photodetectors. The optical sensor may perform one or more measurements to determine the oxygenation of the patient's tissues or blood pressure. Oxygen saturation and blood pressure may indicate one or more patient conditions, such as heart failure, hypertension, sleep apnea, or COPD. In some examples, sensor 106 includes one or more accelerometers. The accelerometers may generate accelerometer signals that reflect measurements of the patient's movement and / or posture. In some cases, the accelerometers may collect a triaxial accelerometer signal that indicates the movement of the patient's movement in a three-dimensional cartesian space.

[0054] The sound (or acoustic) sensor 108 may include a piezoelectric crystal or an accelerometer. Such a sensor may be configured to generate a signal that changes with sound in the patient's environment. In some examples, the sound sensor 108, such as a piezoelectric sensor, can generate an acoustic signal without requiring the injection of current into the sensor, thereby reducing the impact of the continuous operation of the sound sensor on the power supply of the IMD 10. The sound sensor 108 may be mounted on the inner surface of the housing of the IMD 10, or otherwise mounted inside it, but in other examples, it may be mounted on the outer surface of the IMD 10, or coupled to the IMD 10 via lead wires.

[0055] The communication circuit 110 may include any suitable hardware, firmware, software, or any combination thereof for communicating with the computing device 12, another networked computing device, or another device such as another IMD or sensor. Under the control of the processing circuit 100, the communication circuit 110 may receive downlink telemetry and transmit uplink telemetry from the computing device 12 or another device with the help of an internal or external antenna, for example, antenna 60. Antenna 60 and the communication circuit 110 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 methods.

[0056] In some examples, memory 102 includes computer-readable instructions that, when executed by processing circuit 100, cause IMD 10 and processing circuit 100 to perform various functions attributed to IMD 10 and processing circuit 100 as described herein. Memory 102 may include any volatile, non-volatile, magnetic, optical, or electrical medium, such as random-access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), electrically-erasable programmable ROM (EEPROM), ferroelectric RAM (FRAM), dynamic random-access memory (DRAM), flash memory, or any other digital medium. Memory 102 may, for example, store programmed values ​​of one or more operating parameters of IMD 10. Memory 102 may also store data collected by IMD 10 for transmission to another device using communication circuit 110 and / or for further analysis by processing circuit 100.

[0057] IMD10 is an example of a medical device comprising one or more sound sensors 108 configured to generate an audio signal containing noise experienced by patient 4. As shown in Figure 4, memory 102 can store applications 120 and data 130 used by IMD10, for example, processing circuit 100, to perform the techniques described in this disclosure relating to determining the health of patient 4 based on the audio signal.

[0058] For example, application 120 may include a health management application 122. The noise component 124 of the health management application 112 determines the noise level 132 experienced by patient 4 based on the sound signal. In some examples, each of the noise levels 132 may be stored as data 130 in memory 102 in relation to the time the noise level was measured. In some examples, the noise level 132 may be the decibel level of the noise experienced by patient 4. The noise component 124 may apply a table or function from memory 102 to the sound signal to determine the decibel level, and the table or function may be calibrated as described above with respect to Figure 2.

[0059] The noise component 124 may store as noise level 132 only each determined noise level, or noise levels that exceed the magnitude of a threshold noise. The noise component 124 may store as each noise level 132 the average or other central trend representation of the noise magnitude over several periods. The noise component 124 may also store as each noise level 132 the maximum value of the noise magnitude over several periods. In some examples, the noise component 124 may store as noise level 132 for multiple periods, the integral or sum of the sound signal over the periods, or a count, percentage, sum, or other representation of the amount of time during which the signal magnitude exceeds one or more thresholds. For example, the noise component 124 may store as noise level 132 a value representing the amount or percentage of time during each period in which the decibel level is between 60 decibels and 80 decibels, and / or exceeds 80 decibels. Each period may be, for example, 1 second or longer, 1 minute or longer, or 1 hour or longer. The ability of the noise component 124 to determine such a metric as a noise level from ambient sound signals is a task that is impossible for the human mind to perform and can provide an operational advantage in the ability of the IMD 10 to monitor the cardiovascular health of patient 4.

[0060] The movement of patient 4 may introduce signal noise into the noise signal generated by the sound sensor 108, or may interfere with the determination of the noise level 132 by the noise component 124. In some examples, the processing circuit 100 may determine the activity level of patient 4, for example, based on the accelerometers of the parameter sensor 106 and / or the sound sensor 108. The noise component 124 may be configured to determine whether the activity level of patient 4 is below an activity threshold and to determine the noise level 132 based on the sound signal generated by the sound sensor 108 when the activity level of patient 4 is below the threshold.

[0061] In some examples, the risk component 126 of the health management application 122 determines the risk of cardiac disease for patient 4 based on the noise level 132 and generates an output of the cardiac disease risk, such as an alert or other message, to the computing device 12 via the communication circuit 110. The risk component 126 can determine the risk of cardiac disease by determining whether the noise level 132 meets one or more noise exposure criteria 134. The noise exposure criteria 134 may include one or more threshold noise magnitudes and / or one or more threshold noise durations. In some examples, the risk component 126 can associate different thresholds with different cardiac disease risk levels, such as mild, moderate, and severe, or other risk level stages / designations. In some examples, the cardiac disease risk level may be a numerical value on a scale of 1 to 10 or 1 to 100. In some examples, the cardiac disease risk level may be the probability that patient 4 will experience an exacerbation of cardiac disease within a certain time frame after noise exposure.

[0062] In some examples, different noise exposure criteria 134 may be associated with different durations. For example, a first noise exposure criterion 134 (e.g., a threshold) may be compared to one or more noise levels 132 representing instantaneous or short-term noise exposure, while a second noise exposure criterion 134 (e.g., a threshold) may be compared to noise levels 132 representing long-term or cumulative noise exposure, for example, for more than one day or over a month.

[0063] In some examples, the risk component 126 may be configured to apply noise levels 132, for example, time-series noise levels 132, as input to one or more machine learning models 136 that can output one or more values ​​indicating a probability or other cardiac disease risk level. Physiological data 138 may include values ​​of physiological parameters determined based on signals sensed via electrodes 46 and parameter sensors 106, as discussed herein. In some examples, the risk component 126 may apply physiological data as one or more additional inputs for the machine learning models 136. In some examples, the risk component 126 may apply techniques for determining cardiac disease risk based on noise levels 132 and, optionally, other physiological data 138 similar to the data described in U.S. Patent Application Publication No. 20120253207 by the same applicant, entitled “HEART FAILURE MONITORING,” which is incorporated herein in its entirety by reference. The technique described in U.S. Patent Application Publication No. 20120253207 includes applying confidence levels determined from multiple types of patient parameter data to a Bayesian belief network or other probabilistic model, which is an example of a machine learning model 136.

[0064] In some examples, the noise level 132 may include multiple noise levels experienced by patient 4 over a period of time, and the risk component 126 may determine a noise profile from them. The risk component 126 may apply the profile to a machine learning model 136 and apply the profile's features to a noise exposure criterion 134, or otherwise determine the risk of cardiac disease based on the noise profile. Alerts or other messages output to the computing device 12 regarding the risk of cardiac disease may include the noise profile, and as a result, the user may also review and evaluate the noise profile. For example, the calculations used by the risk component 126 to determine the risk of cardiac disease based on noise levels using the criteria or machine learning models described above cannot be performed by the human mind and may provide advantages in the ability system 2 to monitor the cardiovascular health of patient 4.

[0065] In some embodiments, the health management application 122 is configured to determine if a patient is asleep based on physiological parameters sensed via electrodes 46 and / or parameter sensors 106, such as ECG signals, EEG signals, respiratory signals, blood oxygenation signals, and blood pressure signals. The health management application 122 may also be configured to determine one or more sleep metrics, for example, indicating the depth or quality of sleep, while the patient is determined to be asleep based on these physiological parameters. The health management application 122 can store the sleep metrics in memory 102 as physiological data 138.

[0066] The risk component 126 can determine the patient's risk of cardiovascular disease by, for example, correlating one or more sleep metrics with one or more noise levels 132 experienced by the patient 4, for example, over time, and at least partially based on the correlation between one or more sleep metrics and one or more noise levels. Noise levels 132 are sufficient to disrupt sleep and are also likely to cause or worsen cardiovascular disease. To determine the risk of cardiovascular disease, the risk component 126 may be configured to apply correlation features or metrics to one or more criteria 134, or to apply time correlation signals as input to one or more machine learning models 136.

[0067] The impact of noise on patient 4's health may differ between daytime and nighttime. For example, noise levels of equal magnitude may have different physiological effects at night than during the day, for example, due to startle responses. Therefore, the noise component 124 can group noise levels 132 into daytime (e.g., noon to 4pm) or nighttime (e.g., midnight to 4am) groups and calculate various statistical or other representations of daytime and nighttime noise levels 132. The boundary between daytime and nighttime may be configurable by patient 4, a clinician, or other users via computing devices 12, 14. Furthermore, the risk component 126 can determine the risk of cardiac disease based on noise level 132, such that it differs depending on whether the noise level 132 is a daytime or nighttime noise level. For example, the risk component 126 may apply noise level 132 to different thresholds (e.g., daytime thresholds and nighttime thresholds) or other criteria 134, or different machine learning models 136, based on whether the noise level 132 is a daytime or nighttime noise level.

[0068] Figure 5 is a block diagram illustrating an exemplary configuration of computing device 12 that may correspond to either (or both in conjunction with) computing devices 12A and 12B of Figure 1, operating according to one or more techniques of the present disclosure. In some examples, computing device 12 may take the form of a smartphone, laptop, tablet computer, personal digital assistant (PDA), smartwatch or other wearable computing device, or a smart speaker, smart home hub or other Internet of Things (IoT) device.

[0069] As shown in the example in Figure 5, the computing device 12 may be logically divided into user space 142, kernel space 144, and hardware 146. Hardware 146 may include one or more hardware components that provide an operating environment for components running in user space 142 and kernel space 144. User space 142 and kernel space 144 may represent different sections or segmentations of memory, but kernel space 144 provides processes and threads with higher privileges than user space 142. For example, kernel space 144 may include an operating system 188 that operates with higher privileges than components running in user space 142.

[0070] As shown in Figure 5, the hardware 146 includes a processing circuit 190, a memory 192, one or more input devices 194, one or more output devices 196, one or more sensors 198, and a communication circuit 199. The computing device 12 is shown in Figure 5 as a standalone device as an example, but can be any component or system including a processing circuit or other suitable computing environment for executing software instructions, and does not necessarily have to include one or more elements shown in Figure 5, for example.

[0071] The processing circuit 190 is configured to perform functions and / or process instructions within the computing device 12. For example, the processing circuit 190 may be configured to receive and process instructions stored in memory 192 that provide functions for components included in kernel space 144 and user space 142 to perform one or more operations in accordance with the art of this disclosure. Examples of the processing circuit 190 include any one or more microprocessors, controllers, GPUs, TPUs, DSPs, ASICs, FPGAs, or equivalent discrete or integrated logic circuits.

[0072] Memory 192 may be configured to store information within the computing device 12 for processing during the operation of the computing device 12. In some examples, memory 192 is described as a computer-readable storage medium. In some examples, memory 192 includes temporary memory or volatile memory. Examples of volatile memory include random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), and other forms of volatile memory known in the art. Memory 192 also, in some examples, includes one or more memories configured for long-term storage of information, for example, non-volatile memory elements. Practical examples of such non-volatile memory elements include magnetic hard disks, optical disks, floppy disks, flash memory, or electrically programmable memories (EPROM) or electrically erasable and programmable memories (EEPROM) memory. In some examples, memory 192 includes cloud-related storage.

[0073] One or more input devices 194 of the computing device 12 may receive input from, for example, patient 4 or another user. Examples of inputs include tactile input, voice input, dynamic input, and visual input. Examples of input devices 194 may include a mouse, keyboard, voice response system, camera, button, control pad, microphone, presence-aware or touch-sensing component (e.g., screen), or any other device for detecting input from a user or machine. In some examples, the microphone of the input device 194 may function as a sound sensor that senses ambient noise simultaneously with the sound sensor 108 of the IMD 10 for the purpose of calibrating the determination of the noise level 132 by the IMD 10 as described above.

[0074] One or more output devices 196 of the computing device 12 may generate output to, for example, patient 4 or another user. Examples of output include tactile output, haptic output, audio output, and visual output. The output devices 196 of the computing device 12 may include a presence screen, a sound card, a video graphics adapter card, a speaker, a cathode ray tube (CRT) monitor, a liquid crystal display (LCD), light-emitting diodes (LEDs), or any type of device for generating tactile output, audio output, and / or visual output. In some examples, the speaker of the output device 196 may generate a predetermined noise for the purpose of calibrating the determination of the noise level 132 by the IMD 10, as described above.

[0075] One or more sensors 198 of the computing device 12 may sense physiological parameters or signals of patient 4. The sensors 198 may include electrodes, accelerometers (e.g., triaxial accelerometers), optical sensors, impedance sensors, temperature sensors, pressure sensors, heart sound sensors (e.g., microphones), and other sensors, as well as sensing circuits (e.g., including ADCs) similar to those described above with respect to IMD 10 and Figure 4.

[0076] The communication circuit 199 of the computing device 12 may communicate with other devices by sending and receiving data. The communication circuit 199 may include a network interface card such as an Ethernet card, an optical transceiver, a radio frequency transceiver, or any other type of device capable of sending and receiving information. For example, the communication circuit 199 may include a wireless transceiver configured to communicate in accordance with standards or protocols such as 3G, 4G, 5G, WiFi (e.g., 802.11 or 802.15 ZigBee), Bluetooth®, or Bluetooth® Low Energy (BLE).

[0077] As shown in Figure 5, the health management application 150 runs in the user space 142 of the computing device 12. The health management application 150 can be logically divided into a presentation layer 152, an application layer 154, and a data layer 156. The presentation layer 152 may include a user interface (UI) component 160 that generates and renders the user interface of the health management application 150.

[0078] The application layer 154 may include, but is not limited to, a risk component 170, a location service 174, and a clock 176. The risk component 170 can determine the risk of cardiac disease based on a noise level 180 received from the IMD 10 via a communication circuit 199. For example, the risk component 170 can determine the risk of cardiac disease based on a comparison of the noise level 180 with one or more criteria 182 and / or the application of one or more noise levels 180 to one or more machine learning models 184, in the manner described above with respect to the IMD 10 and Figure 4. In some examples, the risk component 170 can determine the risk of cardiac disease by applying physiological data 186 of patient 4 to the criteria 182 and / or models 184 in addition to the noise level 180, in the manner described above with respect to the IMD 10 and Figure 4.

[0079] Physiological data 186 may include data collected by IMD 10 as described above and received via communication circuit 199. In some examples, physiological data 186 may include data collected by processing circuit 190 via input device 194 and sensor 198. For example, sensing data from computing device 12 may include one or more of the following: activity level, walking / running distance, resting energy, activity energy, exercise minutes, orthostatic quantification, obesity level, body weight index, heart rate, low heart rate events, high heart rate events, and / or irregular heart rate events, heart rate variability, walking heart rate, heart rate series, digitized ECG, blood oxygen saturation, blood pressure (systolic and / or diastolic), respiratory rate, maximum oxygen volume, blood glucose, peripheral perfusion, and sleep patterns. In some examples, patient data may include responses to queries entered by patient 4 via input device 194 and presented by health management application 150 regarding patient 4's condition via output device 196.

[0080] Location service 174 can determine the location of computing device 12, thereby determining the estimated location of patient 4. Location service 178 may use GPS data, multilateration, and / or any other well-known techniques for locating computing devices. Clock 176 can generate data indicating the time associated with patient 4's location. Furthermore, based on timestamp data from IMD 10, processing circuit 190 can associate the noise level 180 received from IMD 10 with location and time. Together with cardiac disease risk information, output device 196 can present noise levels 180 determined to be excessive or contributing to cardiac disease risk, along with their associated locations and times. Based on this information, patient 4 or other interested users can identify the source of noise exposure.

[0081] Figure 6 is a block diagram showing a logical perspective of a healthcare management service (HMS) 26 operated by a computing system 20 (Figure 1). An exemplary implementation typically includes various hardware / software components that operate on the processing circuit 22 of the computing system 20 (Figure 1) and are generally configured to be network-accessible for sending and receiving various data to and from patient medical devices (e.g., IMD 10), their local devices (e.g., computing devices 12), and other users' computing devices 14.

[0082] Figure 6 provides an operational perspective of HMS26 when hosted as a cloud-based platform. In the example in Figure 6, the components of HMS26 are arranged according to multiple logical layers that perform the techniques of this disclosure. Each layer may be implemented by one or more modules consisting of hardware, software, or a combination of hardware and software.

[0083] Computing devices such as computing devices 12 and 14 in Figure 1 can operate as clients communicating with HMS26 via interface layer 202. Computing devices typically run client software applications such as desktop applications, mobile applications, and web applications, for example, a health management application 150. Interface layer 202 represents a set of application programming interfaces (APIs) or protocol interfaces presented and supported by HMS26 for client software applications. Interface layer 202 may be implemented using one or more web servers.

[0084] As shown in Figure 6, the HMS26 also includes an application layer 204, which represents a set of services 210 for performing the functions attributed to the HMS26 as described herein. The application layer 204 receives information from client applications, such as noise levels determined by the IMD10, and possibly the relevant location and time of patient 4 determined by the computing device 12, and stores them as noise levels 240. The application layer 204 may also receive physiological data 246 from the IMD10 and the computing device 12. The application layer 204 processes the information according to one or more of the services 210 in order to respond to the information. The application layer 204 may be implemented as one or more discrete software services 210 running on one or more application servers (e.g., physical or virtual machines). That is, the application servers provide the runtime environment for the execution of the services 210. In some examples, the functions of the interface layer 202 and the application layer 204 described above may run on the same server. The services 210 may communicate via a logical service bus 212. The service bus 212 generally represents a set of logical interconnections or interfaces that enable different services 210 to send messages to other services, such as through a publish / subscription communication model.

[0085] The data layer 206 of HMS26 provides persistence of information within HMS26 using one or more data repositories 220. A data repository 220 can generally be any data structure or software that stores and / or manages data. Examples of data repositories 220 include, but are not limited to, relational databases, multidimensional databases, maps, and hash tables.

[0086] As shown in Figure 6, each service 230-234 is implemented in a modular form within the HMS26. Although shown as a separate module for each service, in some embodiments, the functionality of two or more services may be combined into a single module or component. Each of services 230-234 may be executed in software, hardware, or a combination of hardware and software. Furthermore, services 230-234 may generally be executed as standalone devices for running on one or more physical processors, as separate virtual machines or containers, as processes, threads, or as software instructions.

[0087] The cardiovascular disease risk analysis service 230 may perform any of the techniques described herein to determine cardiovascular disease risk based on the application of noise levels 240 (and optionally physiological data 246) to one or more criteria 242 and / or machine learning models 244. The machine learning model configuration service 232 may train, validate, and otherwise configure the machine learning models 244 using training data 248. The training data 248 may include a large number of sets of noise levels (and optionally time corresponding to physiological data) from various subjects labeled with cardiovascular disease risk levels. Exemplary machine learning techniques that may be employed to generate one or more models 244 may include a variety of learning styles, such as supervised learning, unsupervised learning, and semi-supervised learning. Representative types of algorithms include Bayesian algorithms, clustering algorithms, decision tree algorithms, regularization algorithms, regression algorithms, example-based algorithms, artificial neural network algorithms, deep learning algorithms, and dimensionality reduction algorithms.Various examples of specific algorithms include Bayesian linear regression, boosted decision tree regression, and neural network regression, backpropagation neural networks, convolutional neural networks (CNNs), long short-term networks (LSTMs), a priori algorithms, K-means clustering, k-nearest neighbor method (kNN), learning vector quantization (LVQ), self-organizing maps (SOMs), locally weighted learning (LWL), ridge regression, least absolute shrinkage and selection operator (LASSO), elastic networks, least-angle regression (LARS), principal component analysis (PCA), and principal component regression (PCR).

[0088] Figure 7 is a flowchart illustrating exemplary operation of one or more techniques of this disclosure for generating a user-facing output of a patient's cardiac disease risk caused by ambient noise in the patient's environment. The exemplary operation in Figure 7 is described as being performed by a processing circuit which may comprise one or more of the processing circuits 100 of the IMD 10, the processing circuit 190 of the computing device 12, or the processing circuit 22 of the computing system 20.

[0089] As shown in the example in Figure 7, the processing circuit determines one or more noise levels based on sound signals generated by one or more sound sensors of the IMD 10 (300). The noise level may be magnitude (e.g., in decibels), a representative value determined from such magnitude over several periods, a representation of the time during which the magnitude exceeded one or more thresholds, or any other noise level value as described herein. The processing circuit determines the risk of cardiac disease based on the noise level (302). The risk may be a numerical or qualitative value of the magnitude of the risk, or the probability of developing or worsening a cardiac disease or contributing condition such as heart failure, arrhythmia, or hypertension, as described herein. The processing circuit may generate an output for the cardiac disease risk, e.g., an alert or other report (304). The output corresponding to the cardiac disease risk may be via communication with the patient 4's computing device 12 or another user's computing device 14.

[0090] In some examples, the processing circuit may create a daily graph of time above a decibel threshold, where the decibel threshold corresponds to a significant noisy environment. One or more computing devices are configured to display graphs and / or other information related to noise exposure and cardiac disease risk. In some examples, additional or alternative graphs may include representative values ​​of noise levels for periods graphed over longer time scales.

[0091] Figure 8 is a flowchart illustrating an exemplary operation for generating a patient noise profile over a period of time using one or more techniques described herein. The exemplary operation in Figure 8 is described as being performed by a processing circuit which may comprise one or more of the processing circuits 100 of the IMD 10, the processing circuit 190 of the computing device 12, or the processing circuit 22 of the computing system 20.

[0092] As shown in the example in Figure 8, the processing circuit determines one or more noise levels over a period of time, such as one hour or one day, based on sound signals generated by one or more sound sensors of the IMD 10 (400). The processing circuit creates a noise profile based on the noise levels (402) and determines the patient's risk of cardiac disease based on the profile (404). The profile can characterize the amount of noise exposure over the period based on the time series of noise levels during that period. The processing circuit can determine the risk of cardiac disease based on the noise profile by applying the profile as a time series of noise levels to a machine learning model or by applying the features of the profile to a noise exposure criterion. The processing circuit can generate an output corresponding to the risk of cardiac disease, for example, via communication with the patient's computing device 12 or another user's computing device 14 (304). In some cases, the output, such as an alert or report, may include a representation of the profile, such as a graph.

[0093] In one or more examples, the described techniques may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functionality may 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 non-temporary computer-readable media, corresponding to tangible media such as data storage media (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 that can be accessed by a computer).

[0094] Instructions may be executed by one or more processors, such as digital signal processors (DSPs), general-purpose microprocessors, application-specific integrated circuits (ASICs), field-programmable logic arrays (FPGAs), or other equivalent integrated circuits or discrete logic circuits. Therefore, the terms “processor” or “processing circuit” as used herein may refer to any of the aforementioned structures or any other physical structure suitable for implementing the described technology. Furthermore, the technology may be fully implemented by one or more circuits or logic elements.

[0095] Various embodiments are described. These embodiments and other embodiments are within the scope of the following claims.

[0096] The following examples are a non-limiting list of one or more technical sections of this disclosure.

[0097] Example 1. A medical device system comprising: a medical device having one or more sound sensors configured to generate an audio signal containing noise experienced by a patient; and a processing circuit configured to determine one or more noise levels experienced by the patient based on the audio signal, determine the patient's risk of cardiac disease based at least partially on one or more noise levels, and generate an output corresponding to the risk of cardiac disease for the patient or another user's computing device.

[0098] Example 2. The medical device system according to Example 1, wherein, in order to determine one or more noise levels, the processing circuit is configured to determine a plurality of noise levels experienced by the patient over a period of time, and the processing circuit is further configured to create a patient noise profile, which includes at least a plurality of determined noise levels and a corresponding timestamp for each of the plurality of noise levels, based on the plurality of noise levels determined during the period, and to determine the patient's risk of cardiac disease based at least in part on the noise profile.

[0099] Example 3. The medical device system according to Example 2, wherein the processing circuit is further configured to output a patient noise profile for display on a computing device.

[0100] Example 4. A medical device system according to one or more of Examples 1 to 3, wherein one or more noise levels are determined during one or more regularly occurring predetermined periods.

[0101] Example 5. The medical device system according to Example 4, wherein one or more regularly occurring predetermined periods include either a nighttime period or a daytime period or both.

[0102] Example 6. The medical device system according to Example 5, wherein, in order to determine the risk of cardiac disease, the processing circuit is configured to compare one or more noise levels during the nighttime period with one or more first criteria, and one or more noise levels during the daytime period with one or more second criteria that are different from the one or more first criteria.

[0103] Example 7. A medical device system according to any one or more of Examples 1 to 6, wherein the processing circuit is further configured to determine that the patient's activity level is below a threshold and to determine one or more noise levels experienced by the patient based on the sound signal generated when the patient's activity level is below a threshold.

[0104] Example 8. The medical device system according to Example 7, comprising an accelerometer configured to generate a patient's motion signal, and a processing circuit that determines the activity level based on the motion signal.

[0105] Example 9. A medical device system according to any one or more of Examples 1 to 8, wherein the processing circuit is further configured to identify one or more noise conditions that cause one or more noise levels experienced by the patient.

[0106] Example 10. The medical device system according to Example 9, wherein, in order to identify one or more noise conditions, the processing circuit is further configured to determine the location of a patient associated with a noise level via global positioning system data.

[0107] Example 11. The medical device system according to Example 9 or 10, further comprising a clock, wherein the processing circuit is further configured to determine a time associated with a noise level via the clock in order to identify one or more noise conditions.

[0108] Example 12. A medical device system according to any one or more of Examples 1 to 11, comprising one or more additional sensors configured to generate one or more additional signals indicating one or more physiological parameters of a patient, and further configured a processing circuit to determine that the patient is asleep based on one or more physiological parameters, measure one or more sleep metrics while the patient is determined to be asleep based on one or more physiological parameters, correlate one or more sleep metrics with one or more noise levels experienced by the patient, and determine the patient's risk of cardiac disease at least in part based on the correlation between one or more sleep metrics and one or more noise levels.

[0109] Example 13. A medical device system according to one or more of Examples 1 to 12, wherein the computing device is configured to emit one or more sounds having a known noise level, and the processing circuit is configured to calibrate one or more sound sensors of a medical device based on one or more sounds emitted from the computing device.

[0110] Example 14. A medical device system according to any one or more of Examples 1 to 13, wherein one or more sound sensors are a first set of one or more sound sensors, the sound signal includes a first sound signal, and one or more noise levels include a first set of one or more noise levels, and the medical device system further comprises a computing device having a second set of one or more sound sensors configured to generate a second sound signal, and the processing circuit is configured to determine a second set of one or more noise levels based on the second set of one or more noise levels, and to calibrate the first set of one or more sound sensors based on the second set of one or more noise levels.

[0111] Example 15. A medical device system according to one or more of Examples 1 to 14, wherein one or more sound sensors are configured to continuously generate sound signals.

[0112] Example 16. The medical device system according to Example 15, wherein the processing circuit is configured to continuously determine the noise level based on an audio signal.

[0113] Example 17. The medical device system according to Example 15, wherein the processing circuit is configured to determine the noise level at predetermined intervals.

[0114] Example 18. A medical device system according to one or more of Examples 1 to 17, wherein a processing circuit is configured to determine whether one or more noise levels meet one or more noise exposure criteria in order to determine the risk of cardiac disease based at least partially on one or more noise levels.

[0115] Example 19. The medical device system according to Example 18, wherein one or more noise exposure criteria include the magnitude of a threshold noise.

[0116] Example 20. A medical device system according to Example 18 or 19, wherein one or more noise exposure criteria include a threshold noise duration.

[0117] Example 21. A medical device system according to one or more of Examples 1 to 20, wherein the risk of cardiac disease includes one or more of the following: risk of heart failure, risk of hypertension, or risk of arrhythmia.

[0118] Example 22. A medical device system according to one or more of Examples 1 to 21, wherein the processing circuit is configured to apply one or more noise levels to a machine learning model in order to determine the risk of cardiac disease.

[0119] Example 23. The medical device system according to Example 22, further comprising one or more additional sensors configured to generate one or more additional signals indicating one or more physiological parameters of a patient, and a processing circuit further configured to determine one or more additional inputs for a machine learning model based on the one or more additional signals.

[0120] Example 24. A medical device system according to one or more of Examples 1 to 23, wherein the medical device is an implantable medical device configured for subcutaneous implantation.

[0121] Example 25. The medical device system according to Example 24, comprising: a housing having a length from a first end to a second end, a width, and a depth, wherein the length is greater than the width and the width is greater than the depth, and one or more sound sensors are located inside the housing; a first electrode located at or near the first end of the housing; a second electrode located at or near the second end of the housing; and a circuit located inside the housing and configured to sense an electrocardiogram via the first and second electrodes.

[0122] Example 26. A medical device system according to one or more of Examples 1 to 25, wherein the medical device comprises a processing circuit.

[0123] Example 27. A medical device system according to any one or more of Examples 1 to 25, comprising: a processing circuit for a medical device configured to determine one or more noise levels; and at least one processing circuit for a computing device or cloud computing system that communicates with a computing device via a network and is configured to determine the risk of cardiac disease and generate an output.

[0124] Example 28. A medical device comprising an implantable cardiac monitor, comprising a sealed housing configured for subcutaneous implantation in a patient, wherein the housing has a length from a first end to a second end, a width, and a depth, the length being greater than the width and the width being greater than the depth, the length being in the range of 5 mm to 60 mm, the width being in the range of 5 mm to 15 mm, and the depth being in the range of 5 mm to 15 mm; a processing circuit within the housing; a power supply located within the housing and operably coupled to the processing circuit; a memory located within the housing and operably coupled to the processing circuit; a sensing circuit located within the housing and operably coupled to the processing circuit; a first electrode located at or near the first end of the housing and operably coupled to the sensing circuit; and a second electrode located at or near the second end of the housing and operably coupled to the sensing circuit, as described in one or more of Examples 1 to 23.

[0125] Example 29. A method comprising: a processing circuit of a medical device system including a medical device, determining one or more noise levels experienced by a patient based on sound signals generated by a sound sensor of the medical device; the processing circuit determining the patient's risk of cardiac disease based at least partially on one or more noise levels; and the processing circuit generating an output corresponding to the risk of cardiac disease for the patient or another user's computing device.

[0126] Example 30. The method according to Example 29, wherein determining one or more noise levels includes creating a patient noise profile, which includes at least several determined noise levels and corresponding timestamps for each of the multiple noise levels, based on the multiple noise levels determined during the period, and determining the patient's risk of cardiac disease based at least in part on the noise profile.

[0127] Example 31. The method according to Example 30, further comprising outputting a patient's noise profile for display on a computer device by a processing circuit.

[0128] Example 32. Determining one or more noise levels is a method according to any one or more of Examples 29 to 31, comprising determining one or more noise levels during one or more regularly occurring predetermined periods.

[0129] Example 33. The method according to Example 32, wherein one or more regularly occurring predetermined periods include either a nighttime period or a daytime period or both.

[0130] Example 34. The method according to Example 33, wherein determining the risk of cardiac disease includes comparing one or more noise levels during the nighttime period with one or more first criteria, and comparing one or more noise levels during the daytime period with one or more second criteria that are different from the one or more first criteria.

[0131] Example 35. The method according to any one or more of Examples 29 to 34, further comprising determining by a processing circuit that the patient's activity level is below a threshold, and determining one or more noise levels, which includes determining one or more noise levels experienced by the patient based on the sound signal generated when the patient's activity level is below a threshold.

[0132] Example 36. The method according to Example 35, further comprising a processing circuit determining an activity level based on a motion signal generated by an accelerometer of a medical device.

[0133] Example 37. The method according to any one or more of Examples 29 to 36, further comprising using a processing circuit to identify one or more noise conditions that cause one or more noise levels experienced by the patient.

[0134] Example 38. The method according to Example 37, wherein identifying one or more noise conditions includes determining the location of a patient associated with a noise level via Global Positioning System data.

[0135] Example 39. The method according to Example 37 or 38, wherein identifying one or more noise conditions includes determining the time associated with the noise level via a clock.

[0136] Example 40. The method according to any one or more of Examples 29 to 39, wherein the medical device comprises one or more additional sensors configured to generate one or more additional signals indicating one or more physiological parameters of a patient, and the method comprises: determining by a processing circuit that the patient is asleep based on one or more physiological parameters; measuring one or more sleep metrics by the processing circuit while the patient is determined to be asleep based on one or more physiological parameters; correlating one or more sleep metrics with one or more noise levels experienced by the patient; and determining the patient's risk of cardiac disease by the processing circuit, at least in part, based on the correlation between one or more sleep metrics and one or more noise levels.

[0137] Example 41. The method according to any one or more of Examples 29 to 40, wherein the computing device is configured to emit one or more sounds having a known noise level, and the method further comprises a processing circuit calibrating one or more sound sensors of a medical device based on one or more sounds emitted from the computing device.

[0138] Example 42. The method according to any one or more of Examples 29 to 41, wherein one or more sound sensors is a first set of one or more sound sensors, sound signal includes a first sound signal, one or more noise levels include a first set of one or more noise levels, and computing device includes a second set of one or more sound sensors configured to generate a second sound signal, and the method further comprises determining a second set of one or more noise levels based on the second sound signal by a processing circuit, and calibrating the first set of one or more sound sensors based on the second set of one or more noise levels by a processing circuit.

[0139] Example 43. The method according to one or more of Examples 29 to 42, wherein one or more sound sensors are configured to continuously generate sound signals.

[0140] Example 44. The method according to Example 43, wherein determining one or more noise levels comprises continuously determining one or more noise levels based on an audio signal.

[0141] Example 45. The method of Example 44, wherein determining one or more noise levels includes determining one or more noise levels at predetermined intervals based on an audio signal.

[0142] Example 46. Determining cardiac disease risk based at least partially on one or more noise levels, the method according to any one or more of Examples 29 to 45, comprising determining whether one or more noise levels meet one or more noise exposure criteria.

[0143] Example 47. The method according to Example 46, wherein one or more noise exposure criteria include the magnitude of threshold noise.

[0144] Example 48. One or more noise exposure criteria, including a threshold noise duration, as described in Example 46 or 47.

[0145] Example 49. The method according to one or more of Examples 29 to 48, wherein the risk of cardiovascular disease includes one or more of the following: risk of heart failure, risk of hypertension, or risk of arrhythmia.

[0146] Example 50. The method according to any one or more of Examples 28 to 48, wherein determining the risk of cardiac disease involves applying one or more noise levels to a machine learning model.

[0147] Example 51. The method according to Example 50, wherein the medical device comprises one or more additional sensors configured to generate one or more additional signals indicating one or more physiological parameters of a patient, and the method further comprises a processing circuit determining one or more additional inputs for a machine learning model based on the one or more additional signals.

[0148] Example 52. The method according to one or more of Examples 29 to 51, wherein the medical device is an implantable medical device configured for subcutaneous implantation.

[0149] Example 53. The method according to Example 52, wherein the implantable medical device comprises a housing having a length from a first end to a second end, a width, and a depth, wherein the length is greater than the width and the width is greater than the depth, and one or more sound sensors are located inside the housing; a first electrode located at or near the first end of the housing; a second electrode located at or near the second end of the housing; and a circuit located inside the housing and configured to sense an electrocardiogram via the first and second electrodes.

[0150] Example 54. The method according to one or more of Examples 29 to 53, wherein the medical device comprises a processing circuit.

[0151] Example 55. The method according to any one or more of Examples 29 to 54, wherein the processing circuit comprises a processing circuit of a medical device configured to determine one or more noise levels, and at least one processing of a computing device or cloud computing system that communicates with a computing device via a network and is configured to determine the risk of cardiac disease and generate an output.

[0152] Example 56. A non-temporary computer-readable storage medium containing instructions that, when executed, cause a processing circuit of a medical device system to perform the method described in any of Examples 19 to 55.

Claims

1. A medical device system, A medical device comprising one or more sound sensors configured to generate an audio signal containing noise experienced by the patient, A processing circuit is provided, and the processing circuit is Based on the aforementioned sound signal, one or more noise levels experienced by the patient are determined. The patient's risk of cardiac disease is determined based at least partially on one or more noise levels. A medical device system configured to generate an output corresponding to the aforementioned risk of heart disease to the patient's or another user's computing device.

2. To determine the one or more noise levels, the processing circuit is configured to determine a plurality of noise levels experienced by the patient over a period of time, and the processing circuit is configured Based on the multiple noise levels determined during the aforementioned period, a noise profile of the patient is created, including at least the multiple determined noise levels and a corresponding timestamp for each of the multiple noise levels. The medical device system according to claim 1, further configured to determine the patient's risk of cardiac disease based at least in part on the noise profile.

3. The medical device system according to claim 2, wherein the processing circuit is further configured to output the patient's noise profile for display on the computing device.

4. The medical device system according to any one or more of claims 1 to 3, wherein the one or more noise levels are determined during one or more regularly occurring predetermined periods.

5. The medical device system according to claim 4, wherein the one or more regularly occurring predetermined periods include either a nighttime period or a daytime period or both.

6. To determine the risk of the aforementioned heart disease, the processing circuit, The one or more noise levels during the aforementioned nighttime period are compared with the first one or more references, The medical device system according to claim 5, configured to compare the one or more noise levels during the daytime with one or more second criteria that are different from the first one or more criteria.

7. The aforementioned processing circuit is The activity level of the aforementioned patient was determined to be below the threshold, A medical device system according to any one or more of claims 1 to 6, further configured to determine one or more noise levels experienced by the patient based on the sound signal generated when the patient's activity level is below the threshold.

8. The medical device system according to claim 7, wherein the medical device comprises an accelerometer configured to generate a motion signal of the patient, and the processing circuit determines the activity level based on the motion signal.

9. The medical device system according to any one or more of claims 1 to 8, wherein the processing circuit is further configured to identify one or more noise conditions that cause the one or more noise levels experienced by the patient.

10. The medical device system according to claim 9, wherein the processing circuit is further configured to determine the location of the patient associated with the noise level via global positioning system data in order to identify one or more noise conditions.

11. The medical device system according to claim 9 or 10, further comprising a clock, wherein the processing circuit is further configured to determine a time associated with the noise level via the clock in order to identify the one or more noise states.

12. The medical device comprises one or more additional sensors configured to generate one or more additional signals indicating one or more physiological parameters of the patient, and the processing circuit comprises Based on one or more of the above physiological parameters, it is determined that the patient is asleep. While the patient is determined to be asleep based on one or more of the aforementioned physiological parameters, one or more sleep metrics are measured, The one or more sleep metrics are correlated with the one or more noise levels experienced by the patient. A medical device system according to any one or more of claims 1 to 11, further configured to determine the patient's risk of cardiac disease based at least in part on the correlation between the one or more sleep metrics and the one or more noise levels.

13. The medical device system according to any one or more of claims 1 to 12, wherein the computing device is configured to emit one or more sounds having a known noise level, and the processing circuit is configured to calibrate one or more sound sensors of the medical device based on the one or more sounds emitted from the computing device.

14. The one or more sound sensors are a first set of one or more sound sensors, the sound signal includes a first sound signal, the one or more noise levels include a first set of one or more noise levels, the medical device system further comprises the computing device comprising a second set of one or more sound sensors configured to generate a second sound signal, and the processing circuit is Based on the second sound signal, one or more second noise levels are determined. A medical device system according to any one or more of claims 1 to 13, configured to calibrate the first set of one or more sound sensors based on the second set of one or more noise levels.

15. It is a method, A processing circuit of a medical device system, including a medical device, determines one or more noise levels experienced by a patient based on sound signals generated by the sound sensor of the medical device. The processing circuit determines the patient's risk of cardiac disease at least partially based on one or more noise levels, A method comprising generating an output corresponding to the risk of heart disease for the patient or another user's computing device using the processing circuit.

Images