Personalization of cochlea health monitoring

Abstract

Presented herein are techniques for monitoring a condition associated with a recipient of a medical device. A model is trained based on historical electrophysiological measurements associated with a recipient of a medical device over a period of time. One or more current electrophysiological measurements associated with the recipient of a medical device are obtained. A condition associated with the recipient is monitored based on the one or more current electrophysiological measurements and the model.

Description

Atty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 PERSONALIZATION OF COCHLEA HEALTH MONITORING BACKGROUND Field of the Invention

[0001] The present invention relates generally to personalization of cochlea health monitoring. Related Art

[0002] Medical devices have provided a wide range of therapeutic benefits to recipients over recent decades. Medical devices can include internal or implantable components / devices, external or wearable components / devices, or combinations thereof (e.g., a device having an external component communicating with an implantable component). Medical devices, such as traditional hearing aids, partially or fully-implantable hearing prostheses (e.g., bone conduction devices, mechanical stimulators, cochlear implants, etc.), pacemakers, defibrillators, functional electrical stimulation devices, and other medical devices, have been successful in performing lifesaving and / or lifestyle enhancement functions and / or recipient monitoring for a number of years.

[0003] The types of medical devices and the ranges of functions performed thereby have increased over the years. For example, many medical devices, sometimes referred to as “implantable medical devices,” now often include one or more instruments, apparatus, sensors, processors, controllers or other functional mechanical or electrical components that are permanently or temporarily implanted in a recipient. These functional devices are typically used to diagnose, prevent, monitor, treat, or manage a disease / injury or symptom thereof, or to investigate, replace or modify the anatomy or a physiological process. Many of these functional devices utilize power and / or data received from external devices that are part of, or operate in conjunction with, implantable components. SUMMARY

[0004] In one aspect, a first method is provided. The first method comprises: obtaining one or more current electrophysiological measurements associated with a recipient of a medical device; and monitoring a condition associated with the recipient based on the one or more current electrophysiological measurements and a history of electrophysiological measurements associated with the recipient.

[0005] In another aspect, a second method is provided. The second method comprises: obtaining an impedance dataset associated with a recipient of a medical device, the impedanceAtty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 dataset including impedance measurements collected over a period of time; training a model using the impedance dataset; and monitoring a condition associated with the recipient based on the model.

[0006] In another aspect, a one or more non-transitory computer readable storage media are provided. The one or more non-transitory computer readable storage media comprise instructions that when executed by a processor, cause the processor to: obtain one or more electrophysiological measurements associated with a cochlea of a recipient; obtain historical data associated with prior electrophysiological measurements obtained from the cochlea; and analyze the one or more electrophysiological measurements based on the historical data.

[0007] In another aspect, a system is provided. The system includes: a memory; at least one processor operable coupled to the display screen and the memory, wherein the at least one processor is configured to: obtain one or more electrophysiological measurements associated with a cochlea of a recipient; obtain historical data associated with prior electrophysiological measurements obtained from the cochlea; analyze the one or more electrophysiological measurements based on the historical data. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Embodiments of the present invention are described herein in conjunction with the accompanying drawings, in which:

[0009] FIG. 1A is a schematic diagram illustrating a cochlear implant system with which aspects of the techniques presented herein can be implemented;

[0010] FIG. 1B is a side view of a recipient wearing a sound processing unit of the cochlear implant system of FIG.1A;

[0011] FIG.1C is a schematic view of components of the cochlear implant system of FIG.1A;

[0012] FIG.1D is a block diagram of the cochlear implant system of FIG.1A;

[0013] FIG.1E is a schematic diagram illustrating a computing device with which aspects of the techniques presented herein can be implemented;

[0014] FIG. 2A is an exemplary graph illustrating impedance fluctuations associated with a first recipient of a medical device, according to embodiments described herein;Atty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1

[0015] FIG. 2B is an exemplary graph illustrating impedance fluctuations associated with a second recipient of a medical device, according to embodiments described herein;

[0016] FIG. 2C is an exemplary graph illustrating impedance fluctuations associated with a third recipient of a medical device, according to embodiments described herein;

[0017] FIG. 2D is an exemplary graph illustrating impedance fluctuations associated with a fourth recipient of a medical device, according to embodiments described herein;

[0018] FIG.2E is an exemplary graph illustrating a range of impedances values occurring per recipient within a day, according to embodiments described herein;

[0019] FIG. 2F illustrates an exemplary graph in which the impedance values are separated into a resistive part and a capacitive part, according to embodiments described herein;

[0020] FIG. 3 is a diagram illustrating the generation of a recipient-dependent anomaly detection model, according to embodiments described herein;

[0021] FIG. 4 is a block diagram illustrating using a recipient-dependent model to classify a datapoint associated with a recipient as normal or anomalous, according to embodiments described herein;

[0022] FIG.5 is a flow diagram illustrating a method of monitoring a condition of a recipient of a medical device, according to embodiments described herein;

[0023] FIG. 6 is a flow diagram of a method for monitoring a condition associated with a recipient based on a model, according to embodiments described herein;

[0024] FIG. 7 is a flow diagram illustrating a method of analyzing one or more electrophysiological measurements based on historical data associated with prior electrophysiological measurements associated with a recipient, according to embodiments described herein;

[0025] FIG. 8 is a schematic diagram illustrating a vestibular stimulator system with which aspects of the techniques presented herein can be implemented; and

[0026] FIG.9 is a schematic diagram illustrating a retinal prosthesis system with which aspects of the techniques presented herein can be implemented. DETAILED DESCRIPTION

[0027] Presented herein are techniques for personalized monitoring of a recipient of an implantable medical device. The personalized recipient monitoring, which can includeAtty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 monitoring of a condition of a recipient (e.g., cochlea health), monitoring of a status of the implantable medical device (e.g., auditory prosthesis), etc., is based on both current data associated (e.g., obtained from) the recipient, as well as historical data associated with the recipient. In certain embodiments, a model is trained based on historical data associated with the recipient (e.g., electrophysiological measurement data, such as impedance measurement data, over a period of time) and the model is used to analyze similar current data associated with the recipient and, accordingly, monitor the recipient. This analysis can, in turn, be used to monitor a “condition” or “status” of the recipient. As used herein, monitoring a “condition” or “status” of a recipient includes monitoring a health condition of a recipient, monitoring a condition or status of an implantable medical device implanted in or worn by the recipient, etc.

[0028] Current methods for monitoring of cochlea health look at absolute values of change in extracted biomarkers (e.g., electrophysiological measurement data, such impedance measurement data, etc.). However, it has been discovered that variations in biomarkers, such as impedances, are highly recipient-dependent and parameter changes are not necessarily linked to alarming clinical events. For example, there can be recipient differences in the changes in short-term impedances during the day and in the amount of passivation that occurs overnight when the electrodes are not stimulated. In addition, longer term impedance fluctuations can vary from recipient to recipient.

[0029] Existing methods for monitoring recipient health apply a “one-size-fits-all” paradigm and do not consider the “normal” variance of parameters for each individual. Since “normal” impedance values can vary (sometimes significantly) between recipients, high impedance values for a recipient are not necessarily associated with a clinically relevant event. A system that sets an alarm at a threshold impedance level for all recipients can result in false alarms for recipients that normally experience higher impedance values. Techniques described herein provide for an alarm system that can be adjusted to the individual norm of impedance values for a recipient to avoid false alarms in subjects with a larger range of impedances while still being sensitive to changes in subjects with a very narrow range of impedances.

[0030] In addition, techniques described herein provide for separating impedance into access resistance and polarization components, which indicate different temporal patterns that represent different biological processes. As such, techniques described herein provide for an alarm system in which an abnormal variation is both recipient-dependent and impedance component-dependent.Atty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1

[0031] There are a number of different types of devices in / with which embodiments of the present invention can be implemented. Merely for ease of description, the techniques presented herein are primarily described with reference to a specific device in the form of a cochlear implant system. However, it is to be appreciated that the techniques presented herein can also be partially or fully implemented by any of a number of different types of devices, including consumer electronic device (e.g., mobile phones), wearable devices (e.g., smartwatches), hearing devices, implantable medical devices, consumer electronic devices, etc. As used herein, the term “hearing device” is to be broadly construed as any device that acts on an acoustical perception of an individual, including to improve perception of sound signals, to reduce perception of sound signals, etc. In particular, a hearing device can deliver sound signals to a user in any form, including in the form of acoustical stimulation, mechanical stimulation, electrical stimulation, etc., and / or can operate to suppress all or some sound signals. As such, a hearing device can be a device for use by a hearing-impaired person (e.g., hearing aids, middle ear auditory prostheses, bone conduction devices, direct acoustic stimulators, electro-acoustic hearing prostheses, auditory brainstem stimulators, bimodal hearing prostheses, bilateral hearing prostheses, dedicated tinnitus therapy devices, tinnitus therapy device systems, combinations or variations thereof, etc.), a device for use by a person with normal hearing (e.g., consumer devices that provide audio streaming, consumer headphones, earphones, and other listening devices), a hearing protection device, etc. In other examples, the techniques presented herein can be implemented by, or used in conjunction with, various implantable medical devices, such as visual devices (i.e., bionic eyes), sensors, pacemakers, drug delivery systems, defibrillators, functional electrical stimulation devices, catheters, seizure devices (e.g., devices for monitoring and / or treating epileptic events), sleep apnea devices, electroporation devices, etc.

[0032] FIGs.1A-1D illustrates an example cochlear implant system 102 with which aspects of the techniques presented herein can be implemented. The cochlear implant system 102 comprises an external component 104 that is configured to be directly or indirectly attached to the body of the user, and an internal / implantable component 112 that is configured to be implanted in or worn on the head of the user. In the examples of FIGs.1A-1D, the implantable component 112 is sometimes referred to as a “cochlear implant.” FIG. 1A illustrates the cochlear implant 112 implanted in the head 154 of a user, while FIG.1B is a schematic drawing of the external component 104 worn on the head 154 of the user. FIG.1C is another schematic view of the cochlear implant system 102, while FIG. 1D illustrates further details of theAtty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 cochlear implant system 102. For ease of description, FIGs.1A-1D will generally be described together.

[0033] In the examples of FIGs. 1A-1D, the external component 104 comprises a sound processing unit 106, an external coil 108, and generally, a magnet fixed relative to the external coil 108. The cochlear implant 112 includes an implantable coil 114, an implant body 134, and an elongate stimulating assembly 116 configured to be implanted in the user’s cochlea. In one example, the sound processing unit 106 is an off-the-ear (OTE) sound processing unit, sometimes referred to herein as an OTE component, which is configured to send data and power to the implantable component 112. In general, an OTE sound processing unit is a component having a generally cylindrically shaped housing 111 and which is configured to be magnetically coupled to the user’s head 154 (e.g., includes an integrated external magnet 150 configured to be magnetically coupled to an internal / implantable magnet 152 in the implantable component 112). The OTE sound processing unit 106 also includes an integrated external (headpiece) coil 108 (the external coil 108) that is configured to be inductively coupled to the implantable coil 114.

[0034] It is to be appreciated that the OTE sound processing unit 106 is merely illustrative of the external devices that could operate with implantable component 112. For example, in alternative examples, the external component 104 can comprise a behind-the-ear (BTE) sound processing unit configured to be attached to, and worn adjacent to, the recipient’s ear. In general, a BTE sound processing unit comprises a housing that is shaped to be worn on the outer ear of the user and is connected to the separate external coil assembly via a cable, where the external coil assembly is configured to be magnetically and inductively coupled to the implantable coil 114. It is also to be appreciated that alternative external components could be located in the user’s ear canal, worn on the body, etc.

[0035] Although the cochlear implant system 102 includes the sound processing unit 106 and the cochlear implant 112, as described below, the cochlear implant 112 can operate independently from the sound processing unit 106, for at least a period, to stimulate the user. For example, the cochlear implant 112 can operate in a first general mode, sometimes referred to as an “external hearing mode,” in which the sound processing unit 106 captures sound signals which are then used as the basis for delivering stimulation signals to the user. The cochlear implant 112 can also operate in a second general mode, sometimes referred as an “invisible hearing” mode, in which the sound processing unit 106 is unable to provide sound signals to the cochlear implant 112 (e.g., the sound processing unit 106 is not present, the soundAtty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 processing unit 106 is powered-off, the sound processing unit 106 is malfunctioning, etc.). As such, in the invisible hearing mode, the cochlear implant 112 captures sound signals itself via implantable sound sensors and then uses those sound signals as the basis for delivering stimulation signals to the user. Further details regarding operation of the cochlear implant 112 in the external hearing mode are provided below, followed by details regarding operation of the cochlear implant 112 in the invisible hearing mode. It is to be appreciated that reference to the external hearing mode and the invisible hearing mode is merely illustrative and that the cochlear implant 112 could also operate in alternative modes.

[0036] In FIGs.1A and 1C, the cochlear implant system 102 is shown with an external device 110, configured to implement aspects of the techniques presented. The external device 110, which is shown in greater detail in FIG.1E, is a computing device, such as a personal computer (e.g., laptop, desktop, tablet), a mobile phone (e.g., smartphone), remote control unit, etc. The external device 110 and the cochlear implant system 102 (e.g., sound processing unit 106 or the cochlear implant 112) wirelessly communicate via a bi-directional communication link 126. The bi-directional communication link 126 can comprise, for example, a short-range communication, such as Bluetooth link, Bluetooth Low Energy (BLE) link, a proprietary link, etc.

[0037] Returning to the example of FIGs.1A-1D, the sound processing unit 106 of the external component 104 also comprises one or more input devices configured to capture and / or receive input signals (e.g., sound or data signals) at the sound processing unit 106. The one or more input devices include, for example, one or more sound input devices 118 (e.g., one or more external microphones, audio input ports, telecoils, etc.), one or more auxiliary input devices 128 (e.g., audio ports, such as a Direct Audio Input (DAI), data ports, such as a Universal Serial Bus (USB) port, cable port, etc.), and a short-range wireless transmitter / receiver (wireless transceiver) 120 (e.g., for communication with the external device 110), each located in, on or near the sound processing unit 106. However, it is to be appreciated that one or more input devices can include additional types of input devices and / or less input devices (e.g., the short- range wireless transceiver 120 and / or one or more auxiliary input devices 128 could be omitted).

[0038] The sound processing unit 106 also comprises the external coil 108, a charging coil 130, a closely-coupled radio frequency transmitter / receiver (RF transceiver) 122, at least one rechargeable battery 132, and an external sound processing module 124. The external sound processing module 124 can be configured to perform a number of operations which areAtty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 represented in FIG.1D by an electrophysiological measurement module 131, a sound processor 133, and a condition monitoring module 135. Each of the electrophysiological measurement module 131, the sound processor 133, and the condition monitoring module 135 can be formed by one or more processors (e.g., one or more Digital Signal Processors (DSPs), one or more uC cores, etc.), firmware, software, etc. arranged to perform operations described herein. That is, the electrophysiological measurement module 131, the sound processor 133, and the condition monitoring module 135 can each be implemented as firmware elements, partially or fully implemented with digital logic gates in one or more application-specific integrated circuits (ASICs), partially or fully in software, etc. Although FIG. 1D illustrates the electrophysiological measurement module 131, a sound processor 133, and the condition monitoring module 135 as being implemented / performed at the external sound processing module 124, it is to be appreciated that these elements (e.g., functional operations) could also or alternatively be implemented / performed as part of the implantable sound processing module 158, as part of the external device 110, etc.

[0039] Returning to the example of FIGs. 1A-1D, the implantable component 112 comprises an implant body (main module) 134, a lead region 136, and the intra-cochlear stimulating assembly 116, all configured to be implanted under the skin (tissue) 115 of the user. The implant body 134 generally comprises a hermetically-sealed housing 138 that includes, in certain examples, at least one power source 125 (e.g., one or more batteries, one or more capacitors, etc.) 125, in which RF interface circuitry 140 and a stimulator unit 142 are disposed. The implant body 134 also includes the internal / implantable coil 114 that is generally external to the housing 138, but which is connected to the RF interface circuitry 140 via a hermetic feedthrough (not shown in FIG.1D).

[0040] As noted, stimulating assembly 116 is configured to be at least partially implanted in the user’s cochlea. Stimulating assembly 116 includes a plurality of longitudinally spaced intra-cochlear electrical stimulating contacts (electrodes) 144 that collectively form a contact array (electrode array) 146 for delivery of electrical stimulation (current) to the recipient’s cochlea. Stimulating assembly 116 extends through an opening in the recipient’s cochlea (e.g., cochleostomy, the round window, etc.) and has a proximal end connected to stimulator unit 142 via lead region 136 and a hermetic feedthrough (not shown in FIG.1D). Lead region 136 includes a plurality of conductors (wires) that electrically couple the electrodes 144 to the stimulator unit 142. The implantable component 112 also includes an electrode outside of the cochlea, sometimes referred to as the extra-cochlear electrode (ECE) 139.Atty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1

[0041] As noted, the cochlear implant system 102 includes the external coil 108 and the implantable coil 114. The external magnet 150 is fixed relative to the external coil 108 and the internal / implantable magnet 152 is fixed relative to the implantable coil 114. The external magnet 150 and the internal / implantable magnet 152 fixed relative to the external coil 108 and the internal / implantable coil 114, respectively, facilitate the operational alignment of the external coil 108 with the implantable coil 114. This operational alignment of the coils enables the external component 104 to transmit data and power to the implantable component 112 via a closely-coupled wireless link 148 formed between the external coil 108 with the implantable coil 114. In certain examples, the closely-coupled wireless link 148 is a radio frequency (RF) link. However, various other types of energy transfer, such as infrared (IR), electromagnetic, capacitive and inductive transfer, can be used to transfer the power and / or data from an external component to an implantable component and, as such, FIG. 1D illustrates only one example arrangement.

[0042] As noted above, sound processing unit 106 includes the external sound processing module 124. The external sound processing module 124 is configured to process the received input audio signals (received at one or more of the input devices, such as sound input devices 118 and / or auxiliary input devices 128), and convert the received input audio signals into output control signals for use in stimulating a first ear of a recipient or user (i.e., the external sound processing module 124 is configured to perform sound processing on input signals received at the sound processing unit 106). Stated differently, the one or more processors (e.g., processing element(s) implementing firmware, software, etc.) in the external sound processing module 124 are configured to execute sound processing logic in memory to convert the received input audio signals into output control signals (stimulation signals) that represent electrical stimulation for delivery to the recipient.

[0043] As noted, FIG. 1D illustrates an embodiment in which the external sound processing module 124 in the sound processing unit 106 generates the output control signals. In an alternative embodiment, the sound processing unit 106 can send less processed information (e.g., audio data) to the implantable component 112 and the sound processing operations (e.g., conversion of input sounds to output control signals 156) can be performed by a processor within the implantable component 112.

[0044] In FIG. 1D, according to an example embodiment, output control signals (stimulation signals) are provided to the RF transceiver 122, which transcutaneously transfers the output control signals (e.g., in an encoded manner) to the implantable component 112 via external coilAtty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 108 and implantable coil 114. That is, the output control signals (stimulation signals) are received at the RF interface circuitry 140 via implantable coil 114 and provided to the stimulator unit 142. The stimulator unit 142 is configured to utilize the output control signals to generate electrical stimulation signals (e.g., current signals) for delivery to the user’s cochlea via one or more of the stimulating contacts (electrodes) 144. In this way, cochlear implant system 102 electrically stimulates the user’s auditory nerve cells, bypassing absent or defective hair cells that normally transduce acoustic vibrations into neural activity, in a manner that causes the recipient to perceive one or more components of the input audio signals (the received sound signals).

[0045] As detailed above, in the external hearing mode, the cochlear implant 112 receives processed sound signals from the sound processing unit 106. However, in the invisible hearing mode, the cochlear implant 112 is configured to capture and process sound signals for use in electrically stimulating the user’s auditory nerve cells. In particular, as shown in FIG.1D, an example embodiment of the cochlear implant 112 can include a plurality of implantable sound sensors 165(1), 165(2) that collectively form a sensor array 160, and an implantable sound processing module 158. Similar to the external sound processing module 124, the implantable sound processing module 158 can comprise, for example, one or more processors and a memory device (memory) that includes sound processing logic. The memory device can comprise any one or more of: Non-Volatile Memory (NVM), Ferroelectric Random Access Memory (FRAM), read only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. The one or more processors are, for example, microprocessors or microcontrollers that execute instructions for the sound processing logic stored in memory device.

[0046] In the invisible hearing mode, the implantable sound sensors 165(1), 165(2) of the sensor array 160 are configured to detect / capture input sound signals 166 (e.g., acoustic sound signals, vibrations, etc.), which are provided to the implantable sound processing module 158. The implantable sound processing module 158 is configured to convert received input sound signals 166 (received at one or more of the implantable sound sensors 165(1), 165(2)) into output control signals 156 for use in stimulating the first ear of a recipient or user (i.e., the implantable sound processing module 158 is configured to perform sound processing operations). Stated differently, the one or more processors (e.g., processing element(s) implementing firmware, software, etc.) in implantable sound processing module 158 areAtty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 configured to execute sound processing logic in memory to convert the received input sound signals 166 into output control signals 156 that are provided to the stimulator unit 142. The stimulator unit 142 is configured to utilize the output control signals 156 to generate electrical stimulation signals (e.g., current signals) for delivery to the user’s cochlea, thereby bypassing the absent or defective hair cells that normally transduce acoustic vibrations into neural activity.

[0047] It is to be appreciated that the above description of the so-called external hearing mode and the so-called invisible hearing mode are merely illustrative and that the cochlear implant system 102 could operate differently in different embodiments. For example, in one alternative implementation of the external hearing mode, the cochlear implant 112 could use signals captured by the sound input devices 118 and the implantable sound sensors 165(1), 165(2) of sensor array 160 in generating stimulation signals for delivery to the user.

[0048] According to the techniques of the present disclosure, external sound processing module 124 can also include an inertial measurement unit (IMU) 170. The inertial measurement unit 170 is configured to measure the inertia of the user's head, that is, motion of the user's head. As such, inertial measurement unit 170 comprises one or more sensors 175 each configured to sense one or more of rectilinear or rotatory motion in the same or different axes. Examples of sensors 175 that can be used as part of inertial measurement unit 170 include accelerometers, gyroscopes, inclinometers, compasses, and the like. Such sensors can be implemented in, for example, micro electromechanical systems (MEMS) or with other technology suitable for the particular application.

[0049] As also illustrated in FIG.1D, in certain examples, a second inertial measurement unit (IMU) 180 including one or more sensors 185 is incorporated into implantable sound processing module 158 of implant body 134. Second inertial measurement unit 180 can serve as an additional or alternative inertial measurement unit to inertial measurement unit 170 of external sound processing module 124. Like sensors 175, sensors 185 can each be configured to sense one or more of rectilinear or rotatory motion in the same or different axes. Examples of sensors 185 that can be used as part of inertial measurement unit 180 include accelerometers, gyroscopes, inclinometers, compasses, and the like. Such sensors can be implemented in, for example, micro electromechanical systems (MEMS) or with other technology suitable for the particular application. For hearing devices that include an implantable sound processing module, such as implantable sound processing module 158, that includes an IMU, such as IMU 180, the techniques presented herein can be implemented without an external processor.Atty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 Accordingly, a hearing device that includes an implant body 134 and lacks an external component 104 can be configured to implement the techniques presented herein.

[0050] FIG. 1E is a block diagram illustrating one example arrangement for an external computing device 110 configured to perform one or more operations in accordance with certain embodiments presented herein. As shown in FIG. 1E, in its most basic configuration, the external computing device 110 includes at least one processing unit 183 and a memory 184. The processing unit 183 includes one or more hardware or software processors (e.g., Central Processing Units) that can obtain and execute instructions. The processing unit 183 can communicate with and control the performance of other components of the external computing device 110. The memory 184 is one or more software or hardware-based computer-readable storage media operable to store information accessible by the processing unit 183. The memory 184 can store, among other things, instructions executable by the processing unit 183 to implement applications or cause performance of operations described herein, as well as other data. The memory 184 can be volatile memory (e.g., RAM), non-volatile memory (e.g., ROM), or combinations thereof. The memory 184 can include transitory memory or non-transitory memory. The memory 184 can also include one or more removable or non-removable storage devices. In examples, the memory 184 can include random access memory (RAM), read only memory (ROM), EEPROM (Electronically-Erasable Programmable Read-Only Memory), flash memory, optical disc storage, magnetic storage, solid state storage, or any other memory media usable to store information for later access. By way of example, and not limitation, the memory 184 can include wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared and other wireless media or combinations thereof. In certain embodiments, the memory 184 comprises logic 195 that, when executed, enables the processing unit 183 to perform aspects of the techniques presented.

[0051] In the illustrated example of FIG. 1E, the external computing device 110 further includes a network adapter 186, one or more input devices 187, and one or more output devices 188. The external computing device 110 can include other components, such as a system bus, component interfaces, a graphics system, a power source (e.g., a battery), among other components. The network adapter 186 is a component of the external computing device 110 that provides network access (e.g., access to at least one network 189). The network adapter 186 can provide wired or wireless network access and can support one or more of a variety of communication technologies and protocols, such as ETHERNET, cellular, BLUETOOTH, near-field communication, and RF (Radiofrequency), among others. The network adapter 186Atty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 can include one or more antennas and associated components configured for wireless communication according to one or more wireless communication technologies and protocols. The one or more input devices 187 are devices over which the external computing device 110 receives input from a user. The one or more input devices 187 can include physically- actuatable user-interface elements (e.g., buttons, switches, or dials), a keypad, keyboard, mouse, touchscreen, and voice input devices, among other input devices that can accept user input. The one or more output devices 188 are devices by which the computing device 110 is able to provide output to a user. The output devices 188 can include a display 190 (e.g., a liquid crystal display (LCD)) and one or more speakers 191, among other output devices for presentation of visual or audible information to the recipient, a clinician, an audiologist, or other user.

[0052] It is to be appreciated that the arrangement for the external computing device 110 shown in FIG. 1E is merely illustrative and that aspects of the techniques presented herein can be implemented at a number of different types of systems / devices including any combination of hardware, software, and / or firmware configured to perform the functions described herein. For example, the external computing device 110 can be a personal computer (e.g., a desktop or laptop computer), a hand-held device (e.g., a tablet computer), a mobile device (e.g., a smartphone), a surgical system, and / or any other electronic device having the capabilities to perform the associated operations described elsewhere herein.

[0053] It is to be appreciated that the use of an external component is merely illustrative and that the techniques presented herein can be used in cochlear implant arrangements and, indeed, other types of implantable medical devices. For example, in certain embodiments, the techniques presented herein can be implemented in a smart implant or totally implantable cochlear implant system where all components of the cochlear implant system are configured to be implanted under the skin / tissue of a recipient. Because all components are implantable, a totally implantable system operates, for at least a finite period of time, without the need of an external device. However, an external device can be used to, for example, charge an implantable power source of the totally implantable system, to receive signal data (obtained via the magnetic coils), etc. A totally implantable system can include an implantable battery and implantable electronic assembly.

[0054] As noted, changes in extracted biomarkers obtained from a recipient of a medical device (e.g., hearing device) recipient can be used to monitor a “condition” or “status” of the recipient. As noted above, monitoring a “condition” or “status” of a recipient includes monitoring a healthAtty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 condition of a recipient, monitoring a condition or status of medical device implanted in or worn by the recipient, etc. In certain examples, impedance values associated with a recipient can be measured and analyzed to monitor a condition associated with the recipient. For example, changes in impedance data (impedance measurements) above or below threshold values can indicate a clinical event. However, it has been discovered that impedance variations over time are highly recipient dependent. For example, a parameter change can be “normal” for one recipient and a sign of an alarming clinical event for another recipient. In addition, recipients can experience different amounts of impedance fluctuations in the short-term (e.g., over a day) or longer-term (e.g., over a week or month).

[0055] FIGs. 2A-2D are graphs illustrating impedance fluctuations associated with different medical device recipients over a number of days. The impedance values can be gathered and analyzed to monitor conditions (e.g., health of the cochlea, status of a medical device, etc.) associated with recipients of medical devices, such as cochlear implants. Although monopolar impedance values are illustrated in FIGs. 2A-2D, impedance values can include transimpedance values, monopolar values, bipolar values, or other types of impedance values. In addition to impedance values, other types of electrophysiological measurements can be taken and analyzed to monitor the condition / cochlea health of recipients.

[0056] FIG. 2A is a graph 210 illustrating impedance fluctuations associated with a first recipient of a medical device. As illustrated in graph 210, the impedances associated with the first recipient are low and steady around the median impedance value. In addition, the impedances jump in the morning. Impedance peaks are common overnight when a recipient is not using a medical device. When the electrodes are not stimulated (e.g., during the night when the user is not using the medical device), the impedances increase. The impedances decrease again when the recipient uses the medical device in the morning and the electrodes are stimulated. In this example, the first recipient experiences slight impedance fluctuation on a daily basis, but the impedances are steady throughout the weeks.

[0057] FIG. 2B is a graph 220 illustrating impedance fluctuations associated with a second recipient of a medical device. As illustrated in graph 220, the impedance values associated with the second recipient are low and steady around the median impedance value. Similar to the first recipient, the impedances of the second recipient jump in the morning. In this example, the second recipient experiences impedance fluctuation on a daily basis, but the impedances are steady throughout the weeks. On average, the impedance values of the second recipient are lower than the impedance values of the first recipient.Atty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1

[0058] FIG. 2C is a graph 230 illustrating impedance fluctuations associated with a third recipient of a medical device. As illustrated in graph 230, the impedance values associated with the third recipient are high and steady around the median impedance value. In this case, there are no morning impedance jumps or peaks. Instead, in this example, the third recipient experiences impedance fluctuations during the day. In addition, although on some days (e.g., 10-03), the impedances fluctuations are larger, in general the impedance values are steady over the two-week period. The impedance values associated with the third recipient are higher than the impedance values associated with the first recipient and the second recipient.

[0059] FIG. 2D is a graph 240 illustrating impedance fluctuations associated with a fourth recipient of a medical device. Graph 240 illustrates that the impedances are high and peak in the mornings. Unlike in graphs 210, 220, and 230, the impedance values in graph 240 are not steady around the median. Instead, in addition to the daily impedance fluctuations, the impedance values also change over a longer time. As can be seen in graph 240, the baseline impedance values increase around 11-19 to 11-21 and then decrease again. The fourth recipient can experience cyclical changes in impedance values over a longer period of time.

[0060] The examples illustrated in FIGs. 2A-2D illustrate “normal” impedance variations for four different recipients. In other words, none of the recipients experienced any clinical events or reported issues with hearing or cochlea health during the analyzed time periods. Instead, each recipient has a different level of “normal” impedance values and impedance variations. As can be seen, impedance levels and degree of impedance fluctuation can vary drastically from recipient to recipient, even in the absence of a clinical event.

[0061] FIG. 2E is a graph 250 illustrating the range of impedances values occurring per recipient within a day for 20 recipients of medical devices. In other words, graph 250 illustrates the daily impedance delta per day per recipient. The values for each recipient indicate the difference between the highest impedance value measured in a day and the lowest impedance value measured in the same day per recipient. Each box plot in graph 250 illustrates the ranges of impedance values for all electrodes for each day over 14 days. When looking at the range of impedances values occurring per subject within a day, ranges of well above 1 kOhm are seen in 4 out of the 20 subjects with maximum values of ~6kOhm. For example, box plots 252, 254, 256, and 258 illustrate much higher ranges in the daily impedance deltas than the other box plots in graph 250. In addition, box plot 252 shows a maximum value of greater than 6 kOhm.Atty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1

[0062] Although the daily fluctuations for the recipients in graph 250 varied greatly from recipient to recipient, none of these changes are associated with a clinically relevant event. In other words, none of the recipients reported any problems with hearing or cochlea health during the time periods illustrated in the graphs. It can be seen that “normal” impedance values can differ from recipient to recipient. Therefore, an alarm system that applies a “one-size-fits-all” paradigm without taking into account the variance of parameters for each individual user can result in a large number of false alarms. This shows that an alarm system needs to be adjusted to the individual norm of impedance values to avoid false alarms in subjects with a larger range of impedances, but still be sensitive to changes in subjects with a very narrow range of impedances.

[0063] FIG. 2F illustrates a graph 260 in which the impedance values are separated into a resistive part and a capacitive part. In graph 260, plot 262 shows the impedance values for a recipient, plot 264 shows the resistive portion of the impedance, and plot 266 shows the capacitive / polarization portion of the impedance. The impedance values in plot 262 show the impedance values over a two-week period for the same recipient. As can be seen in plot 262, the impedance values fluctuate daily and over the two-week period. For example, the baseline impedances increase over the first three days, decrease again or stay stable for the next four days, and then increase again.

[0064] The resistive portion and the polarization portion of the impedance values have different temporal patterns because each portion represents a different biological process. This means that the definition of an abnormal variation is recipient-dependent as well as impedance component-dependent. Graph 260 illustrates that the change in the baseline of the resistive portion over time mirrors the change in the baseline impedance over time. In addition, the daily fluctuations of the polarization portion align with the daily fluctuations of the impedance values. Therefore, fluctuations in the different portions of the impedance can account for the fluctuations in the impedance values over different time periods (e.g., fluctuations per day versus fluctuations per week, month, etc.). The personalized alarm system described herein accounts for fluctuations in the different components of the impedance.

[0065] Presented herein is a framework to scan multi-dimensional diagnostic data for abnormal events that can develop at different possible time scales (e.g., over a day, over a week, over a month, etc.). The diagnostic data can be based on a variety of raw data sources, including electrode impedances (in different modes and at different time-points), transimpedances, and other data from connected sensors. As one example of a time series analysis, the underlyingAtty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 biological events can result in quick variations (within the order of hours), induce slower processes (within order of 1 week, such as with a disease), or induce very slow processes (within order of multiple weeks, such as with hormonal changes, fibrosis formation, etc.). The number of time-constants is flexible.

[0066] The system presented herein learns from a recipient’s own history to personalize the analysis of measured data (e.g., impedance values) based on the individual’s reference of normal variations (e.g., in women during the monthly cycle or other “benign” fluctuations) and based on other personal data. The benefit of the system is that the personalized alarm system is more robust and avoids false alarms. Any false alarm will have a negative impact on the user and will lower the compliance in case of a true alarm. The system also can be capable of re-calibrating itself based on additional data, such as a permanent change in a user’s conditions. In some embodiments, the additional data can include a non-permanent change. For example, if a temporary change is detected (e.g., a temperature change when the patient is experiencing an illness), the system can adapt based on the information of a “real event.” In some embodiments, a patient or a healthcare provider can mark or label a certain moment in time as an event. For example, the patient or healthcare provider can mark the time of a temperature change as a time of patient illness.

[0067] FIG. 3 is a diagram illustrating the generation of a recipient-dependent anomaly detection model. The general mechanism of the recipient-dependent anomaly detection model consists of model creation, classification, and retraining.

[0068] As illustrated in FIG.3, to generate an initial recipient-dependent model 308, averaged recipient data 304 from other recipients of medical devices is fed into machine learning model 302. The averaged recipient data 304 is based on of an averaged model of all existing recipient models (e.g., from prior datasets or ongoing study data). For example, the models for other recipients of medical devices are averaged and inputted into machine learning model 302 to determine a baseline model.

[0069] Recipient measurements 306 associated with a recipient of a medical device are additionally fed into machine learning model 302. Recipient measurements 306 can include, for example, an impedance dataset associated with a recipient. The impedance data can be continuously collected and stored at an external storage (e.g., at a remote storage in the cloud). The impedance data can be collected at multiple time points during a pulse to allow decomposition (e.g., into resistive and polarization components). The impedance dataset canAtty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 be multi-dimensional. In other words, each measurement instance can contain a combination of different measurements (e.g., complex impedance measurements, transimpedance measurements, bipolar 4-point impedances, etc.). In addition, measurements are repeated (e.g., multiple times per day over several months), thus generating longitudinal data. The trajectories of impedance data and components can be described in a time series analysis (e.g., seasonal analysis) to disentangle changes on different timescales related to different processes (e.g., passivation overnight, long term changes due to fibrous tissue growth, mid-term changes due to hormonal changes, etc.).

[0070] Parameter extraction is performed on the impedance dataset to decompose the complex impedance into subcomponents, such as access resistance and polarization impedance. In addition, transimpedance data can be decomposed into components that can include, for example, far- and near-field components, estimation of abnormal current paths, estimation of abnormal distribution of tissue impedances, etc. Each component can capture different inner- ear processes on different timescales. Each parameter is represented as a timeseries and inputted to the machine learning model 302.

[0071] Additional data 312 can be inputted to machine learning model 302 to improve the prediction accuracy. Additional data 312 can include sensor data available from fitness trackers or smartwatches (e.g., skin temperature measurements, heart rate, skin conductance, menstrual cycle information, etc.). In addition, additional data 312 can include medical device information from data logs, such as the device usage and applied charge. Additional data 312 can also include personal information, such as medication intake, changes of vertigo or tinnitus levels, hearing test scores, etc.

[0072] Based on the averaged recipient data 304, recipient measurements 306, and / or additional data 312, machine learning model 302 can generate recipient-dependent model 308. The recipient-dependent model 308 can be used to monitor the condition (e.g., cochlea health, status of medical device, etc.) of a recipient. For example, if measurements (e.g., impedance measurements) associated with the recipient indicate that levels (e.g., impedance data) associated with the recipient are outside a normal range, the recipient can be notified of a potential clinical event.

[0073] The recipient-dependent model 308 is generated for a specific recipient of a medical device based on data associated with the recipient. Because the recipient-dependent model 308 is generated based on recipient-specific data, fewer false alarms will be generated than with aAtty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 conventional alarm system. For example, the recipient-dependent model 308 is generated to account for regular fluctuations over a day, week, month, etc. In addition, the recipient- dependent model 308 is generated based on the subcomponents of the measured data. Since the system is trained based on measurements from the recipient, the recipient-dependent model 308 determines whether current measurements are out of range of the normal for the day, week, month, etc. or for a particular sub-component of a measurement. In other words, the model is generated based on personalized baselines over different time frames / periods and impedance changes are evaluated based on the personalized baselines.

[0074] The recipient-dependent model 308 can be updated based on updated measurements 310 associated with the recipient. In this way, the system can readjust itself and periodically adapt the recipient-dependent model 308 based on changes associated with the recipient. For example, as a fibrosis grows along a length of an electrode array after implantation of the electrode array in the cochlea of the recipient, impedance values associated with the recipient can change. The system can update the recipient-dependent model 308 based on the fibrosis growth while continuing to monitor the longer-term changes due to fibrous tissue growth. The recipient can also experience different kinds of permanent changes that can affect “normal” impedance values. By updating the recipient-dependent model 308 as the impedance values associated with the recipient change, the recipient-dependent model 308 can continue to adapt and become more accurate, which decreases the chances of false alarms. The system can continue to adapt as more measurements associated with the recipient are taken.

[0075] FIG.4 is a block diagram illustrating using recipient-dependent model 308 to classify a datapoint associated with a recipient as normal or anomalous. As illustrated in FIG. 4, recipient measurements 402 can be inputted into recipient-dependent model 308. Recipient measurements 402 can include electrophysiological data (e.g., impedance data) associated with the recipient. Similar to the recipient measurements 306 described above, recipient measurement 402 can include a multi-dimensional dataset and can be decomposed into subcomponents. Recipient measurements 402 can additionally include sensor data associated with the recipient (e.g., temperature measurements, heart rate, skin conductance, menstrual cycle information, etc.).

[0076] Additional information 404 can be inputted to the recipient-dependent model 308. The additional information 404 can include, for example, information associated with the recipient’s medical device (e.g., device usage, applied charge, etc.) and personal informationAtty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 associated with the recipient (e.g., medication intake, changes of vertigo or tinnitus levels, hearing test scores, etc.).

[0077] In some embodiments, additional information 404 can include a stimulation history associated with the recipient’s medical device. Since it is known that electric stimulation has a conditioning effect on the electrode impedances, the stimulation history can be inputted into recipient-dependent model 308 during the analysis of impedance changes. For example, impedances are expected to increase overnight when no stimulation is applied for several hours. Furthermore, during live mode stimulation, not all electrodes are selected in each stimulation frame and the stimulation level depends on the incoming signal. Therefore, the conditioning effect depends on the overall device use of the medical device and the incoming sound.

[0078] In other words, the stimulation history of an electrode array can affect impedance measurements associated with a recipient. If unusually high impedances are measured, but the electrodes have not been stimulated for a period of time, the high impedance values are likely due to the lack of stimulation of the electrodes and not due to a critical event. Therefore, taking the stimulation history into account can decrease the likelihood of false alarms.

[0079] In order to take these factors into account, embodiments described herein can keep track of the overall device usage (e.g., taken from hourly usage logs) and the stimulation that has been applied to the individual electrodes of the electrode array of the medical device. In some embodiments, a dosimeter can be used to track the cumulative amount of current (charge) on an electrode over a given time period. Other statistics of the stimulation history can be used (e.g., the “silent” periods on an electrode) to identify the stimulation current / charge over given time period.

[0080] The above is related to the intended current that was supposed to be applied to the electrodes. In case of an out-of-compliance event, the intended current cannot be delivered. This error modality can be tracked to see how related error currents and additional charging / discharging of the electrode interface and the series capacitors influence the impedances.

[0081] In another embodiment, additional information 404 can include data associated with a control electrode. The ongoing stimulation of the implanted electrodes and the related conditioning effect result in lower impedances, which is generally seen as a positive effect. On the other hand, the conditioning effect can mask any long-term effects on the electrodes caused by biological processes since the electrodes get cleaned when stimulated and proteins or otherAtty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 molecules get removed from the surface. For example, the amount of the passivation effect that occurs overnight can provide useful information about the immune activity in the implanted ear.

[0082] According to certain embodiments, the differences in impedance change during passive periods of different lengths and different times of the day can be analyzed. To avoid an unintended conditioning effect, at least one electrode (e.g., a control electrode) can be available as a passive or probe electrode. The control electrode may not be used as part of the standard stimulation and can be located at different places along the electrode array or in the implanted area (for an implantable device in an area different than the ear). By keeping the control electrodes separate from the ongoing stimulation, the system can make use of specific stimulation paradigms for diagnostic measurements (e.g., using small probe currents, applying Electrode Impedance Spectroscopy, applying pulse shapes that could not be used for standard audio stimulation, etc.) and also control the duration of silent periods on these electrodes. The dedicated control electrode can provide information indicating the effects the body have on the electrodes when the electrodes are not stimulated. This information can be helpful when determining whether the electrophysiological measurements associated with the recipient are anomalous.

[0083] In the case of devices with multiple current sources, current steering can be used to make sure that no current is “contaminating” the probe / control electrodes. In some embodiments, probe / control electrodes can also be made of other material than the standard stimulation electrodes.

[0084] Recipient-dependent model 308 can be used to analyze the recipient measurements 402 and optionally the additional information 404. The measurement datasets from the recipient measurements 402 associated with a recipient can be analyzed using a number of methods.

[0085] In one embodiment, the analysis can include time series forecasting. One method for time series forecasting is ‘seasonal decomposition,’ which decomposes the original time series into the sum of, for example, four components: Y(t) = T(t) + C(t) + S(t) + R(t). The trend component T(t) reflects the long-term progression of the series. A trend exists when there is a persistent increasing or decreasing direction in the data. The cyclical component C(t) reflects repeated but non-periodic fluctuations. Seasonality S(t) represents the recurring patterns within the data and occurs over a fixed and known time period (e.g., a day). The residual component R(t) captures random noise or unexplained variation. A multiplicative model canAtty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 appropriate if the trend is proportional to the level of the time series, where Y(t) = T(t) x C(t) x S(t) x R(t).

[0086] After decomposition, the trend and seasonality can be modeled for forecasting separately using AutoRegressive Integrated Moving Average (ARIMA). The forecasted trend and seasonal components are combined to obtain the overall forecast. The model generates a forecast of the next impedance measurement with a margin. In some instances, there can be a latency time between the diagnostic period in which the data is collected and the predicted period of impedance measurements. For example, the model can predict what will happen in the next few days or in a few months based on the observation of current trends. The length of the predicted period can be variable. Using the time series forecasting method, the new datapoint is identified as an anomaly if the difference exceeds the forecast margin.

[0087] In another embodiment, the analysis can additionally include clustering. When using the clustering method, the input parameters can be clustered using spectral clustering, which does not assume spherical distributions of the clusters such as k-means. The anomalies can lie in a less-dense cluster away from the main cluster that contains the normal datapoints. More than two clusters can be found. This can be determined using the Elbow method. When a new datapoint is presented, the distance of this point (e.g., Mahalanobis distance) is calculated to all clusters and assigned to the nearest cluster. Based on the assignment, the new datapoint is classified as normal or anomalous. The new datapoint is used for retraining the clustering.

[0088] In yet another embodiment, the analysis can include using neural networks. In one example, the neural network can include a multi-variate convolutional neural network (CNN). When a CNN is used, timeseries features are extracted by a multi-variate CNN, which automatically extracts features at different timescales. When using this method, the CNN learns to map a sequence of past observations as input to an output observation. To simplify the model, a CNN can be trained for each impedance component separately. The output of the feature extraction is combined by new layers of neural networks that learn to classify input observations. To determine how anomalous the incoming values are, the predicted values are compared to their actual values. Retraining can be performed using transfer learning. Since the retraining of a model can take a long time, the retraining can be performed overnight when there is a low amount of incoming datapoints and lower need for immediate classification.

[0089] Another type of network that can be used for anomaly detection is an autoencoder network. Autoencoders do not require a labeled input and, therefore, are unsupervised. AnAtty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 autoencoder consists of an encoder that transforms the data to a lower dimensional “latent” space and reconstructs the data using a decoder. By training an autoencoder on a dataset of normal time series data, the autoencoder can learn to reconstruct normal patterns in the data. To detect anomalies in time series data, the trained autoencoder can be used to reconstruct new data points. If the difference between the original data point and its reconstructed version is above a certain threshold, the data point is considered anomalous.

[0090] Based on the analysis, recipient-dependent model 308 can output classification 406 indicating whether the recipient measurements 402 are in the normal range for the recipient or are anomalous. The classification 406 can indicate a current condition associated with the recipient. The condition can indicate, for example, a health of the recipient (e.g., a health of the recipient’s cochlea), a growth of a fibrosis in the cochlea, a status of the electrodes of a medical device, a status of the medical device, or another condition. If the recipient measurements 402 are anomalous, an indication of the anomalous measurements can be stored (e.g., in a file associated with the recipient) and / or transmitted to the recipient and / or another recipient (e.g., a doctor, clinician, etc.). Additional information (e.g., the recipient measurements 402, additional measurements / data, recipient history, or other relevant information) can additionally be stored and / or transmitted to the recipient and / or the other recipient.

[0091] FIG. 5 is a flow diagram illustrating a method 500 of monitoring a condition of a recipient of a medical device. At 502, one or more current electrophysiological measures associated with the recipient of the medical device are obtained. For example, impedance measurements associated with the recipient can be obtained. At 504, a condition associated with the recipient is monitored based on the one or more current measurements and a history of electrophysiological measurements associated with the recipient. For example, it can be determined whether the current electrophysiological measurements are in a normal range for the recipient based on the history of electrophysiological measurements associated with the recipient.

[0092] FIG.6 is a flow diagram of a method 600 for monitoring a condition associated with a recipient based on a model. At 602, an impedance dataset associated with the recipient of the medical device is obtained. The impedance dataset includes impedance measurements collected over a period of time. At 604, a model is trained using the impedance dataset. For example, the model is trained to identify a normal range of impedances for the recipient during different time periods. At 606, a condition associated with the recipient is monitored based onAtty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 the model. For example, current impedance measurements associated with the recipient are analyzed based on the model to determine whether the current impedance measurements are in a normal range for the recipient at a current time period.

[0093] FIG. 7 is a flow diagram illustrating a method 700 of analyzing one or more electrophysiological measurements based on historical data associated with prior electrophysiological measurements associated with a recipient. At 702, one or more electrophysiological measurements associated with a cochlea of a recipient are obtained. At 704, historical data associated with prior electrophysiological measurements obtained from the cochlea is obtained. At 706, the one or more electrophysiological measurements are analyzed based on the historical data.

[0094] As previously described, the technology disclosed herein can be applied in any of a variety of circumstances and with a variety of different devices. Example devices that can benefit from technology disclosed herein are described in more detail in FIGS. 8 and 9. The techniques of the present disclosure can be applied to other devices, such as neurostimulators, cardiac pacemakers, cardiac defibrillators, sleep apnea management stimulators, seizure therapy stimulators, tinnitus management stimulators, and vestibular stimulation devices, as well as other medical devices that deliver stimulation to tissue. Further, technology described herein can also be applied to consumer devices. These different systems and devices can benefit from the technology described herein.

[0095] FIG. 8 illustrates an example vestibular stimulator system 802, with which embodiments presented herein can be implemented. As shown, the vestibular stimulator system 802 comprises an implantable component (vestibular stimulator) 812 and an external device / component 804 (e.g., external processing device, battery charger, remote control, etc.). The external device 804 comprises a transceiver unit 860. As such, the external device 804 is configured to transfer data (and potentially power) to the vestibular stimulator 812,

[0096] The vestibular stimulator 812 comprises an implant body (main module) 834, a lead region 836, and a stimulating assembly 816, all configured to be implanted under the skin / tissue (tissue) 815 of the recipient. The implant body 834 generally comprises a hermetically-sealed housing 838 in which RF interface circuitry, one or more rechargeable batteries, one or more processors, and a stimulator unit are disposed. The implant body 134 also includes an internal / implantable coil 814 that is generally external to the housing 838, but which is connected to the transceiver via a hermetic feedthrough (not shown).Atty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1

[0097] The stimulating assembly 816 comprises a plurality of electrodes 844(1)-(3) disposed in a carrier member (e.g., a flexible silicone body). In this specific example, the stimulating assembly 816 comprises three (3) stimulation electrodes, referred to as stimulation electrodes 844(1), 844(2), and 844(3). The stimulation electrodes 844(1), 844(2), and 844(3) function as an electrical interface for delivery of electrical stimulation signals to the recipient’s vestibular system.

[0098] The stimulating assembly 816 is configured such that a surgeon can implant the stimulating assembly adjacent the recipient’s otolith organs via, for example, the recipient’s oval window. It is to be appreciated that this specific embodiment with three stimulation electrodes is merely illustrative and that the techniques presented herein can be used with stimulating assemblies having different numbers of stimulation electrodes, stimulating assemblies having different lengths, etc.

[0099] In operation, the vestibular stimulator 812, the external device 804, and / or another external device, can be configured to implement the techniques presented herein. That is, the vestibular stimulator 812, possibly in combination with the external device 804 and / or another external device, can include an evoked biological response analysis system, as described elsewhere herein.

[0100] FIG.9 illustrates a retinal prosthesis system 901 that comprises an external device 910 (which can correspond to the wearable device 100) configured to communicate with an implantable retinal prosthesis 900 via signals 951. The retinal prosthesis 900 comprises an implanted processing module 925 and a retinal prosthesis sensor-stimulator 990 is positioned proximate the retina of a recipient. The external device 910 and the processing module 925 can communicate via coils 908, 914.

[0101] In an example, sensory inputs (e.g., photons entering the eye) are absorbed by a microelectronic array of the sensor-stimulator 990 that is hybridized to a glass piece 992 including, for example, an embedded array of microwires. The glass can have a curved surface that conforms to the inner radius of the retina. The sensor-stimulator 990 can include a microelectronic imaging device that can be made of thin silicon containing integrated circuitry that convert the incident photons to an electronic charge.

[0102] The processing module 925 includes an image processor 923 that is in signal communication with the sensor-stimulator 990 via, for example, a lead 988 which extends through surgical incision 989 formed in the eye wall. In other examples, processing moduleAtty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 925 is in wireless communication with the sensor-stimulator 990. The image processor 923 processes the input into the sensor-stimulator 990, and provides control signals back to the sensor-stimulator 990 so the device can provide an output to the optic nerve. That said, in an alternate example, the processing is executed by a component proximate to, or integrated with, the sensor-stimulator 990. The electric charge resulting from the conversion of the incident photons is converted to a proportional amount of electronic current which is input to a nearby retinal cell layer. The cells fire and a signal is sent to the optic nerve, thus inducing a sight perception.

[0103] The processing module 925 can be implanted in the recipient and function by communicating with the external device 910, such as a behind-the-ear unit, a pair of eyeglasses, etc. The external device 910 can include an external light / image capture device (e.g., located in / on a behind-the-ear device or a pair of glasses, etc.), while, as noted above, in some examples, the sensor-stimulator 990 captures light / images, which sensor-stimulator is implanted in the recipient.

[0104] As should be appreciated, while particular uses of the technology have been illustrated and discussed above, the disclosed technology can be used with a variety of devices in accordance with many examples of the technology. The above discussion is not meant to suggest that the disclosed technology is only suitable for implementation within systems akin to that illustrated in the figures. In general, additional configurations can be used to practice the processes and systems herein and / or some aspects described can be excluded without departing from the processes and systems disclosed herein.

[0105] This disclosure described some aspects of the present technology with reference to the accompanying drawings, in which only some of the possible aspects were shown. Other aspects can, however, be embodied in many different forms and should not be construed as limited to the aspects set forth herein. Rather, these aspects were provided so that this disclosure was thorough and complete and fully conveyed the scope of the possible aspects to those skilled in the art.

[0106] As should be appreciated, the various aspects (e.g., portions, components, etc.) described with respect to the figures herein are not intended to limit the systems and processes to the particular aspects described. Accordingly, additional configurations can be used to practice the methods and systems herein and / or some aspects described can be excluded without departing from the methods and systems disclosed herein.Atty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1

[0107] According to certain aspects, systems and non-transitory computer readable storage media are provided. The systems are configured with hardware configured to execute operations analogous to the methods of the present disclosure. The one or more non-transitory computer readable storage media comprise instructions that, when executed by one or more processors, cause the one or more processors to execute operations analogous to the methods of the present disclosure.

[0108] Similarly, where steps of a process are disclosed, those steps are described for purposes of illustrating the present methods and systems and are not intended to limit the disclosure to a particular sequence of steps. For example, the steps can be performed in differing order, two or more steps can be performed concurrently, additional steps can be performed, and disclosed steps can be excluded without departing from the present disclosure. Further, the disclosed processes can be repeated.

[0109] Although specific aspects were described herein, the scope of the technology is not limited to those specific aspects. One skilled in the art will recognize other aspects or improvements that are within the scope of the present technology. Therefore, the specific structure, acts, or media are disclosed only as illustrative aspects. The scope of the technology is defined by the following claims and any equivalents therein.

[0110] It is also to be appreciated that the embodiments presented herein are not mutually exclusive and that the various embodiments can be combined with another in any of a number of different manners.

Claims

Atty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 CLAIMS What is claimed is:

1. A method comprising: obtaining one or more current electrophysiological measurements associated with a recipient of a medical device; and monitoring a condition associated with the recipient based on the one or more current electrophysiological measurements and a history of electrophysiological measurements associated with the recipient.

2. The method of claim 1, wherein monitoring the condition further comprises: analyzing the electrophysiological measurements using a time series analysis to identify differences in the electrophysiological measurements on different timescales; and monitoring the condition based on the analyzing.

3. The method of claim 1, wherein monitoring the condition further comprises: analyzing the electrophysiological measurements using a clustering analysis; and monitoring the condition based on the analyzing.

4. The method of claim 1, wherein monitoring the condition further comprises: analyzing the electrophysiological measurements using a convolutional neural network; and monitoring the condition based on the analyzing.

5. The method of claim 1, 2, 3, or 4, wherein the electrophysiological measurements include impedance data.

6. The method of claim 1, 2, 3, or 4, wherein monitoring the condition further comprises: monitoring the condition based on additional data obtained from an external device associated with the recipient.

7. The method of claim 1, 2, 3, or 4, wherein monitoring the condition further comprises:Atty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 monitoring the condition based on a stimulation history of one or more electrodes associated with the medical device.

8. The method of claim 1, 2, 3, or 4, wherein monitoring the condition further comprises: monitoring the condition based on data associated with a control electrode associated with the medical device.

9. The method of claim 1, 2, 3, or 4, wherein monitoring the condition further comprises: training a model associated with the recipient based on history of electrophysiological measurements associated with the recipient; and monitoring the condition based on the model.

10. The method of claim 9, further comprising: updating the model based on the one or more current electrophysiological measurements.

11. The method of claim 1, 2, 3, or 4, wherein monitoring the condition further comprises: decomposing the one or more current electrophysiological measurements into a plurality of components; and monitoring the condition based on the plurality of components.

12. The method of claim 1, 2, 3, or 4, wherein the history of electrophysiological measurements associated with the recipient includes a plurality of electrophysiological measurements taken over different periods of time.

13. A method comprising: obtaining an impedance dataset associated with a recipient of a medical device, the impedance dataset including impedance measurements collected over a period of time; training a model using the impedance dataset; and monitoring a condition associated with the recipient based on the model.Atty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 14. The method of claim 13, wherein the model is generated based on impedance datasets associated with other recipients of medical devices.

15. The method of claim 13 or 14, further comprising: receiving additional impedance data associated with the recipient; and updating the model based on the additional impedance data.

16. The method of claim 15, wherein training the model further comprises: decomposing impedance data of the impedance dataset into components; and training the model using the components.

17. The method of claim 15, wherein the impedance measurements are collected over a plurality of periods of time that vary in length.

18. The method of claim 15, wherein monitoring the condition includes determining whether a current impedance dataset associated with the recipient is in a normal range for the recipient based on the model.

19. The method of claim 15, wherein the model is based on time series forecasting.

20. The method of claim 15, wherein the model is based on clustering.

21. The method of claim 15, wherein the model is based on a neural network.

22. The method of claim 15, wherein monitoring the condition further includes monitoring the condition based on a stimulation history of one or more electrodes associated with the medical device.

23. The method of claim 15, wherein monitoring the condition further includes monitoring the condition based on a stimulation history of one or more electrodes associated with the medical device.

24. The method of claim 15, wherein monitoring the condition further comprises monitoring the condition based on data associated with a control electrode associated with the medical device.Atty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 25. One or more non-transitory computer readable storage media comprising instructions that, when executed by a processor, cause the processor to: obtain one or more electrophysiological measurements associated with an inner ear of a recipient; obtain historical data associated with prior electrophysiological measurements obtained from the inner ear; and analyze the one or more electrophysiological measurements based on the historical data.

26. The one or more non-transitory computer readable storage media of claim 25, further comprising instructions that, when executed, cause the processor to: train a model based on the historical data associated with the prior electrophysiological measurements; and analyze the one or more electrophysiological measurements based on the model.

27. The one or more non-transitory computer readable storage media of claim 25 or 26, wherein the prior electrophysiological measurements are obtained from the inner ear over different time periods of varying lengths of time.

28. The one or more non-transitory computer readable storage media of claim 25 or 26, wherein the instructions that, when executed, cause the processor to analyze the one or more electrophysiological measurements include instructions operable to monitor whether the one or more electrophysiological measurements associated with the inner ear are in a normal range for the inner ear based on the historical data.

29. The one or more non-transitory computer readable storage media of claim 25 or 26, further comprising operable to: decompose the one or more electrophysiological measurements into components; and analyze the one or more electrophysiological measurements based on the components.Atty. Docket No.3065.0755i Client Ref. No. CID03755WOPC1 30. A system, comprising: a memory; and at least one processor operable coupled to the memory, wherein the at least one processor is configured to: obtain one or more electrophysiological measurements associated with an inner ear of a recipient; obtain historical data associated with prior electrophysiological measurements obtained from the inner ear; and analyze the one or more electrophysiological measurements based on the historical data.

31. The system of claim 30, wherein the at least one processor is further configured to: train a model based on the historical data associated with the prior electrophysiological measurements; and analyze the one or more electrophysiological measurements based on the model.

32. The system of claim 30 or 31, wherein the prior electrophysiological measurements are obtained from the inner ear over different time periods of varying lengths of time.

33. The system of claim 30 or 31, wherein, analyzing the one or more electrophysiological measurements, the at least one processor is further configured to monitor whether the one or more electrophysiological measurements associated with the inner ear are in a normal range for the inner ear based on the historical data.

34. The system of claim 30 or 31, wherein the at least one processor is further configured to: decomposing the one or more electrophysiological measurements into components; and analyzing the one or more electrophysiological measurements based on the components.

Images