Automated determination of device settings

Abstract

Presented herein are techniques for fitting a recipient device to a recipient. A priori data is used to determine a first plurality of candidate stimulation setting groups for a recipient device of a recipient based on principal component analysis and system, processor, implant, and patient data. A selected one of the first plurality of candidate stimulation setting groups is instantiated in the recipient device. Measurement data associated with the recipient device is obtained while operating using the first one of the first plurality of candidate stimulation setting groups. A second plurality of candidate stimulation setting groups for the recipient device is determined using the measurement data and a selected one of the second plurality of candidate stimulation setting groups is instantiated in the recipient device. This process is repeated iteratively until a high confidence score is reached.

Description

Atty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1AUTOMATED DETERMINATION OF DEVICE SETTINGSBACKGROUNDField of the Invention[ooot] The present invention relates generally to determining parameters / settings of recipient devices, including medical devices or hearing devices.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 method is provided. The method comprises using a priori data to determine a first plurality of candidate stimulation setting groups for a medical device of a recipient; instantiating a selected one of the first plurality of candidate stimulation setting groups in the medical device; obtaining measurement data associated with the medical device while operating using the selected one of the first plurality of candidate stimulation setting groups; determining, using the measurement data, a second plurality of candidate stimulationAtty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1 setting groups for the medical device; and instantiating a selected one of the second plurality of candidate stimulation setting groups in the medical device.

[0005] In another aspect, another method is provided. The method includes identifying first set of operational settings for a medical device of a recipient based on measurement data associated with the medical device and feedback from the recipient; determining a confidence score associated with the first set of operational settings; identifying, by a machine learning model, a next test to perform with respect to the medical device in order effectuate an increase in the confidence score, the test being identified based on the measurement data associated with the medical device, the feedback from the recipient, and the confidence score; performing the next test to obtain second measurement data; and identifying a second set of operational settings for the medical device based on second measurement data.

[0006] In another aspect, 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 one or more processors to use a priori data to determine a first plurality of candidate stimulation setting groups for a medical device of a recipient; instantiate a selected one of the first plurality of candidate stimulation setting groups in the medical device; obtain measurement data associated with the medical device while operating using the first one of the first plurality of candidate stimulation setting groups; determine, using the measurement data, a second plurality of candidate stimulation setting groups for the medical device; and instantiate a selected one of the second plurality of candidate stimulation setting groups in the medical device.

[0007] In yet another aspect, a system is provided. The system comprises a memory; at least one processor operable coupled to the memory, wherein the at least one processor is configured to: identify a first set of operational settings for a recipient device associated with a recipient based on measurement data associated with the recipient device and feedback from the recipient; determine one or more confidence scores associated with the first set of operational settings; identify, by a machine learning model, a next test to perform with respect to the recipient device in order effectuate an increase in the one or more confidence scores, the test being identified based on the measurement data associated with the recipient device, the feedback from the recipient, and the one or more confidence scores; perform the next test to obtain second measurement data; and identify a second set of operational settings for the recipient device based on second measurement dataAtty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1BRIEF 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;[ooto] FIG. IB is a side view of a recipient wearing a sound processing unit of the cochlear implant system of FIG. 1A;[ooit] FIG. 1C is a schematic view of components of the cochlear implant system of FIG. 1 A;

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

[0013] FIG. IE is a schematic diagram illustrating an external device with which aspects of the techniques presented herein can be implemented;

[0014] FIG. 2A is a diagram illustrating an example in which initial or base candidate settings are identified for a recipient of a hearing device, according to an example embodiment.

[0015] FIG. 2B is a diagram illustrating an example in which personalized candidate settings are identified for the recipient based on additional data associated with the recipient and / or the hearing device, according to an example embodiment.

[0016] FIG. 3 is a flow diagram illustrating a method of generating a set of initial candidate settings for a medical device, according to an example embodiment.

[0017] FIG. 4 is a flow diagram illustrating a method of generating additional candidate settings for a medical device using updated data, according to an example embodiment.

[0018] FIG. 5 is a flow diagram of a method of instantiating a selected one of a plurality of candidate stimulation setting groups in a medical device, according to an example embodiment.

[0019] FIG. 6 is a flow diagram of a method of identifying a set of operational settings for a medical device based on measurement data from performing an identified test, according to an example embodiment.

[0020] FIG. 7 is a schematic diagram illustrating a vestibular stimulator system with which aspects of the techniques presented herein can be implemented; and

[0021] FIG. 8 is a schematic diagram illustrating a retinal prosthesis system with which aspects of the techniques presented herein can be implemented.Atty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1DETAILED DESCRIPTION

[0022] A recipient device, such as a hearing device or a medical device, is a device that is configured to provide a therapeutic benefit to a recipient. In general, recipient devices are configured to be worn by, or implanted in, a recipient, and operate in accordance with one or more configurable settings / parameters. Presented herein are techniques for automated determination / selection of the settings / parameters of recipient devices, such as hearing devices or a medical devices.

[0023] For example, cochlear implants are sophisticated medical devices designed to restore hearing in individuals with severe-to-profound hearing loss. The success of cochlear implantation relies on accurate and personalized device programming (setting determination), known as "fitting," to ensure that the device settings enable the device to meet the unique auditory needs of each recipient. In most cases, this fitting is performed “manually,” meaning that a trained audiologist / clinician works with a particular recipient to determine the settings for the device.

[0024] Manual fitting poses a number of challenges. For example, manual cochlear implant fitting is a complex and time-consuming / resource-intensive process that requires expertise from audiologists, which are not always available to all recipients. For example, access to experienced audiologists who specialize in cochlear implant fitting can be limited in certain geographical regions, leading to delayed or suboptimal fitting for some recipients.

[0025] Furthermore, manual cochlear implant fitting relies on subjective assessments by audiologists, which can vary based on individual interpretations and may not fully capture the recipient's auditory experiences. Due to lack of standardization, manual fitting may not always lead to optimal outcomes.

[0026] In addition, the dynamic nature of hearing can lead to performing manual fitting multiple times for a single patient and hearing abilities can change overtime and especially in the first few months after activation of cochlear implant. Factors such as adaption to electrical hearing, age, environmental conditions, or changes in health can require frequent adaptions. Manual fitting may not efficiently adapt to these changes. Variations in individual responses to stimulation, changes in hearing over time, and the need for frequent adjustments pose challenges to achieving optimal hearing outcomes for cochlear implant recipient, particularly with manual fitting.Atty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1

[0027] In order to address the above and other challenges, presented herein are techniques that leverage machine learning models and algorithms, signal process techniques, and real-time recipient feedback to provide an automated fitting solution that can be used to dynamically determine and activate optimized / personalized medical device settings. In particular, techniques presented herein provide baseline candidates settings based on population data and candidate demographics. Updated candidate settings are provided using data such as objective measures, subjective performance data, recipient feedback, candidate profile information, and / or additional data. A confidence score can be calculated for the candidate settings and additional candidate settings can be determined and provided based on additional data until settings with a confidence score above a particular level are identified for the recipient. The confidence score can be based on the quality and quantity of data that is available.

[0028] When the confidence score is below the particular level, additional tests can be performed, and the results of the tests can be used to identify updated candidate settings. In some embodiments, the hearing device can be configured using the settings with the highest confidence score until the additional tests can be performed and additional candidate settings can be generated. According to embodiments described herein, the system can identify a next test to perform based on which test results can be the most impactful or useful for identifying candidate settings with the highest confidence score.

[0029] The settings can be updated based on additional tests, recipient feedback, or other data as the hearing abilities of the recipient change over time. By automating the process, optimized settings can be provided for the hearing device quickly and easily as different factors associated with the hearing device or the recipient change or evolve.

[0030] There are a number of different types of recipient devices in / with which embodiments of the present invention can be implemented, including any number of hearing devices or medical devices. Merely for ease of description, the techniques presented herein are primarily described with reference to a specific recipient device in the form of a cochlear implant in 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 soundAtty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1 signals to a user / recipient 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.

[0031] FIGs. 1A-1D illustrate 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 recipient, and an intemal / implantable component 112 that is configured to be implanted in or worn on the head of the recipient. 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 recipient, while FIG. IB is a schematic drawing of the external component 104 worn on the head 154 of the recipient. FIG. 1C is another schematic view of the cochlear implant system 102, while FIG. ID illustrates further details of the cochlear implant system 102. For ease of description, FIGs. 1A-1D will generally be described together.

[0032] 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 recipient’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, that 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 magneticallyAtty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1 coupled to the recipient’s head 154 (e.g., includes an integrated external magnet 150 configured to be magnetically coupled to an intemal / 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.

[0033] 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. A BTE sound processing unit comprises a housing that is shaped to be worn on the outer ear of the recipient. In certain examples, the BTE is connected to a 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, while in other embodiments the BTE includes a coil disposed in or on the housing worn on the outer ear of the recipient. It is also to be appreciated that alternative external components could be located in the recipient’s ear canal, worn on the body, etc.

[0034] 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 recipient. 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 recipient. 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 sound 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 recipient. 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.Atty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1

[0035] 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. IE, is a computing device, such as a personal computer (e.g., laptop, desktop, tablet), a mobile phone (e.g., smartphone), a 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.

[0036] 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).

[0037] The sound processing unit 106 also comprises the external coil 108, a charging coil, 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 that are represented in FIG. ID by a settings generation module 131, a sound processor 133, and a confidence score calculation module 135. Each of the settings generation module 131, the sound processor 133, and the confidence score calculation 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 settings generation module 131, the sound processor 133, and the confidence score calculation 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), partiallyAtty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1 or fully in software, etc. Although FIG. ID illustrates the settings generation module 131, the sound processor 133, and the confidence score calculation 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.

[0038] 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 stimulating assembly 116, all configured to be implanted under the skin (tissue) 115 of the recipient. 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.), in which the RF interface circuitry 140 and a stimulator unit 142 are disposed. The implant body 134 also includes the intemal / 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. ID).

[0039] As noted, the stimulating assembly 116 is configured to be at least partially implanted in the recipient’s cochlea. The 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. The 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. ID). 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.

[0040] 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 intemal / implantable magnet 152 is fixed relative to the implantable coil 114. The external magnet 150 and the intemal / implantable magnet 152 fixed relative to the external coil 108 and the intemal / 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 viaAtty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1 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 an 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. ID illustrates only one example arrangement.

[0041] As noted above, the 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.

[0042] As noted, FIG. ID 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.

[0043] In FIG. ID, 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 the external coil 108 and the implantable coil 114. That is, the output control signals (stimulation signals) are received at the RF interface circuitry 140 via the 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 recipient’s cochlea via one or more of the stimulating contacts 144. In this way, cochlear implant system 102 electrically stimulates the recipient’s auditory nerve cells, bypassing absent or defective hair cells that normally transduce acoustic vibrations into neural activity, in a manner thatAtty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1 causes the recipient to perceive one or more components of the input audio signals (the received sound signals).

[0044] 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 recipient’s auditory nerve cells. In particular, as shown in FIG. ID, 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.

[0045] 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 recipient (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 the implantable sound processing module 158 are 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 recipient’s cochlea, thereby bypassing the absent or defective hair cells that normally transduce acoustic vibrations into neural activity.Atty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1

[0046] 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 recipient.

[0047] According to the techniques of the present disclosure, the external sound processing module 124 can also include an inertial measurement unit (IMU) 170. The IMU 170 is configured to measure the inertia of the recipient's head, that is, motion of the recipient's head. As such, the IMU 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.

[0048] As also illustrated in FIG. ID, in certain examples, a second IMU 180 including one or more sensors 185 is incorporated into implantable sound processing module 158 of implant body 134. The second IMU 180 can serve as an additional or alternative inertial measurement unit to the IMU 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, 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 the IMU 180, the techniques presented herein can be implemented without an external processor. 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.

[0049] FIG. IE is a block diagram illustrating one example arrangement for an external device 110 configured to perform one or more operations in accordance with certain embodiments presented herein. As shown in FIG. IE, in its most basic configuration, the external device 1 10 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 obtainAtty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1 and execute instructions. The processing unit 183 can communicate with and control the performance of other components of the external 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 RAM, 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, other wireless media, or combinations thereof. In certain embodiments, the memory 184 comprises logic 195 and 196 that, when executed, enables the processing unit 183 to perform aspects of the techniques presented. For example, in certain embodiments, logic 195 and 196 that, when executed can perform the operations associated with the settings generation module 131, the sound processor 133, and / or the confidence score calculation module 135 (e.g., one or more of these modules could be implemented, whole in or in part, on the external device 110).

[0050] In the illustrated example of FIG. IE, the external device 110 further includes a network adapter 186, one or more input devices 187, and one or more output devices 188. The external 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 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, among others. The network adapter 186 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 device 110 receives input from a recipient. The one or more input devices 187 can include physically- actuatable user-interface elements (e.g., buttons, switches, or dials), a keypad, keyboard,Atty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1 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 external 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.

[0051] It is to be appreciated that the arrangement for the external device 110 shown in FIG. IE 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 device 110 can be a personal computer (e.g., a desktop or laptop computer), a handheld 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.

[0052] As noted, techniques described herein provide for automated fitting of a medical device, such as a cochlear implant, using machine-learning models, signal processing techniques, objective measures, outcome measures and real-time recipient feedback. Reference is first made to FIGs. 2A and 2B, which illustrate aspects presented herein for identifying candidate settings for a recipient of a cochlear implant and narrowing down or identifying different candidate settings for the recipient based on additional data associated with the recipient and / or the hearing device.

[0053] As described elsewhere herein, recipient devices operate in accordance with a number of configurable settings / parameters. As used herein, the term “setting group” is used to refer to a group or collection of settings / parameters of a recipient device, such as medical device or hearing device. The term “stimulation setting group” refers to a collection of settings / parameters of a recipient device that control / dictate how stimulation signals (e.g., electrical stimulation signals) are delivered to a recipient. A stimulation setting group, which in certain field is sometimes referred to as the device “stimulation map” or “map,” can include settings such as the recipient’s Comfort (C) level (e.g., a stimulation level in which stimulation signals are at a loud but comfortable level), the recipient’s Threshold (T) level (e.g., a stimulation level in which stimulation signals are just audible), pulse rate, number of maxima, stimulation rate, interface gap, and other settings. In operation, only one setting group is instantiated and used in a recipient device at any given time.Atty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1

[0054] As used herein, the terms “setting groups,” “candidate setting groups,” or “set of setting groups” are used to refer to a collection comprised of at least a first setting group, and at least a second setting group (and likely more) that are each different in some manner (i.e., each include at least one different setting). Candidate setting groups, in particular, are setting groups that could be, but have not yet been, instantiated in a recipient device.

[0055] As noted above, it is to be appreciated that the techniques presented herein can be used to determine a settings (e.g., a setting group) for a number of different recipient devices. However, again merely for ease of illustration, the examples of FIGs. 2A and 2B, as well as those of FIGs. 3 and 4, are described specifically with reference to determination of a setting group (e.g., stimulation setting group or stimulation map) of a cochlear implant implanted in a recipient.

[0056] More specifically, FIG. 2A illustrates an example in which initial or base (baseline) candidate setting groups are identified for a recipient of a cochlear implant. As illustrated in FIG. 2A, machine learning model 200 can be provided an input 206 and machine learning model 200 can output a first set of candidate setting groups 204 for the recipient. Machine learning model 200 can be part of, for example, cochlear implant system 102, external device 110, or another device.

[0057] The first set of candidate setting groups 204 can include, for example, baseline candidate setting groups 204-1 to 204-N generated for the recipient based on the input 206. The input 206 can include, for example, a priori information or data. The a priori data can include, for example, population data, settings used by other recipients of cochlear implants that have the same or similar characteristics as the recipient, system information (e.g., implant type, stimulation mode / strategy, etc.), etc. For example, in certain embodiments, the a priori data can include settings associated with cochlear implant recipients with a similar demographic profiles (e.g., age, etiology, duration of deafness, etc.). In some embodiments, the input 206 can include intraoperative objective measures or data obtained during the surgical procedure when the cochlear implant was implanted in the recipient.

[0058] For a cochlear implant, each of the candidate setting groups 204-1 to 204-N can include different values for different stimulation settings associated with the cochlear implant. That is, as noted above, cochlear implants and / or other stimulating can operate in accordance with different stimulation settings / parameters which are initially set during the fitting session. The stimulation settings of a cochlear implant include one or more of the C level or the T level forAtty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1 each of a plurality of stimulation channels (e.g., the C levels or the T levels can vary across different stimulation channels), pulse rate, number of maxima, stimulation rate, interface gap, and other settings. The different stimulation settings dictate / control how stimulation signals are delivered to recipient for a given input or control signal. In other words, the stimulation settings operate to “map” control signals into stimulation / current levels, etc. to be applied to different electrodes of an electrode array of the cochlear implant.

[0059] Merely for ease of illustration, each of the candidate setting groups 204-1 to 204-N illustrates a single T setting or level and a single C setting or level. For example, candidate setting group 204-1 shows that the T level is set to Taand the C level is set to Cb. As noted above, in practice, a different C level and T level can be determined for each stimulating electrode or channel of the cochlear implant. In addition, in practice, parameters other than the T levels and C levels could be indicated in each of the candidate setting groups 204-1 to 204- N.

[0060] Based on the initial input 206, machine learning model 200 can identify a particular number of candidate setting groups for the recipient. In the example illustrated in FIG. 2A, the machine learning model 200 has identified N candidate setting groups for the recipient. Each of the candidate setting groups 204- 1 to 204-N can be associated with a score or percentage based on, for example, a percentage of the population that uses the candidate settings or a likelihood that the candidate setting group is optimal for the recipient.

[0061] A baseline candidate setting group 204-1 to 204-N can be chosen (e.g., based on the score or percentage) and settings associated the cochlear implant can be adjusted based on the values of the parameters in the chosen candidate setting group. When the settings are instantiated in the cochlear implant, additional data (e.g., objective measures, a candidate profile, and / or recipient feedback) can be obtained and a new, more refined set of candidate setting groups can be generated based on the data.

[0062] As illustrated in FIG. 2B, a machine learning model 200 can refine the candidate setting groups to identify a set of candidate setting groups 210 based on the current settings 207 applied to the cochlear implant, recipient feedback 208, and measurement data 209. Machine learning model 200 can be a statistical model (e.g., a Bayesian statistical model) or a neural network or another type of machine learning model or program that receives information and outputs candidate setting groups and additional information.Atty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1

[0063] Measurement data 209 can include, for example, intraoperative objective measurement data or data obtained during the surgical procedure when the cochlear implant was implanted in the recipient. The measurement data 209 can include, for example, results associated with impedance tests (e.g., clinical or complex impedance tests), Neural Response Telemetry (NRT), Transimpedance Matrix (TIM) measurements, Electrically-Evoked Stapedial Reflex Threshold (ESRT) measurements, imaging measurements, or other tests / measurements. Measurement data 209 can additionally include data associated with post-operative objective measures, such as TIM measurements taken in a home environment or other test data. Since measurements can be taken by a recipient (e.g., using an application on an external device), candidate setting groups can be generated and instantiated in the cochlear implant without the recipient visiting a clinic for in-person fitting.

[0064] Measurement data 209 can include candidate profile information that can be used to refine the candidate settings groups. Candidate profile information can include, for example, a hearing aid program, audiogram information, loudness scaling and hearing history, etc. The candidate profile information can help personalize the candidate setting groups. Measurement data 209 can additionally include subjective performance data, such as loudness scaling, speech scores, etc.

[0065] Recipient feedback 208 can additionally be used to refine the candidate setting groups. For example, a recipient can provide feedback regarding a comfort level, a loudness level, etc., and the recipient feedback can be used to refine the set of candidate setting groups. The recipient can provide feedback using an application on a device, such as external device 110. In some embodiments, a recipient can provide feedback regarding the loudness or comfort level for a particular candidate setting group. In some embodiments, a recipient can provide feedback indicating whether the recipient is satisfied with a particular candidate setting group. If a recipient is dissatisfied with a particular candidate setting group, the machine learning model 200 can use this information when refining the set of candidate setting groups. In addition, a recipient can indicate sounds that the recipient can hear, sounds that are painful to the recipient, sounds that are comfortable to the recipient, or additional information that can be used for refining candidate setting groups.

[0066] The recipient feedback 208, the measurement data 209, and / or additional information (e.g., historic setting data that can be used to ensure that the automatically created candidate settings are of good quality) can be used to identify the set of candidate setting groups 210. As shown in FIG. 2B, the set of candidate setting groups 210 can include candidate setting groupsAtty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1210-1 to 210-M. The set of candidate setting groups 210 can be refined with respect to the set of candidate setting groups 204. In this case, because the set of candidate setting groups 210 was generated based on more information associated with the recipient, the set of candidate setting groups 210 can be more likely to include optimal candidate settings for the recipient than the set of candidate setting groups 204.

[0067] The set of candidate setting groups 210 can include some candidate setting groups that were in the set of candidate setting groups 204. For example, the candidate setting group 210- 2 can have the same levels or values as the candidate setting group 204-2. The set of candidate setting groups 210 can additionally include other candidate settings that were not in the set of candidate setting groups 204. In some cases, the set of candidate setting groups 210 can include fewer candidate setting groups than the set of candidate setting groups 204. For example, when more recipient information (such as test results and recipient feedback) is used to generate the set of candidate setting groups, more optimal candidate setting groups can be identified and other candidate settings can be eliminated from the set of candidate setting groups.

[0068] In some embodiments, each of the candidate setting groups 210-1 to 210-M can be associated with a confidence score. The confidence score can be, for example, a number between 0 and 1 or a number between 0 and 100 (or a number in another range) and can indicate how likely each of the candidate setting groups 210-1 to 210-N is to be the optimal candidate setting group for the recipient. The confidence score can be based on the quality and quantity of data available for the recipient. As more information is obtained, the candidate setting groups can have higher confidence scores. For example, as more test data and / or recipient information is gathered and used to generate sets of candidate setting groups, the number of candidate setting groups in the sets of candidate setting groups can decrease and the confidence scores associated with the candidate setting groups can increase.

[0069] In some embodiments, the confidence score for a candidate setting group can be calculated based on confidence scores for different settings in the candidate setting group. For example, a different candidate score can be determined for each T and C level for each electrode. In some cases, test data can be available for certain frequency ranges associated with certain electrodes and test data may not be available for other frequencies associated with other electrodes. In this case, the confidence score for the electrodes for which measurement data is available can be higher than for electrodes for which measurement data is not available. The total confidence score for a candidate setting group can be calculated based on theAtty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1 confidence scores for all of the electrodes (e.g., by averaging the confidences scores for all electrodes or by calculating the confidence score in another way).

[0070] Machine learning model 200 can additionally output an indication of a next test 211 to perform. The next test 211 can be a test that generates the most helpful or impactful data for generating candidate setting groups with the highest confidence scores. Given the current data available for a patient, machine learning model 200 can determine which additional data can be most helpful for identifying optimal candidate setting groups. For example, if measurement data is available for some frequencies associated with some electrodes, but measurement data is not available for other frequencies associated with other electrodes, machine learning model 200 can indicate that performing tests to obtain measurement data associated with the other electrodes for which data is not currently available can increase the confidence scores for candidate setting groups. Machine learning model 200 can output an indication of the additional data or which tests to perform to obtain the additional data.

[0071] The process of generating updated or refined candidate setting groups can be repeated until the set of candidate settings is sufficiently small and / or the confidence score associated with at least one of the candidate setting groups is sufficiently high (e.g., by comparing the confidence score to a threshold confidence score level). In other words, the process described in FIG. 2B is iterative and stops once converged (i.e., a very good confidence score is reached).

[0072] The optimal candidate setting group for the recipient can be instantiated in the cochlear implant. In other words, the settings of the cochlear implant can be adjusted based on the parameter values or levels indicated in the optimal candidate setting group. When the optimal candidate setting groups has been determined, recipient feedback and / or measurement data can continue to be used to determine whether the current setting group continues to be the optimal setting group or whether different settings can be a better fit for the recipient.

[0073] By continuously updating the instantiated setting group based on recipient feedback and additional data, the system incorporates real-time adaptation capabilities to dynamically adjust cochlear implant settings based on the recipient's responses / feedback and changes in hearing conditions. For example, as time goes on, a recipient’s hearing or preferences can change (e.g., due to fibrosis growth, a recipient’s adjustment to a cochlear implant or hearing settings, biological changes, etc.). By incorporating a feedback loop in which current recipient feedback, measurement data, and / or other data are continuously being used to update theAtty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1 candidate settings, optimal settings can be provided based on a recipient’s current condition and / or preferences.

[0074] In this way, the system prioritizes recipient-centric optimization, considering individual preferences and experiences, to enhance overall satisfaction with the cochlear implant. Additional candidate settings can be generated and proposed in case the proposed estimated confidence score is significantly larger than the current settings applied to the cochlear implant. In addition, the confidence score of the settings can be used to customise time in clinic / followup frequency. For example, if more data is passively collected and used to adjust settings, the recipient can spend less time in the clinic getting fitted. Furthermore, using Al technology to generate candidate settings can reduce human errors in fitting, which ensures a higher quality of the fitting and can help clinicians achieve better fitting outcomes (particularly for less experienced and new audiologists, not only in emerging markets but also in the developed markets). In addition, iteratively narrowing the candidate settings using different parameters provides a safe way to identify the optimal settings. For example, the process described with respect to FIGs. 2A and 2B is conservative to ensure safe stimulation levels to avoid any potential hazards / suboptimal performances.

[0075] Reference is now made to FIG. 3, which is a flow diagram illustrating a method 300 of generating a set of initial candidate setting groups for a medical device, such as a cochlear implant. Method 300 starts at 302. At 304, a set of initial candidate setting groups is generated based on a priori data, including demographics (demographic data) and system information (collectively represented by reference number 308) and population data and statistics (collectively represented by reference number 306).

[0076] The demographic data in the demographics and system information 308 can include, for example, age, gender, aetiology, and additional information associated with a recipient of the cochlear implant. The system information in the demographics and system information 308 can include, for example, an implant type associated with the cochlear implant, a strategy for configuring / implementing the cochlear implant, etc. The population data 306 can include, for example, statistics, a priori information, etc. associated with other recipients of cochlear implants. The population data 306 can indicate settings for cochlear implants associated with the other recipients. The set of initial candidate setting groups that is generated can be based on the setting groups that were generated during fittings of other recipients that have similar demographics and system information as the recipient of the cochlear implant who is being fitted.Atty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1

[0077] In some embodiments, principal component analysis (PCA) can be used to generate the candidate setting groups. The variance is large on all the PCA coefficients because a full range of setting groups is available (approximately 200 (C profile: Mean current level (CL) =30 to Mean CL =230)). In addition, the confidence intervals for all the PCA coefficients are available based on the population statistics and known factors. In other embodiments, analysis methods other than PCA can be used to generate the candidate setting groups. The output A can include a new set of candidate setting groups in addition to other information (e.g., confidence scores, next tests to administer, etc.).

[0078] Reference is now made to FIG. 4, which is a flow diagram illustrating a method 400 of generating additional candidate setting groups using updated data. At 402, using the output A of 302, the a priori data can be updated using new available data and new candidate setting groups can be generated. In addition, a confidence score can be calculated for each of the updated candidate setting groups. The candidate setting groups and confidence scores can be generated based on recipient feedback 404 and objective measurement data 406. In some embodiments, Bayesian inference can be used to update the a priori data. In addition, the PCA parameters can be optimized using a Bayesian approach with a priori and a posteriori knowledge of data.

[0079] The recipient feedback 404 can include live audio / broadband preference that is used to update the believes about the global shift (PCI) and profile. In the case in which no objective or subjective tests are available, the PCI is optimized based on the recipient feedback until the setting group is loud and comfortable. This is the initial target PCI with some noise depending upon recipient responses. This can be an automatic update of setting groups until a loud but comfortable response is achieved.

[0080] The recipient feedback 404 can additionally include endolymphatic space (ELS) data that can be used to update believes about the T / C profile. The recipient feedback 404 can include aided audiometric threshold test (ATT) data that can be used in combination with the ELS data to update T profiles. Recipient feedback on live audio can be regularly collected to reduce the variance of the PCA coefficients and calculate the confidence scores for each initial candidate setting group. ELS test data can be used in combination with objective measures and live audio level preference data to update the candidate setting groups (C / T profiles). ATT data can be used to reduce uncertainty in the T-levels / profile and reach a target.Atty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1

[0081] The objective measurement data 406 can include, for example, NRT (intraoperative and postoperative) data that can be used to update the a priori data in the profile and global shift (PCI). In addition, the objective measurement data 406 can include TIM data that can be used alone or in combination with NRT data to update the T / C profile. When the NRT / TIM data is available, this data can be used to further reduce the variance of the additional PCA coefficients (C-profile, T-profile can also be optimized if no ELS / ATT data is available) with regularization and history (moving average) together with PC 1 information. The objective measurement data 406 can also include ESRT data that can be used to set the C profile and target loudness. The ESRT data can be used to set and optimize the target loudness level over time (target = ESRT- CL - X).

[0082] When the recipient feedback 404 and objective measurement data 406 is obtained, the updated candidate setting groups can be generated using a mathematical algorithm such as PCA or any type of machine learning model. The optimization function minimizes the expected error between the updated candidate setting groups and the recipient feedback and objective measurement data, while taking into account regularization and constrains.

[0083] At 408, the generated set of candidate setting groups can be output based on highest to lowest confidence scores. In this way, the set of candidate setting groups with the highest confidence scores can be identified. One of the candidate setting groups (e.g., the candidate setting group with the highest confidence score) can be instantiated to adjust the settings of the cochlear implant. For example, the settings of the cochlear implant can be adjusted based on the C levels, T levels, and additional parameters indicated in the chosen candidate setting group. In addition, it can be determined whether the confidence score associated with one or more of the candidate setting groups is above a threshold level or in a particular range. If the confidence score is above the threshold level or in a particular range for one of the candidate setting groups, it can be determined that the candidate setting group is optimal for the recipient.

[0084] A next test to perform can additionally be identified. For example, if the confidence levels are not high enough (e.g., below a threshold level), additional data that would be the most impactful for increasing the confidence score can be identified. In some cases, the total confidence level may be high enough (e.g., at or above the threshold level), but a confidence level for a particular electrode or frequency range may be below a threshold level. In these cases, a new setting or test to perform may be identified to increase the confidence score for the particular electrode / frequency range.Atty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1

[0085] At 410, data is collected to generate highest confidence score candidate settings. For example, tests can be performed to obtain the additional most impactful data, and the data can be used to generate an updated set of candidate setting groups. In addition, recipient feedback 404 can be obtained or additional objective measurement data 406 can be obtained. As illustrated in FIG. 4, the collected data can be used as a feedback loop for identifying updated sets of candidate setting groups and confidence scores for the candidate setting groups. The process of obtaining additional data and generating candidate setting groups can be continued until an optimal setting group is identified for the recipient. The optimal setting group can be instantiated in the cochlear implant. The recipient can continue to provide feedback, and additional tests can be performed to ensure that the instantiated setting group continues to be optimal for the recipient.

[0086] Reference is now made to FIG. 5, which is a flowchart of a method 500 of instantiating a selected one of a plurality of candidate stimulation setting groups in a medical device. At 502, method 500 includes using a priori data to determine a first plurality of candidate stimulation setting groups for a medical device of a recipient. For example, the first plurality of candidate stimulation settings groups can be identified based on population data, demographics associated with the recipient, and system information associated with the medical device.

[0087] At 504, a selected one of the first plurality of candidate stimulation setting groups can be instantiated in the medical device. The selected one of the first plurality of candidate stimulation setting groups can be selected based on, for example, a confidence score. At 506, measurement data associated with the medical device can be obtained while operating using the first one of the first plurality of candidate stimulation setting groups. For example, tests can be performed with respect to the recipient and the medical device and measurement data can be obtained based on the performing the tests.

[0088] At 508, a second plurality of candidate stimulation setting groups for the medical device can be determined using the measurement data. For example, a refined plurality of candidate stimulation setting groups can be determined based on the measurement data obtained from performing the tests. At 510, a selected one of the second plurality of candidate stimulation setting groups in the medical device can be instantiated. The selected one of the second plurality of candidate stimulation setting groups can be selected based on, for example, confidence scores associated with the second plurality of candidate stimulation setting groups.Atty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1

[0089] Reference is now made to FIG. 6. FIG. 6 is a flow diagram of a method 600 of identifying a set of operational settings for a medical device based on measurement data from performing an identified test. At 602, a first set of operational settings are identified for a medical device of a recipient based on measurement data associated with the medical device and feedback from the recipient. At 604, a confidence score associated with the first set of operational settings is determined.

[0090] At 606, a next test to perform with respect to the medical device in order to an effectuate an increase in the confidence score is identified by a machine learning model. The next test can be identified based on the measurement data associated with the medical device, the feedback from the recipient, and the confidence score. At 608, the next step is performed to obtain second measurement data. At 610, a second set of operational settings from the medical device is obtained based on the second measurement data.

[0091] 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. 7 and 8. 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.

[0092] FIG. 7 illustrates an example vestibular stimulator system 702, with which embodiments presented herein can be implemented. As shown, the vestibular stimulator system 702 comprises an implantable component (vestibular stimulator) 712 and an external device / component 704 (e.g., external processing device, battery charger, remote control, etc.). The external device 704 comprises a transceiver unit 760. As such, the external device 704 is configured to transfer data (and potentially power) to the vestibular stimulator 712.

[0093] The vestibular stimulator 712 comprises an implant body (main module) 734, a lead region 736, and a stimulating assembly 716, all configured to be implanted underthe skin / tissue (tissue) 715 of the recipient. The implant body 734 generally comprises a hermetically-sealed housing 738 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 anAtty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1 intemal / implantable coil 714 that is generally external to the housing 738, but which is connected to the transceiver via a hermetic feedthrough (not shown).

[0094] The stimulating assembly 716 comprises a plurality of electrodes 744(l)-(3) disposed in a carrier member (e.g., a flexible silicone body). In this specific example, the stimulating assembly 716 comprises three (3) stimulation electrodes, referred to as stimulation electrodes 744(1), 744(2), and 744(3). The stimulation electrodes 744(1), 744(2), and 744(3) function as an electrical interface for delivery of electrical stimulation signals to the recipient’s vestibular system.

[0095] The stimulating assembly 716 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.

[0096] In operation, the vestibular stimulator 712, the external device 704, and / or another external device can be configured to implement the techniques presented herein. That is, the vestibular stimulator 712, possibly in combination with the external device 704 and / or another external device, can include an evoked biological response analysis system, as described elsewhere herein.

[0097] FIG. 8 illustrates a retinal prosthesis system 801 that comprises an external device 810 (which can correspond to a wearable device) configured to communicate with an implantable retinal prosthesis 800 via signals 851. The retinal prosthesis 800 comprises an implanted processing module 825, and a retinal prosthesis sensor-stimulator 890 is positioned proximate the retina of a recipient. The external device 810 and the processing module 825 can communicate via coils 808, 814.

[0098] In an example, sensory inputs (e.g., photons entering the eye) are absorbed by a microelectronic array of the sensor-stimulator 890 that is hybridized to a glass piece 892 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 890 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.Atty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1

[0099] The processing module 825 includes an image processor 823 that is in signal communication with the sensor-stimulator 890 via, for example, a lead 888 that extends through surgical incision 889 formed in the eye wall. In other examples, processing module 825 is in wireless communication with the sensor-stimulator 890. The image processor 823 processes the input into the sensor-stimulator 890 and provides control signals back to the sensor-stimulator 890 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 890. 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.[ootoo] The processing module 825 can be implanted in the recipient and function by communicating with the external device 810, such as a BTE unit, a pair of eyeglasses, etc. The external device 810 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 890 captures light / images, in which sensor-stimulator 890 is implanted in the recipient.[ooiot] 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.

[0102] 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.

[0103] 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 processesAtty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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. 3065.081 li Client Ref. No. CID03817WOPC1CLAIMSWhat is claimed is:

1. A method comprising : using a priori data to determine a first plurality of candidate stimulation setting groups for a medical device of a recipient; instantiating a selected one of the first plurality of candidate stimulation setting groups in the medical device; obtaining measurement data associated with the medical device while operating using the selected one of the first plurality of candidate stimulation setting groups; determining, using the measurement data, a second plurality of candidate stimulation setting groups for the medical device; and instantiating a selected one of the second plurality of candidate stimulation setting groups in the medical device.

2. The method of claim 1, wherein using a priori data to identify the first plurality of candidate stimulation setting groups comprises: using at least one of population data, demographic data, or system data to determine the first plurality of candidate stimulation setting groups.

3. The method of claim 1, wherein obtaining the measurement data includes: performing one or more tests to obtain objective measurement data.

4. The method of claim 3, wherein performing the one or more tests includes performing neural response telemetry testing.

5. The method of claim 3, wherein performing the one or more tests includes performing impedance measurements.

6. The method of claim 3, wherein performing the one or more tests includes performing Electrically-Evoked Stapedial Reflex Threshold (ESRT) measurements.

7. The method of claim 3, wherein performing the one or more tests includes performing imaging measurements.Atty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC18. The method of claim 1, wherein obtaining the measurement data includes: performing one or more tests to obtain subjective measurement data.

9. The method of claim 1, 2, 3, 4, 5, 6, 7, or 8, wherein the first plurality of candidate stimulation setting groups include stimulation levels for a plurality of electrodes of the medical device.

10. The method of claim 9, wherein the first plurality of candidate stimulation setting groups include, for each electrode of the plurality of electrodes, a Comfort (C) level indicating a stimulation level in which stimulation signals are at a loud but comfortable level and a Threshold (T) level indicating a stimulation level in which the stimulation signals are just audible.

11. The method of claim 1, 2, 3, 4, 5, 6, 7, or 8, further comprising: generating a confidence score for each second plurality of candidate stimulation setting groups based on a quality of the measurement data; and identifying the selected one of the second plurality of candidate stimulation setting groups based on the confidence scores.

12. The method of claim 11, further comprising: comparing the confidence score for each second plurality of candidate stimulation setting groups to a threshold; obtaining additional measurement data associated with the medical device when the confidence score is below the threshold; and identifying a third plurality of sets of operational settings associated with the medical device based on obtaining the additional measurement data.

13. The method of claim 11, further comprising: determining a next test to perform to obtain additional measurement data based on the confidence score and the measurement data.

14. The method of claim 1, 2, 3, 4, 5, 6, 7, or 8, wherein determining the second plurality of candidate stimulation setting groups includes determining the second plurality of candidate stimulation setting groups using Principal Component Analysis (PCA).Atty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC115. A method comprising : identifying a first set of operational settings for a medical device of a recipient based on measurement data associated with the medical device and feedback from the recipient; determining a confidence score associated with the first set of operational settings; identifying, by a model, a next test to perform with respect to the medical device in order effectuate an increase in the confidence score, the next test being identified based on the measurement data associated with the medical device, the feedback from the recipient, and the confidence score; performing the next test to obtain second measurement data; and identifying a second set of operational settings for the medical device based on second measurement data.

16. The method of claim 15, wherein the measurement data includes objective measurement data obtained by performing one or more tests.

17. The method of claim 16, wherein performing the one or more tests includes performing neural response telemetry testing.

18. The method of claim 16, wherein performing the one or more tests includes performing impedance measurements.

19. The method of claim 15, wherein the measurement data includes subjective measurement data obtained by performing one or more tests.

20. The method of claim 15, 16, 17, 18, or 19, wherein the first set of operational settings includes stimulation levels for a plurality of electrodes of the medical device.

21. The method of claim 20, wherein the first set of operational settings includes, for each electrode of the plurality of electrodes, a Comfort (C) level indicating a stimulation level in which stimulation signals are at a loud but comfortable level and a Threshold (T) level indicating a stimulation level in which the stimulation signals are just audible.

22. The method of claim 21, further comprising: determining an individual confidence score for each C level and each T level for each electrode of the plurality of electrodes; andAtty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1 calculating the confidence score based on the individual confidence scores.

23. The method of claim 15, 16, 17, 18, or 19, further comprising: comparing the confidence score to a threshold; and performing the next test when the confidence score is below the threshold.

24. The method of claim 15, 16, 17, 18, or 19, further comprising: identifying a second confidence score for the second set of operational settings.

25. The method of claim 24, further comprising: identifying that the second confidence score is above a threshold; and instantiating the second set of operational settings in the medical device based on determining that the second confidence score is above the threshold.

26. The method of claim 15, 16, 17, 18, or 19, wherein identifying first set of operational settings includes identifying the first set of operational settings using Principal Component Analysis (PCA).

27. The method of claim 15, 16, 17, 18, or 19, wherein the model is a machine learning model.

28. The method of claim 15, 16, 17, 18, or 19, wherein the model is a statistical model.

29. The method of claim 15, 16, 17, 18, or 19, wherein the model uses Bayesian inference.

30. One or more non-transitory computer readable storage media comprising instructions that, when executed by a processor, cause one or more processors to: use a priori data to determine a first plurality of candidate stimulation setting groups for a medical device of a recipient; instantiate a selected one of the first plurality of candidate stimulation setting groups in the medical device; obtain measurement data associated with the medical device while operating using the first one of the first plurality of candidate stimulation setting groups;Atty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1 determine, using the measurement data, a second plurality of candidate stimulation setting groups for the medical device; and instantiate a selected one of the second plurality of candidate stimulation setting groups in the medical device.

31. The one or more non-transitory computer readable storage media of claim 30, wherein the instructions that cause the one or more processors to use the a priori data to identify the first plurality of candidate stimulation setting groups include instructions that cause the one or more processors to use at least one of population data, demographic data, or system information to determine the first plurality of candidate stimulation setting groups.

32. The one or more non-transitory computer readable storage media of claim 30, wherein the instructions that cause the one or more processors to obtain the measurement data includes instructions that cause the one or more processors to perform one or more tests to obtain objective measurement data.

33. The one or more non-transitory computer readable storage media of claim 30, wherein the instructions that cause the one or more processors to obtain the measurement data include instructions that cause the one or more processors to perform one or more tests to obtain subjective measurement data.

34. The one or more non-transitory computer readable storage media of claim 30, 31, 32, or 33, wherein the first plurality of candidate stimulation setting groups include stimulation levels for a plurality of electrodes of the medical device.

35. The one or more non-transitory computer readable storage media of claim 30, 31, 32, or 33, wherein the instructions further cause the one or more processors to: generate a confidence score for each second plurality of candidate stimulation setting groups based on a quality of the measurement data; and identify the selected one of the second plurality of candidate stimulation setting groups based on the confidence scores.

36. The one or more non-transitory computer readable storage media of claim 30, 31, 32, or 33, wherein the instructions that cause the one or more processors to determine the secondAtty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC1 plurality of candidate stimulation setting groups include instructions that cause the one or more processors to determine the second plurality of candidate stimulation setting groups using Principal Component Analysis (PCA).

37. A system, comprising: a memory; at least one processor operable coupled to the memory, wherein the at least one processor is configured to: identify a first set of operational settings for a recipient device associated with a recipient based on measurement data associated with the recipient device and feedback from the recipient; determine one or more confidence scores associated with the first set of operational settings; identify, by a machine learning model, a next test to perform with respect to the recipient device in order effectuate an increase in the one or more confidence scores, the next test being identified based on the measurement data associated with the recipient device, the feedback from the recipient, and the one or more confidence scores; perform the next test to obtain second measurement data; and identify a second set of operational settings for the recipient device based on second measurement data.

38. The system of claim 37, wherein the one or more confidence scores include individual confidence scores associated with each electrode of a plurality of electrodes of the recipient device and a confidence score that is calculated based on the individual confidence scores.

39. The system of claim 37, wherein the measurement data includes objective measurement data obtained by performing one or more tests.

40. The system of claim 37, wherein the measurement data includes subjective measurement data obtained by performing one or more tests.

41. The system of claim 37, 38, 39, or 40, wherein the first set of operational settings includes stimulation levels for a plurality of electrodes of the recipient device.Atty. Docket No. 3065.081 li Client Ref. No. CID03817WOPC142. The system of claim 37, 38, 39, or 40, wherein the at least one processor is further configured to: compare the one or more confidence scores to a threshold; and perform the next test when at least one of the one or more confidence scores is below the threshold.

43. The system of claim 37, 38, 39, or 40, wherein the at least one processor is further configured to: identify a second confidence score for the second set of operational settings.

44. The system of claim 37, 38, 39, or 40, wherein, when identifying first set of operational settings, the at least one processor is further configured to identify the first set of operational settings using Principal Component Analysis (PCA).

45. The system of claim 37, 38, 39, or 40, wherein the recipient device is a medical device.

46. The system of claim 37, 38, 39, or 40, wherein the recipient device is a hearing device.

47. The system of claim 37, 38, 39, or 40, wherein the one or more confidence scores change overtime.

Images