Assistive quality control for implant fitting

Abstract

Presented herein are techniques for fitting an implantable medical device to a recipient. In particular, the techniques presented herein can, in certain aspects, generate model settings (maps), generate setting confidence scores, and / or provide an assistance model for the generation of warnings, suggestions, or recommendations with respect to current settings of a device.

Description

ASSISTIVE QUAUITY CONTROU FOR IMPUANT FITTINGBACKGROUNDField of the Invention[oooi] The present invention relates generally to techniques for fitting implantable medical devices to a particular recipient.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: obtaining one or more current operational settings of an implantable medical device implanted in a recipient; obtaining at least one of general normative data or in-clinic normative data for a given population of similarly situated other recipients; analyzing the one or more current operational settings of the implantable medical device relative to at least one of the general normative data and the in-clinic normative data; and outputting data representing the analyzing of the one ormore current operational settings of the implantable medical device relative to the at least one of the general normative data and the in-clinic normative data.

[0005] In another aspect, another method is provided. The method comprises: obtaining operational settings for a recipient of an implantable medical device; generating a current map for the recipient based on the operational settings; generating at least one of a per-clinic model map for a particular clinic or a general model map for a given population of similarly situated other recipients; and displaying the current map of the recipient relative to at least one of the per-clinic model map or the general model map via a user interface.

[0006] In one 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 the processor to: obtain a current map of a recipient during a fitting process of an implantable medical device; analyze the current map of the recipient compared to general normative data for a given population and in-clinic normative data for a particular clinic; generate a fitting quality rating or score for the current map of the recipient based on results of analyzing the current map of the recipient compared to the general normative data for the given population and the in-clinic normative data for the particular clinic; and cause the fitting quality rating or score for the current map of the recipient to be displayed via a user interface of a display device.

[0007] In one aspect, a system is provided. The system comprises: a display screen configured to display a user interface; a memory storing instructions; and at least one processor operably coupled to the display screen and the memory, and configured to execute the instructions to: obtain a current map of a recipient during a fitting process of an implantable medical device; analyze the current map of the recipient compared to general normative data for a given population and in-clinic normative data for a particular clinic to determine a fitting quality for the current map of the recipient; generate one or more warnings, suggestions, or recommendations with respect to the current map of the recipient based on the fitting quality; and display the one or more warnings, suggestions, or recommendations with respect to the current map of the recipient via the user interface displayed on the display screen.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;[ooio] FIG. IB is a side view of a recipient wearing a sound processing unit of the cochlear implant system of FIG. 1A;[ooii] 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 a computing device with which aspects of the techniques presented herein can be implemented;

[0014] FIG. 2A is a graph with mean C-levels and mean standard deviation for a number of clinical centers, illustrating that there is variability within and between clinics;

[0015] FIG. 2B is an example where the current map T-levels are above the in-clinic and global norms;

[0016] FIG. 2C is a flow diagram for calculating distance scores per category, which are used to calculate an overall map confidence score for a recipient’s map, according to an example embodiment;

[0017] FIG. 2D is a graph illustrating the display of a map confidence score, according to an example embodiment;

[0018] FIG. 2E is a detailed view of per-category distance scores of the map confidence score;

[0019] FIG. 3 is a flowchart of a first example method, in accordance with embodiments presented herein;

[0020] FIG. 4 is a schematic diagram illustrating a cochlear implant fitting system with which aspects of the techniques presented herein can be implemented;

[0021] FIG. 5 is a flowchart of a second example method, in accordance with embodiments presented herein;

[0022] FIG. 6 is a flowchart of a third example method, in accordance with embodiments presented herein;

[0023] FIG. 7 is a flowchart of a fourth example method, in accordance with embodiments presented herein;

[0024] FIG. 8 is a flowchart of a fifth example method, in accordance with embodiments presented herein;

[0025] FIG. 9 is a schematic diagram illustrating a vestibular stimulator system with which aspects of the techniques presented herein can be implemented; and

[0026] FIG. 10 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 “configuring” or “fitting” medical devices, such as implantable medical devices, for a specific recipient. As explained in detail below, implantable medical devices are usually configured by medical professionals, referred to herein as clinicians, who are increasingly practicing remotely from the recipient / patient in whom the implantable medical device is implanted. In operation, the clinicians receive data from the implantable medical devices and, in turn, can determine operating parameters for the implantable medical device and return the parameters to the implantable medical device to configure, update, improve, or otherwise alter the operation of the implantable medical device. The techniques of the present disclosure provide for the generation of model settings (maps) and confidence scores. In addition, the techniques of the present disclosure also provide an assistance model for the generation of warnings, suggestions, or recommendations with respect to a recipient’s current settings.

[0028] There are a number of different types of devices in / with which embodiments of the present invention may 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 may also be partially or fully implemented by any of a number of different types of devices, including hearing devices, implantable medical devices, consumer electronic device (e.g., mobile phones), wearable devices (e.g., smartwatches), etc. As used herein, the term “hearing device” is to be broadly construed as any device that delivers sound signals to a user in any form, including in the form of acoustical stimulation, mechanical stimulation, electrical stimulation, etc. 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.) or 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). In other examples, the techniques presented herein can be implemented by, or used in conjunction with, various implantable medical devices, such as vestibular devices (e.g., vestibular implants), 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.

[0029] 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 intemal / 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. IB 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. ID illustrates further details of the cochlear implant system 102. For ease of description, FIGs. 1A-1D will generally be described together.

[0030] 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, 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 magnetically coupled to the user’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) coil108 (the external coil 108) that is configured to be inductively coupled to the implantable coil114.

[0031] 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 may 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.

[0032] 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 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 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.

[0033] 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), remote control unit, etc. The external device 110 and the cochlear implant system 102 (e.g., sound processing unit 106 orthe cochlear implant 112) wirelessly communicate via a bi-directional communication link 126. The bi-directional communication link 126 may comprise, for example, a short-range communication, such as Bluetooth link, Bluetooth Low Energy (BLE) link, a proprietary link, etc.

[0034] Returning to the example ofFIGs. 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 may 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).

[0035] 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, and 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 external sound processing module 124 can 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.

[0036] 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 intemal / implantable coil 114 that is generally externalto the housing 138, but which is connected to the RF interface circuitry 140 via a hermetic feedthrough (not shown in FIG. ID).

[0037] 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. 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.

[0038] 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 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, may 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.

[0039] 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 module124 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.

[0040] 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.

[0041] 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 external coil 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).

[0042] 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. 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 may comprise, for example, one or more processors and a memory device (memory) that includes sound processing logic. The memory device may 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.

[0043] 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 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 user’s cochlea, thereby bypassing the absent or defective hair cells that normally transduce acoustic vibrations into neural activity.

[0044] 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.

[0045] FIG. IE 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. IE, 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 memory184 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.

[0046] In the illustrated example of FIG. IE, 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 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 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.

[0047] It is to be appreciated that the arrangement for the external computing 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 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.

[0048] As noted, cochlear implant system 102 includes one or more sound input devices 118 that receive electrical signals and / or convert audio signals into electrical input signals. The sound processing unit 106 processes the electrical input signals and generates stimulation data for use in delivering stimulation to the recipient in accordance with various operating parameters dictated by one of a number of selectable settings or modes of operation. The various selectable settings or modes of operation may be in the form of executable programs or sets of parameters for use in a program. The settings may accommodate any of a number of specific configurations that influence / control the operation of the cochlear implant. For example, the settings may include different digital signal and sound processing algorithms, processes and / or operational parameters for different algorithms, other types of executable programs (such as system configuration, user interface, etc.), or operational parameters for such programs. In certain examples, the selectable settings would be stored in a memory of the cochlear implant system 102 and relate to different optimal settings for different listening situations or environments encountered by the recipient (i.e., noisy or quiet environments, windy environments, etc.).

[0049] Additionally, since the dynamic range for electrical stimulation is relatively narrow and varies across recipients and stimulating contacts, programs used in a sound processor are typically individually tailored to optimize the perceptions presented to a particular recipient (i.e., tailor the characteristics of electrical stimulation for each recipient). For example, many speech processing strategies rely on a customized set of stimulation settings which provide, for a particular recipient, the threshold levels (T -levels) and comfortable levels (C-levels) of stimulation for each frequency band. Once these stimulation settings are established, the sound processor may then optimally process and convert the received acoustic signals into stimulation data for use by the stimulator unit 142 in delivering stimulation signals to the recipient.

[0050] As such, a typical cochlear implant has many parameters / settings which determine the sound processing, sound coding, and other operations of the device. The individualized programs, commands, data, settings, parameters, instructions, modes, and / or other information that define the specific characteristics used by cochlear implant system 102 to process electrical input signals and generate stimulation data therefrom are generally and collectively referred to herein as the recipient’s “operational settings” or the recipient’s “map” (e.g„ the “map” of the recipient of the implantable medical device). The recipient’s map (i.e., the collection operational settings) is determined / set by medical practitioners (clinicians) in a process known as “fitting” of the cochlear implant. As described in detail below with reference to FIG. 4, external device 110 may be configured to send data to a fitting system (see fitting system 470 of FIG. 4) via, for example, a computer network, such as a wide area network (WAN) or a local area network (LAN). This permits clinicians to use online technologies to individualize the programs, commands, data, settings, parameters, instructions, modes, and / or other information that define the specific operating characteristics used by cochlear implant system 102. In other words, the operational settings (map) can be set and adjusted by the clinician to define, update, and improve the operation of the device.

[0051] For ease of reference, the term “map” will generally be used to refer to the settings of the implantable medical device that are determined through one or more fitting processes. As used herein, the term “map” can include any of a number of different configuration settings / parameters and is not limited to any specific settings or context.

[0052] The fitting process for cochlear implants is typically performed by specialized audiologists in-person in the clinics, and increasingly in recent years, remote configuration (e.g., through a communications network) is also possible. However, despite more than 30 years of experience there is no agreed upon standard among clinics and clinicians on how to optimally fit a cochlear implant. This results in large variability in operational settings across clinics and even within the same clinic. Referring to FIG. 2A, a graph 210 is shown which illustrates that different clinics set significantly different comfort (C) and threshold (T) levels, which are arguably the most important operational settings. In FIG. 2A, the vertical (y) axis corresponds to mean standard deviation (variability) in a particular clinic, and the horizontal (x) axis corresponds to mean level across patients and electrodes in a particular clinic. In the example of FIG. 2A, the average clinic sets C-level at approximately 178 CU, and C-levels may differ by 25 CU to cater for patient differences, for example. Furthermore, some centers also have abnormal within subject variations. Current fitting solutions are oblivious to thesestatistics and do not provide any indication on the quality (confidence score) of the fitted map and solely rely on the competence of the audiologists who are performing the CI fitting. Although not all human errors can be completely avoided, access to “big map data” (i.e., a large corpus of clinical data sets that are collected over time through various clinics and clinicians across different geographical areas and a wide variety of different recipients) now allows some quality controls to be implemented, requesting objective tests, providing confidence scores, and assisting audiologists by providing them with recommendations so that they feel more empowered and provide best fitting for their recipients. In this way, some common human errors can also be avoided.

[0053] Existing fitting software can provide various fitting methodologies. However, the existing fitting software does not perform any quality check on the map (the operational settings), or provide any confidence score or quality rating, nor does it provide any statistics regarding this map compared to general normative data (i.e., aggregated data for a group of clinics, such as clinics in a given country, region, etc.) and / or in-clinic normative data (i.e., aggregated data on per-clinic basis). Existing fitting software also does not provide any basic guidance, warnings, or alerts in instances where certain practices followed by a clinician are known to be sub-optimal practices. For example, it is possible for a clinician to set T-levels and C-levels to zero (or a very low value) on a number of active electrode channels without being alerted to this and warned about the possible consequences. Similarly, no warning is provided when the dynamic ranges become too small, or when the T / C levels are set too low or too high compared to the general normative data or the in-clinic normative data. When studying the distribution of T-values and C-values for maps in big data sets, it has been identified that in a considerable number of cases, the T-values and C-values are often set to an unrealistically low value. For example, these may be channels that should have been disabled, but for which the value is erroneously set very low instead of explicitly disabling them.

[0054] To address these and other needs, the present disclosure provides fitting techniques, e.g., an artificial intelligence (Al) / machine learning (ML) based cochlear implant fitting technique, which performs quality checks and provides guidance / assistance to a clinician or audiologist to avoid human errors in the fitting process. For example, the techniques presented herein can include: (1) an analysis and comparison with in-clinic normative data and general normative data, (2) generation of map confidence scores, (3) flagging of extreme outliers, and (4) an assistance model. Each of these different aspects are described in greater detail below.(1) Analysis and comparison with in-clinic normative data and general normative data.

[0055] According to one aspect, an analysis model (e.g., an artificial intelligence (AI) / machine learning (ML) model), can be used to calculate or generate and display general normative data (e.g., data at a country, region, global, or other level) and in-clinic normative data based on various factors (e.g., electrode type, pulse width, loudness tolerance, etiology, stimulation mode, impedance data, trans-impedance matrix (TIM) data, Neural Response Telemetry (NRT) data, modiolar distance data, medical imaging data, etc.). These factors can be used as input metrics in confidence score calculations (i.e., as variables in the model, as described below), and / or as a basis for requesting objective tests (e.g., hearing performance outcomes). The current map of the recipient can be compared with matched recipients, and the in-clinic normative data and the general normative data is made available for visual comparison. As used herein, the term “matched recipients” refers to a population of similarly situated other recipients, and various other recipients can be selected to form a group of matched recipients for a particular recipient based on several factors, such as other recipients with similar demographics, recipients with similar electrode loudness scaling (ELS) data (audiometric thresholds), recipients with similar objective measurements data, recipients in a similar rehabilitation stage, etc. The matched recipients can be identified on a per-clinic basis to generate or obtain the in-clinic normative data for a particular clinic with respect to the particular recipient. Likewise, the matched recipients can be identified in various groups or subgroups. For example, the matched recipients can be identified on a regional, global, linguistic, country, or other basis to generate or obtain the general normative data for a large population of other recipients (e.g., within a similar geographic area (regional normative data) or spread across different geographic areas (e.g., global normative data)) with respect to the particular recipient.(2) Generation of map confidence score(s).

[0056] A “map confidence score” (also referred to herein as a “fitting quality rating” or a “fitting quality score”) is calculated or generated based on the currently available data for the recipient, as well as the in-clinic normative data and the general normative data. In certain examples, additional data can be requested (e.g., from a recipient, a clinician, an external device, a database, or other source), and the analysis model can be updated with the additional data for better confidence score prediction. The map confidence score may also be considered to be a kind of validation score (e.g., to verify that the default or current operational settings are optimal for a particular recipient), a degree of variance measure (e.g., to determine whether the current map or a particular operational setting of the recipient’s map deviates from the in-clinic normative data or the general normative data by at least a certain amount, degree, number of standard deviations), or the like. Some examples involve evaluating individual maps relative to regional and / or global population norms (e.g., broken down into low / medium / high frequencies of occurrence) for thresholds, dynamics range, comfort levels, equal loudness, etc. Some other examples involve comparing the recipient’s current map with a model map that is generated using aggregated data from matched recipients (e.g., the other recipients with similar demographics, ELS / audiometric thresholds, objective measurements, rehabilitation stage, etc.).(3) Flagging of extreme outliers.

[0057] In some example embodiments, the analysis model is configured to evaluate the recipient’s current map (analyzes one or more of the current operational settings) and available data with in-clinic normative data and / or regional / global general normative data for matched recipients, and flags (identifies, indicates) extreme outliers, which may be indicative of suspicious maps / electrodes. In addition, the analysis model can flag particular clinics with extreme fitting variation (i.e., a relatively large degree of variance within the particular clinic or compared to other similar clinics in the same regional or globally). For a particular recipient, the matched recipients (the population of other recipients that are similarly situated as the recipient) can be grouped based on one or more recipient-related factors and / or one or more device-related factors (e.g., type of electrode array, such as perimodiolar vs. lateral). The “recipient-related factors” can include, but are not limited to: (1) etiology, onset of hearing loss, hearing aid use, data-logs (time on air etc.), (2) objective measures (e.g., trans-impedance matrix (TIM) data, neural response telemetry (NRT) data, stapedial reflex thresholds, modiolar proximity data, medical imaging data, etc.), and / or (3) performance data such as electrical loudness scaling (ELS) data, audiometric thresholds (aided / unaided), consonant vowel consonant (CVC) scores, digit triple test (DTT) scores, etc. In case of waming / flagging of an extreme outlier (e.g., a suspect map / electrode(s)), additional data can be requested if not already available (to ratify / justify un-flagging the outlier or not). For example, additional ELS data, audiometric thresholds data, objective measurements data (such as NRT and or TIM), and / or hearing performance outcomes data (such as CVC or DTT scores) can be requested, and the analysis can be repeated or updated to determine whether to clear the warning or unflag the outlier.

[0058] In one example, the analysis model can determine if the current T-levels are within the norm (in-clinic normative data or general normative data) based on the matched ELS data forthe matched recipients. FIG. 2B shows a graph 220 illustrating an example for a loudness category (ELS) where the current map T-levels are set too high and are above the in-clinic normative data and the general normative data for matched recipients. The analysis model can calculate the distance score (for the loudness / ELS category) between the current map values and the matched group (e.g., per-clinic norms and general population / global norms), and may ask for confirmation and suggest checking the T-levels on specific electrodes. Similar distance scores can be calculated for the objective measures, T and C levels, audiometric thresholds, hearing performance data, etc. A warning can be issued before writing the maps (before actually implementing the operational settings), and either additional data is requested or else the clinician / audiologist can be asked to remeasure or confirm a T-level, for example.

[0059] FIG. 2C is a flow diagram 230 for calculating distance scores which are used to calculate an overall map confidence score for a recipient, according to an example embodiment. As shown in FIG. 2C, for a recipient’s current map 232, a matched recipient model 234 can be generated (or identified in a database) based on the current map 232 and available data associated with the recipient. The current map 232 and the matched recipient model 234 can be used as inputs to calculate or generate a map confidence score (a fitting quality rating or a fitting quality score) for the current map 232 of the recipient. In certain examples, one or more scores can be calculated for one or more categories 240, such as in-clinic normative data 241, electrode loudness scaling (ELS) / audiometric thresholds 242 (e.g., T and C levels), objective measures 243 (e.g., TIM, NRT, eSRT, etc.), general normative data 244, and / or hearing performance outcomes 245 (e.g., CVC, DTT, etc.). Similarly, distance scores can be calculated for various other operational settings. In some examples, a respective weighting (e.g., Wi, W2, W3, W4, W5 in FIG. 2C) can be applied for each category. The (weighted) outputs for each category can then be summed and normalized 247 to calculate or generate a map confidence score 249 (fitting quality rating / score) with respect to the current map 232 of the recipient.

[0060] FIG. 2D is a graph 250 that illustrates an overall map confidence score 259 for a current map of a recipient compared to in-clinic normative data 256 (shown as a distribution of points / dots that each represent scores for other individual recipients at that clinic), along with a clinic range 258 (denoted by the vertical lines with arrows at both ends in FIG. 2D), according to an example embodiment. The clinic range 258 can represent a value (e.g., a average, a mean, a target, etc.) as denoted by the horizontal line that intersects the vertical double-sided arrows, and a standard deviation in each direction as denoted by the length of the lines with the arrows. In certain examples, the graph 250 can be generated based on matched recipient model data (asin FIG. 2C), and the match grouping can be performed based on available data, electrode type, age, etiology, etc.. In some other examples, however, the matching and grouping of similarly- situated other recipients could be skipped.

[0061] In certain examples, there could also be displayed a second set of points / dots (for general normative data) and a second set of vertical double-sided arrows (for a general population range) in a similar manner. In such examples, the second set of data for the global / general population case can be displayed on a separate screen from, and / or can be displayed on the same screen as, the in-clinic case shown in FIG. 2D. As such, the system and techniques described herein provide flexibility with regard to what data is being analyzed and displayed. For example, a clinician may only be interested in analyzing and comparing a recipient’s data with their own clinic’s clinical data (rather than a large clinical data set for a global / general population, including data from other clinics in other regions).

[0062] FIG. 2E is a graph 260 that illustrates a detailed view of a map confidence score as a function of per-category distance scores, along with a clinic range 268 for each category, respectively. As noted, the clinic range 268 can represent a value (e.g., an average, a mean, a target, etc. as denoted by the horizontal line that intersects the vertical double-sided arrows, and a standard deviation in each direction as denoted by the length of the lines with the arrows). As shown in FIG. 2E, per-category distance scores can include a clinic stats score 261, an ELS distance score 262, an NRT / TIM distance score 263, a general population stats score 264, and a CVC / DTT distance score 265, for example. The clinic stats score 261 relates to the in-clinic normative data 241 of FIG. 2C, the ELS distance score 262 relates to the electrode loudness scaling / audiometric thresholds 242 of FIG. 2C, the NRT / TIM distance score 263 relates to the objective measures 243 of FIG. 2C, the general population stats score 264 relates to the general normative data 244 of FIG. 2C, and the CVC / DTT distance score 265 relates to the hearing performance outcomes 245 of FIG. 2C. The distance scores are based on (or can represent) a standard deviation or a percentile difference with respect to each of these different categories, for example.(4) Assistance model.

[0063] Based on the map confidence score (fitting quality rating / score), an assistance model is provided that generates and outputs one or more warnings, suggestions, or recommendations with respect to the current map (one or more current operational settings) of the recipient. In some examples, the assistance model may ask for confirmation based on the map confidencescore and history of maps / actions. In one example, the map confidence score can help differentiate between fitting issues and cognitive issues (e.g., which might help streamline clinical work and / or avoid unnecessary map adjustments). In the case of a warning, additional data can also be requested by the assistance model. For example, the assistance model can request additional electrical loudness scaling (ELS) data, audiometric thresholds, and / or hearing performance outcomes data (e.g., CVC and / or DTT scores). In another example, the model can request objective measurements data (e.g., TIM, NRT, eSRT).

[0064] Several non-limiting illustrative examples of the one or more warnings, suggestions, or recommendations may include: (a) “map confidence score is relatively low - consider collecting the ELS data or NRT data on electrodes 5 and 17”; (b) “T-levels on electrodes X and Y are 3 standard deviations too high compared with the matched recipient ELS data - please re-measure T-levels on these electrodes”; (c) “T / C levels are set to zero - consider deactivating the electrode”; (d) “loud sounds are not balanced across electrodes 5 and 8 - consider balancing the loudness on these electrodes”; I “dynamic range is too small for electrode X - consider increasing C-levels on this electrode”; (f) “the map confidence score is high, no more adjustments are necessary at this moment - consider increasing time “on air” (the current time on air is 2 hours below the matched population mean)”; and the like.

[0065] As noted, existing fitting systems use some basic rules and may display population statistics (e.g., population mean) in the background, but the existing fitting systems do not integrate use of in-clinic normative data against general normative data, and do not provide the ability to generate “map confidence scores” or “fitting quality ratings” based on various the various different inputs described herein, including but not limited to tests such as ELS and others. According to the techniques described herein, a model map can be created using aggregated data from matched recipients (e.g., other recipients that are “similarly situated” as the recipient, such as in terms of similar demographics, ELS / audiometric thresholds, objective measurements, rehab stage, etc.). The model can calculate and display deviations for current map parameter values against normative values, based on similar clinical factors (such as electrode type, pulse width, loudness tolerance, etiology, stimulation mode, and the like). The map parameters can include T levels (e.g., grouped into low / medium / high frequencies), dynamics range, comfort levels, equal loudness, etc. and deviations can be applied for selectable population groups (e.g., in clinic, regionally, globally). The model can identify deviation types / values having a clinical significance (e.g., extreme outliers). The model can generate and display map confidence scores (quality ratings, validation metrics). The modelcan provide clinical suggestions or recommendations based on the map confidence / fitting quality metric, map history, earlier maps / actions (e.g., a previous map and any adjustment(s) made to the operational setting(s) by the clinician), etc. One suggestion can be to perform audiological tests (e.g., ELS, audiometric thresholds, phoneme, identification, speech audiometry) or objective measures (e.g., EECAP, TIM, NRT, and / or eSRT). The solution also provides the ability to adjust the degree of complexity provided on the display for certain clinicians (e.g., of confidence intervals). In some examples, only the current map of the recipient and the general normative data may be displayed, or only the current map of the recipient and the in-clinic normative data may be displayed. In some examples, only the overall map confidence score (fitting quality rating) is displayed, while in other examples the individual per-category distance scores may be displayed.

[0066] Thus, the present disclosure provides data-driven methods to assist with CI fitting. The described solutions can assist the clinician in two main ways: (1) by displaying where a recipient’s map (operational settings / parameters) he with respect to a given population (inclinic and regionally or globally) of matched recipients that are similarly situated as compared to the recipient (e.g., in terms of electrode type, pulse width, etiology, etc.), and (2) by suggesting various changes to the recipient’s map when there is a large difference between the recipient’s map and the general normative data and / or the in-clinic normative data. One approach described herein involves presenting the clinician with both the general normative data as well as the map confidence score or fitting quality rating. While this may be desirable for more experienced clinicians, it may be too much information more newer clinicians. As such, a simplified approach can involve only displaying confidence intervals on certain tests as well as the map adjustment suggestions. One advantage of the solution is to move towards standardization of CI fitting, a process that has historically lacked alignment across clinics and regions, potentially leading to more uniform outcomes (i.e., to ensure that a recipient would get a similar map if fit in clinic A in region B as that recipient would receive in clinic C in region D). For the clinician / audiologist, this process could provide additional confidence, especially for those without extensive CI fitting experience, and the ease of fitting could increase the number of CI fitting centers.

[0067] As explained in detail below, the generation of a user interface display incorporates data from multiple sources in order to solve a specific problem faced by clinicians. More specifically, the display is generated by incorporating clinical data into determining the fitting quality (map confidence score) associated with the recipient’s current map, and providingwarnings, suggestions, or recommendations with respect to the current map based on the fitting quality (map confidence score). The generation of the display can also incorporate clinicspecific data as well as general (e.g., regional, global, etc.) data, along with the recipient’s data. Additionally, feedback can be provided and / or additional information can be requested to train or update the analysis model (e.g., refer to profile analysis logic 487 (e.g., the model map generation logic 492, the map confidence score generation logic 494, and / or the fitting assistance model logic 496) described in below with reference to the fitting system 470 of FIG. 4). Accordingly, the display provides additional information that solves an identified problem for clinicians providing remote or telemedicine services for medical devices, including implantable medical devices.

[0068] With reference now made to FIG. 3, depicted therein is a flowchart 300 illustrating a process flow diagram according to the techniques of the present disclosure. More specifically, flowchart 300 illustrates three example embodiments / processes of the techniques of the present disclosure, as well as the innovative manner in which the three processes interact. A first process involves matching recipients and generating model maps (or identifying model maps stored in a database, if previously generated), for comparison with a recipient’s map, based on various data / factors used for grouping similarly situated other recipients. A second process involves analyzing the recipient’s map in comparison to the model maps to generate and display a map confidence score (which is indicative of fitting quality). A third process involves analyzing the recipient’s map in comparison to the model maps to generate and display one or more warnings, suggestions, or recommendations with respect to the recipient’s current map as compared to the model maps. Additionally, clinician feedback and / or additional information requested by the model can be used to train and / or update the analysis model in order to improve the recipient matching / model map generation process, the map confidence score (fitting quality rating) generation process, and / or the fitting assistance model process.

[0069] The first process of flowchart 300 begins in operation 305, where recipient data (e.g., session data 380, including one or more of fitting quality check data 380a-f) is received at a computing device, such as a computing device utilized in a fitting system for an implantable medical device, a personal computer, a server computer (e.g., a server executing a database system and accompanying data processing functionality), a tablet or smart phone computing device, or other computing devices known to the skilled artisan.

[0070] As shown in FIG. 3, the session data 380 (fitting quality check data 380a-f) is recipientspecific data and can include manual call data 380a, hearing performance data 380b,physiological measurement data 380c, usage data 380d, implant system technical information data 380e, and contextual data 380f. Manual call data 380a may include data sent via a user of a cochlear implant system, such as recipient 471 of cochlear implant system 102 of FIG. 4. Accordingly, manual call data 380a may be an embodiment of a request for assistance by a recipient of an implantable medical device. This manual call data 380a may include telephone audio data, text or instant message data, and / or email text data indicating one or more issues for a clinician to address in the cochlear implant system. Additionally, a recipient’s external device (e.g., external device 110 of FIGs. 1A-1E) may be configured with an application (e.g., a smartphone “app”), that facilitates a recipient sending manual call data 380a. Hearing performance data 380b may be embodied as a recipient’s performance on audiometry tests. For example, if a recipient’s performance on these tests has worsened more than 10% since the last check, the recipient may be struggling. Physiological measurement data 380c may be embodied as data indicting if there are open / short circuits that have appeared since the last check. Such data may indicate that the recipient will need to come in for a re-programming appointment. Usage data 380d may be embodied as data indicating that a recipient is in the top percentile of coil-off events or the bottom percentile of on-air time. Accordingly, such recipients may not be getting much benefit from their implantable medical devices. Implant system technical information data 380e may be embodied as battery state data, error log data and / or implant reset data. Contextual data 38 Of may be embodied as data indicating when recipients received their medical implants, the recipient’s age, the recipient’s history / actions, etc.

[0071] In operation 310, the recipient’s session data 380 (e.g., fitting quality check data 380a- f) is fed to an analysis model. The analysis model also retrieves clinical data from a database 325, such as in-clinic data 326 (per-clinic data) and / or regional / global data 328, to generate a per-clinic model map 327 (in-clinic normative data) and / or a regional / global model map 329 (general normative data) for matched recipients by using a recipient matching model 312, in operation 310. The model maps can then be stored in the database 325 for future reference.

[0072] In operation 320, the analysis model uses the recipient’s session data 380 (e.g., fitting quality check data 380a-f) and one or more of the per-clinic model map 327 and / or the regional / global model map 329 for the matched recipients to generate a map confidence score 384 (or fitting quality rating). Operation 320 may apply the fitting quality check data 380a-f to a map analysis model 314 (map confidence score model, fitting quality rating model), such as a heuristic model or an artificial intelligence (Al) or machine learning (ML) based modelsuch as a neural network. Based upon the recipient’s session data 380 (fitting quality check data 380a- f), operation 320 may also apply a fitting assistance model 316 (an AI / ML based analysis model) to generate one or more warnings, suggestions, or recommendations 386 with respect to the current map of the recipient as compared to the per-clinic model map 327 (inclinic normative data) and / or the regional / global model map 329 (general normative data). A warning may identify a clinical problem, whereas a suggestion or recommendation may identify a proposed solution to the clinical problem (e.g., to improve the map confidence score / fitting quality rating for the recipient).

[0073] In operation 330, the map confidence score 384 (fitting quality rating) can be displayed on the display of the fitting system 470 (e.g., user interface 486 of FIG. 4), along with the warning, suggestion, or recommendation 386. While flowchart 300 illustrates that both the map confidence score 384 and the waming / suggestion / recommendation 386 are displayed in operation 330, it should be appreciated that only one of the map confidence score, or alternatively the waming / suggestion / recommendation, may be displayed in other example embodiments. In addition, one or both of the per-clinic model map 327 (in-clinic normative data) and / or the regional / global model map 329 (general normative data) may be displayed along with the map confidence score in operation 330.

[0074] Turning now to FIG. 4, depicted therein is a block diagram illustrating an example fitting system 470 configured to execute the techniques presented herein. Fitting system 470 is, in general, a computing device that comprises a plurality of interfaces / ports 478(1)-478(N), a memory 480, a processor 484, and a user interface 486. The interfaces 478(1)-478(N) may comprise, for example, any combination of network ports (e.g., Ethernet ports), wireless network interfaces, Universal Serial Bus (USB) ports, Institute of Electrical and Electronics Engineers (IEEE) 1394 interfaces, PS / 2 ports, etc. In the example of FIG. 4, interface 478(1) is connected to cochlear implant system 102 having components implanted in a recipient 471. Interface 478(1) may be directly connected to the cochlear implant system 102 or connected to an external device that is in communication with the cochlear implant system. Interface 478(1) may be configured to communicate with cochlear implant system 102 via a wired or wireless connection (e.g., telemetry, Bluetooth, etc.).

[0075] The user interface 486 includes one or more output devices, such as a display screen (e.g., a liquid crystal display (LCD)) and a speaker, for presentation of visual or audible information to a clinician, audiologist, or other user. The user interface 486 may also compriseone or more input devices that include, for example, a keypad, keyboard, mouse, touchscreen, etc.

[0076] The memory 480 comprises profde management logic 481 that may be executed to generate or update personal profdes 483 of recipients, which are stored in the memory 480. The profde management logic 481 may also be executed to generate or update per-clinic profdes and / or regional / global profdes 485. The “profdes” may store recipient data (e.g., session data 380, fitting quality check data 380a-f) along with the recipient’s current map (current operational settings), as well as a history of maps, actions, adjustments made, etc. In certain embodiments, the profde management logic 481 may be executed to obtain the results of objective evaluations of a recipient from an external device via one of the other interfaces 478(2)- 478(N).

[0077] The memory 480 further comprises profde analysis logic 487. The profde analysis logic 487 is executed to analyze the recipient’s personal profde 483 (e.g., the correlated results of the objective evaluations) to identify correlated stimulation parameters that are optimized for the particular recipient. As shown in FIG. 4, the profde analysis logic 487 can comprise model map generation logic 492, map confidence score generation logic 494, and fitting assistance model logic 496. The model map generation logic 492 is configured to generate the per-clinic model maps (in-clinic normative data) and the regional / global model maps (general normative data). The map confidence score generation logic 494 is configured to calculate the per-category distance scores and the overall map confidence score (fitting quality rating) for the recipient’s current map. The fitting assistance model logic 496 is configured to generate the warnings, suggestions, or recommendations with respect to the current map (operational settings) based on the map confidence score (fitting quality rating).

[0078] Memory 480 may comprise 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 processor 484 is, for example, a microprocessor or microcontroller that executes instructions for the profile management logic 481 and the profile analysis logic 487 (e.g., the model map generation logic 492, the map confidence score generation logic 494, and the fitting assistance model logic 496), respectively. Thus, in general, the memory 480 may comprise one or more tangible (non- transitory) computer readable storage media (e.g., a memory device) encoded with software comprising computer executable instructions and when the software is executed (by the processor 484) it is operable to perform the techniques described herein.

[0079] The correlated stimulation parameters identified through execution of the profile analysis logic 487 are sent to the cochlear implant system 102 for instantiation as the cochlear implant’s current correlated stimulation parameters. However, in certain embodiments, the correlated stimulation parameters identified through execution of the profile analysis logic 487 are first displayed at the user interface 486 for further evaluation and / or adjustment by a user (e.g., a clinician or audiologist). As such, the user has the ability to refine the correlated stimulation parameters before the stimulation parameters are sent to the cochlear implant system 102.

[0080] In some example embodiments, the profile analysis logic 487 (e.g., the fitting assistance model logic 496, or some other dedicated logic) can be configured to determine one or more adjustments to one or more operational settings of the recipient’s current map based on the map confidence score (fitting quality rating) and / or the one or more warnings, suggestions, or recommendations. Further, the profile analysis logic 487 can be configured to implement the one or more adjustments to the one or more operational settings of the recipient’s current map on the implantable medical device, with or without any user input from the clinician. For example, the fitting system 470 can be configured to communicate with the cochlear implant 102 to transmit the one or more adjustments to the one or more operational settings (e.g., the amount of the change to be made, which corresponds to the difference between the current operational setting and the adjusted operational setting), or can transmit one or more adjusted operational settings (the actual updated value that is to be set), to the cochlear implant 102 to cause the cochlear implant 102 to implement the adjustments or adjusted operational settings. In another example, the fitting system 470 can communicate with the cochlear implant 102 to directly reconfigure the implantable medical device by updating the one or more operational settings itself based on the one or more adjustments or the one or more adjusted operational settings. The fitting system 470 can be configured to perform these adjustments to the recipient’s map (the one or more operational settings) automatically, with or without requiring a confirmation or explicit approval from the clinician.

[0081] As such, in certain embodiments, the profile analysis logic 487 may be configured to operate in accordance with one or more selected guidelines set by the clinician or audiologist via the user interface 486, in order to give the clinician some measure of control over these automated aspects of the system and techniques described herein. For example, the clinician can configure which specific operational settings among the various operational settings of the implantable medical device may be adjusted automatically by the fitting system 470 (e.g., byenabling or disabling automatic adjustments for specific map settings), and / or the clinician can set limits with respect to how much (i.e., the amount or degree of change) a particular operational setting may be automatically adjusted by the fitting system 470.

[0082] Returning to FIG. 3, the recipient data (i.e., the session data 380, also referred to herein as fitting quality check data 380a-f) received at the computing device of the fitting system 470 in operation 305 may be received via the interface s / ports 478(1)-(N) illustrated in FIG. 4. According to other example embodiments, the recipient’s session data 380 (fitting quality check data 380a-f) may be received by another type of processing system or device, as described above. For example, data 380a-f may be received at a centralized database system that provides services according to the techniques of the present disclosure to multiple clinicians. According to other example embodiments, data 380a-f may be received at a clinicspecific database system configured to implement the techniques of the present disclosure. Such database systems may permit clinicians to access this data using separate computing devices, such as fitting system 470 of FIG. 4, a personal computing device, a tablet or smart phone computing device, or other computing devices known to the skilled artisan.

[0083] Additionally, the system that receives the recipient’s session data 380 (fitting quality check data 380a-f), and that implements the other operations of FIG. 3, need not be specific to one particular type of medical device. For example, a system according to the techniques of the present disclosure may receive data, such as the recipient’s session data 380 (fitting quality check data 380a-f), from a number of different medical device types, including implantable stimulation systems, vestibular stimulator systems, retinal prosthesis systems, and other types of medical devices known to the skilled artisan. Accordingly, the computing device used to implement the fitting system 470 of FIG. 4 may be configured to communicate with multiple cochlear implant systems 102, as well as other types of medical devices.

[0084] The recipient’s session data 380 (fitting quality check data 380a-f) may be received via, for example, a fitting session during which a recipient’s medical device interfaces with a fitting system, such as fitting system 470 of FIG. 4. According to other example embodiments, the session data 380 (fitting quality check data 380a-f) may be received in response to a recipient connecting their medical device (e.g., external component 104 of FIGs. 1A-1D) or associated external device (e.g., external device 110 of FIGs. 1A-1E) to the Internet. For example, a recipient’s external device may be configured with an application, such as a smartphone application (“app”) that transfers data 380a-f to a processing system using the Internet. This transfer of data 380a-f may take place passively (e.g., without the recipient initiating thetransfer) at regular intervals or in response to the external device connecting to the Internet, or may be actively initiated in response to a recipient or clinician command received at the external device.

[0085] The hearing performance data 380b, physiological measurement data 380c, usage data 380d, implant system technical information data 380e, and contextual data 380f may be considered fitting data (also referred to herein as fitting quality check data sets 380b-f), as this data may be used by a fitting system, such as fitting system 470 of FIG. 4. The fitting quality check data sets 380b-f may be automatically sent to the processing device (e.g., the processing devices described above, including fitting system 470 of FIG. 4) via the cochlear implant system 102. According to other example embodiments, the fitting system 470 may interface with the cochlear implant system 102 to initiate the transfer of this data to the fitting system, or the user of the cochlear implant system 102 may initiate the sending of this data to the fitting system 470. It should be appreciated that all of the clinical data types 380a-f described above are not required, and only one clinical data type or only a subset (less than all) of the clinical data types 380a-f may be received in various different implementations of the techniques described herein.

[0086] Turning now to FIG. 5, depicted therein is a flowchart 500 for implementing the map confidence score (fitting quality rating) generation aspects as well as the displaying aspects of flowchart 300. Specifically, flowchart 500 begins with operation 510, in which the fitting system 470 obtains current session data for the recipient (which is analogous to the fitting quality check data 380b-f of FIG. 3). The current session data (fitting quality check data 380b- f) is recipient-specific data and can include one or more of: hearing performance data 380b (e.g., word recognition triplet test), physiological measurements 380c (e.g., impedance data, TIM data, NRT data), usage data 380d (e.g., on-airtime, coil offs, recipient own voice detection (OVD)), implant system technical information 380e (e.g., battery state, error logs, implant resets), and / or contextual data 380f (e.g., implant surgery date, recipient age, recipient history, session date). It should be appreciated that these examples are merely illustrative and nonlimiting.

[0087] In operation 520, the current session data (e.g., the fitting quality check data 380b-f) is analyzed with respect to one or more of general normative data (e.g., a regional / global model map) and in-clinic normative data (e.g., a per-clinic model map) for a given population of similarly situated other recipients (i.e., “matched recipients”). In certain embodiments, trends can be analyzed based on the current session data (e.g., the fitting quality check data 380b-f)in relation to previously received session data (e.g., historical fitting quality check data for the particular recipient), which can allow any fitting trends to be identified and / or can enable fitting quality improvements to be quantified, for example.

[0088] Based on the analysis provided in operation 520, the fitting quality is determined (a map confidence score is calculated or a fitting quality rating is generated) with respect to the current map (i.e., the current operational settings) of the recipient, in operation 530. In certain embodiments, a fitting quality rating (map confidence score) may be calculated or generated for a clinical profile associated with a specific recipient. For example, a recipient of an implantable hearing prosthesis may have an associated fitting profile (also referred to herein as a personal profile 483) that indicates the individualized programs, commands, data, settings, parameters, instructions, modes, and / or other information that define the specific operating characteristics used by the recipient’s hearing prosthesis. Accordingly, when the fitting quality rating (map confidence score) is calculated or generated in operation 530, the fitting quality rating (map confidence score) may be associated with the recipient in general (or their personal profile 483), as opposed to any one specific category. In certain embodiments, individual fitting quality ratings or map confidence scores (also referred to above as distance scores) can also be calculated or generated on a per-category basis (e.g., refer to categories 240 in FIG. 2C).

[0089] In certain examples, the fitting quality rating (map confidence score) generation provided by operation 530 may include determining a fitting quality “rating” (e.g., discrete tiers or rankings, such as high / medium / low) for the recipient’s current map in operation 532. In other examples, the fitting quality generation provided by operation 530 may include calculating a fitting quality “score” (e.g., a specific value, such as a value in a range from 1- 100) in operation 534. Accordingly, operations 510, 520, and 530 (including operation 532 or 534) are analogous to the generation of the map confidence score (fitting quality rating) in operation 320 of FIG. 3.

[0090] Once the fitting quality check is performed in operations 520 and 530 (i.e., after the fitting quality rating or map confidence score is calculated or generated using one of operations 532 or 534), the fitting quality rating or map confidence score is displayed in a dashboard, such as a user interface display, in operation 540. Additionally or alternatively, in operation 550, the user interface displays one or more warnings, suggestions, or recommendations with respect to the current map (the current operational settings) of the recipient. For example, a warning, suggestion, or recommendation may indicate that the current map (or one or moreoperational settings thereof) of the recipient substantially deviates from expected norms or a target range for a particular clinic (e.g., based on comparison of the current map of the recipient with a per-clinic model map, by comparing one or more respective operational settings) and / or expected norms or a target range for a large population of similarly situated other recipients (e.g., based on comparison of the current map of the recipient with a regional / global model map, by comparing one or more respective operational settings). Accordingly, operations 540 and / or 550 are analogous to the displaying of the one or more map confidence scores (fitting quality ratings) and / or the one or more wamings / suggestions / recommendations with respect to the current map (operational settings) of the recipient in operation 330 of flowchart 300 of FIG. 3.

[0091] As illustrated through flowchart 300 of FIG. 3 and / or flowchart 500 of FIG. 5, a display which provides an indication of fitting quality, whereby a fitting quality rating or a map confidence score is derived from current session data (e.g., the fitting quality check data 380b- f), incorporates data from multiple sources in order to solve a specific problem faced by clinicians. More specifically, flowchart 300 of FIG. 3 and / or flowchart 500 of FIG. 5 generate their respective displays by incorporating clinical data into the display generation in determining the fitting quality associated with a current map of the recipient, and / or in determining the warnings, suggestions, or recommendations with respect to the current map of the recipient based on the determined fitting quality.

[0092] Next, returning to FIG. 3, once provided with a display via operation 330, a clinician decides whether to apply the suggested solution to a clinical problem. In operation 340, the clinician may implement the suggestion or recommendation to address the warning that was generated in operation 320 and displayed in operation 330. The implementation of the suggested solution may include the sending of configuration data and / or operational settings directly to an implantable medical device, such as the cochlear implant system 102 of FIG. 4. For example, the implementation of the solution may include the sending of correlated stimulation parameters to the cochlear implant system. Accordingly, the techniques illustrated in FIG. 3 include the configuration of the operating parameters of an implantable medical device, such as a cochlear implant system. However, it should be appreciated that while manual adjustments to the recipient’s map or one or more operational settings thereof can be made by the clinician, the fitting system itself may be configured to determine any appropriate adjustments to the map settings itself, and then automatically reconfigure the implantablemedical device or automatically control the implantable medical device to reconfigure itself according to some other example embodiments, as noted above.

[0093] As noted, the clinician may make adjustments to one or more operational settings, obtain additional data, perform one or more tests, etc. Then, in operation 345, the clinician can provide feedback and / or any additional data that was requested by the analysis model. The clinician feedback and / or the additional data can be fed back into the analysis model to train or update the analysis model of FIG. 3 (e.g., one or more of the recipient matching model 312, the map analysis model 314, and / or the fitting assistance model 316 in operation 310). Likewise, the clinician feedback and / or additional data can be used to modify the profile analysis logic 487 (e.g., the model map generation logic 492, the map confidence score generation logic 494, and / or the fitting assistance model logic 496) stored in the memory 480 of the fitting system 470 of FIG. 4. By using this clinician feedback and / or additional data to train / update and refine the analysis model over time, more accurate map confidence scores (fitting quality) can be generated, more useful warnings and suggestions / recommendations can be generated, and overall fitting quality can be improved for implant recipients. For example, the feedback provided allows for the retraining of the analysis model using supplemental training datasets such that it takes into account the suggestions / recommendations and clinician decisions that improved or did not improve a particular recipient’s map confidence score (or fitting quality rating). The feedback provided can also serve to refine, modify, or improve the analysis model and processes involving the automated adjustments to maps / settings / parameters. Accordingly, the feedback of operation 345 and retraining of the analysis model improves the functioning of the computing device implementing operations 310 and 320.

[0094] In summary, flowchart 300 of FIG. 3, fitting system 470 of FIG. 4, and flowchart 500 of FIG. 5 provide a robust system and methods that support decision making in environments where online technologies for healthcare services are used that allow different clinicians in different clinics to maintain a similar standard of professional care, and eventually move towards the standardization of the professional care, both within any given clinic and across different clinics in the same or different geographical regions. Next, reference is made to FIGs. 6, 7, and 8, which are directed to various different aspects of flowchart 300 and flowchart 500, and may utilize the fitting system 470 of FIG. 4 to implement the respective operations of these methods.

[0095] FIG. 6 is a flowchart of a method 600 according to an example embodiment. Method 600 begins with obtaining operational settings for an implantable medical device implanted in a recipient, in operation 610. In operation 620, a current map is generated for the recipient based on the operational settings. In operation 630, one or more of a per-clinic model map is generated for a particular clinic and / or a regional / global model map is generated for a given population of similarly situated other recipients. Then, the current map of the recipient is displayed relative to the one or more of the per-clinic model map and / or the regional / global model map via a user interface, in operation 640.

[0096] FIG. 7 is a flowchart of a method 700 according to an example embodiment. Method 700 begins with obtaining a current map of a recipient during a fitting process of an implantable medical device, in operation 710. In operation 720, the current map of the recipient is analyzed and compared to general normative data for a given population (e.g., regional or global) and in-clinic normative data for a particular clinic. In operation 730, a fitting quality is determined for the current map of the recipient based on the analyzing. In some examples, a fitting quality “rating” is determined (operation 532). In some other examples, a fitting quality “score” (or map confidence score) is calculated (operation 534). Then, the fitting quality rating / score for the current map of the recipient is displayed via a user interface, in operation 740.

[0097] FIG. 8 is a flowchart of a method 800 according to an example embodiment. Method 800 begins with obtaining a current map of a recipient during a fitting process of an implantable medical device, in operation 810. In operation 820, the current map of the recipient is analyzed and compared to general normative data for a given population (e.g., regional or global) and in-clinic normative data for a particular clinic to determine a fitting quality rating / score for the current map of the recipient. In operation 830, one or more warnings, suggestions, or recommendations are generated with respect to the current map of the recipient based on the fitting quality rating / score. Then, the one or more warnings, suggestions, or recommendations with respect to the current map of the recipient are displayed via a user interface, in operation 840.

[0098] In general, it should be appreciated that before making any specific warnings, suggestions, or recommendations when the current map of the recipient is outside the global norms or the in-clinic norms (i.e., deviates from the in-clinic normative data and / or the global general normative data), the system can first request additional information from the clinician (e.g., request that certain tests be performed for the recipient, and that the results be provided back to the system to update the analysis), update the model / analysis based on the additionalinformation, and only then output a specific warning, suggestion, or recommendation if needed (depending on how the additional information changed the results of the analysis). In addition, the methods described herein are not limited to any particular sequence of operations, and various different ordering of steps is possible.

[0099] In summary, the techniques of the present disclosure present new ways to collect and interactively process various datatypes, and to create a new and practical system for supporting decision making in the new online environment. By implementing one or more of the methods, apparatuses and systems described above with reference to FIGs. 3, 5, 6, 7, and 8, clinicians may be enabled to reduce human errors in the fitting process, which will ensure good quality of the fitting and will guide clinicians to achieve better outcomes. The techniques described herein are particularly useful for less experienced and new CI audiologists in emerging markets, as well as developed markets. The map confidence score can be used to differentiate between fitting issues and cognitive issues, and thus help streamline clinical work and / or avoid unnecessary map adjustments. The techniques can also enable a clinician to distinguish channels that should be disabled which sometimes are set improperly, for example. In addition, artificial intelligence and machine learning techniques can be used in the analysis, as well as to automatically determine and implement appropriate adjustments to one or more operational parameters of recipient maps in order to improve the map confidence score, and thereby improve overall fitting quality.[ooioo] 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. 9 and 10. 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.[ooioi] FIG. 9 illustrates an example vestibular stimulator system 902, with which embodiments presented herein can be implemented. As shown, the vestibular stimulator system 902 comprises an implantable component (vestibular stimulator) 912 and an external device / component 904 (e.g., external processing device, battery charger, remote control, etc.).The external device 904 comprises a transceiver unit 1060. As such, the external device 904 is configured to transfer data (and potentially power) to the vestibular stimulator 912.

[0102] The vestibular stimulator 912 comprises an implant body (main module) 934, a lead region 936, and a stimulating assembly 916, all configured to be implanted under the skin / tissue (tissue) 915 of the recipient. The implant body 934 generally comprises a hermetically-sealed housing 938 in which RF interface circuitry, one or more rechargeable batteries, one or more processors, and a stimulator unit are disposed. The implant body 934 also includes an intemal / implantable coil 914 that is generally external to the housing 938, but which is connected to the transceiver via a hermetic feedthrough (not shown).

[0103] The stimulating assembly 916 comprises a plurality of electrodes 944(l)-(3) disposed in a carrier member (e.g., a flexible silicone body). In this specific example, the stimulating assembly 916 comprises three (3) stimulation electrodes, referred to as stimulation electrodes 944(1), 944(2), and 944(3). The stimulation electrodes 944(1), 944(2), and 944(3) function as an electrical interface for delivery of electrical stimulation signals to the recipient’s vestibular system.

[0104] The stimulating assembly 916 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 may be used with stimulating assemblies having different numbers of stimulation electrodes, stimulating assemblies having different lengths, etc.

[0105] In operation, the vestibular stimulator 912, the external device 904, and / or another external device, can be configured to implement the techniques presented herein. That is, the vestibular stimulator 912, possibly in combination with the external device 904 and / or another external device, can include an evoked biological response analysis system, as described elsewhere herein.

[0106] FIG. 10 illustrates a retinal prosthesis system 1001 that comprises an external device 1010 (which can correspond to the wearable device 100) configured to communicate with an implantable retinal prosthesis 1000 via signals 1051. The retinal prosthesis 1000 comprises an implanted processing module 1025 and a retinal prosthesis sensor-stimulator 1090 is positioned proximate the retina of a recipient. The external device 1010 and the processing module 1025 can communicate via coils 1008, 1014.

[0107] In an example, sensory inputs (e.g., photons entering the eye) are absorbed by a microelectronic array of the sensor-stimulator 1090 that is hybridized to a glass piece 1092 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 1090 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.

[0108] The processing module 1025 includes an image processor 1023 that is in signal communication with the sensor-stimulator 1090 via, for example, a lead 1088 which extends through surgical incision 1089 formed in the eye wall. In other examples, processing module 1025 is in wireless communication with the sensor-stimulator 1090. The image processor 1023 processes the input into the sensor-stimulator 1090, and provides control signals back to the sensor-stimulator 1090 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 1090. 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.

[0109] The processing module 1025 can be implanted in the recipient and function by communicating with the external device 1010, such as a behind-the-ear unit, a pair of eyeglasses, etc. The external device 1010 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 1090 captures light / images, which sensor-stimulator is implanted in the recipient.[oono] 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.[oom] 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. Otheraspects 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] It is also to be appreciated that the embodiments presented herein are not mutually exclusive and that the various embodiments may be combined with another in any of a number of different manners.

Claims

CLAIMSWhat is claimed is:

1. A method comprising : obtaining one or more current operational settings of an implantable medical device implanted in a recipient; obtaining at least one of general normative data or in-clinic normative data for a given population of similarly situated other recipients; analyzing the one or more current operational settings of the implantable medical device relative to at least one of the general normative data and the in-clinic normative data; and outputting data representing the analyzing of the one or more current operational settings of the implantable medical device relative to the at least one of the general normative data and the in-clinic normative data.

2. The method of claim 1, wherein analyzing the one or more current operational settings of the implantable medical device relative to at least one of the general normative data and the in-clinic normative data comprises: generating one or more confidence scores for the one or more current operational settings.

3. The method of claim 2, wherein outputting data representing the analyzing of the one or more current operational settings of the implantable medical device relative to the at least one of the general normative data and the in-clinic normative data comprises: outputting the one or more confidence scores for display on a display device.

4. The method of claim 1, wherein analyzing the one or more current operational settings of the implantable medical device relative to at least one of the general normative data and the in-clinic normative data comprises: evaluating the one or more current operational settings relative to the at least one of the general normative data and the in-clinic normative data to identify outlying settings.

5. The method of claim 4, wherein outputting data representing the analyzing of the one or more current operational settings of the implantable medical device relative to the at least one of the general normative data and the in-clinic normative data comprises: outputting a visual indication of the outlying settings.

6. The method of claim 1, wherein obtaining at least one of general normative data or inclinic normative data for a given population of similarly situated recipient comprises: obtaining at least one of general normative data or in-clinic normative data associated with other recipients having similar etiology as the recipient.

7. The method of claim 1, wherein obtaining at least one of general normative data or inclinic normative data for a given population of similarly situated other recipients comprises: obtaining at least one of general normative data or in-clinic normative data associated with other recipients having similar demographic attributes as the recipient.

8. The method of claim 1, wherein obtaining at least one of general normative data or inclinic normative data for a given population of similarly situated other recipients comprises: obtaining at least one of general normative data or in-clinic normative data associated with other recipients having similar electrode loudness scaling (ELS) settings or audiometric thresholds as the recipient.

9. The method of claim 1, wherein obtaining at least one of the general normative data or in-clinic normative data for a given population of similarly situated other recipients comprises: obtaining at least one of general normative data or in-clinic normative data associated with other recipients having similar objective measurement results as the recipient.

10. The method of claim 1, wherein obtaining at least one of general normative data or inclinic normative data for a given population of similarly situated other recipients comprises: obtaining at least one of general normative data or in-clinic normative data associated with other recipients having similar hearing performance outcomes, similar modiolar distance, or similar medical imaging as the recipient.

11. The method of claim 1, wherein analyzing the one or more current operational settings of the implantable medical device relative to at least one of the general normative data and the in-clinic normative data comprises: using a trained machine learning model to calculate the general normative data and inclinic normative data for the given population of similarly situated patients, and to generate one or more confidence scores with respect to the one or more current operational settings for the recipient.

12. The method of claim 1, wherein obtaining at least one of general normative data or inclinic normative data for a given population of similarly situated other recipients comprises: identifying matched recipients to form the given population of similarly situated other recipients based one or more recipient-specific or device-specific factors including at least one of electrode type, pulse width, loudness tolerance, etiology, and stimulation mode.

13. The method of claim 1, further comprising: displaying, via a display device, the one or more current operational settings of the recipient relative to the general normative data and in-clinic normative data for the given population of similarly situated other recipients.

14. The method of claim 13, further comprising: displaying one or more confidence scores along with statistical data regarding the one or more current operational settings of the recipient relative to the general normative data and in-clinic normative data for the given population of similarly situated other recipients.

15. The method of claim 13, wherein displaying the one or more current operational settings of the recipient relative to the general normative data and in-clinic normative data for the given population of similarly situated other recipients comprises: displaying confidence intervals for one or more objective tests performed for the recipient.

16. The method of claim 1, further comprising: selecting one or more matched recipients, based on one or more of demographic data, electrode loudness scaling (ELS) data, objective measurements data, and hearingperformance data, to form the given population of similarly situated other recipients for comparison with the recipient.

17. The method of claim 16, wherein analyzing the one or more current operational settings of the recipient relative to at least one of the general normative data and in-clinic normative data comprises: analyzing the one or more current operational settings of the recipient relative to a model map that is generated using aggregated data associated with one or more matched recipients forming the given population of similarly situated other recipients to generate one or more map confidence scores or fitting quality ratings.

18. The method of claim 1, wherein displaying the one or more current operational settings of the recipient relative to the given population of similarly situated other recipients comprises at least one of: displaying personal operational settings of the recipient relative to per-clinic operational settings; or displaying the personal operational settings of the recipient relative to regional general operational settings or global general operational settings.

19. The method of claim 18, further comprising one or more of: generating a personal profde for the recipient based on the personal operational settings; generating one or more in-clinic profde s for other recipients of one or more particular clinics based on the per-clinic operational settings; and generating one or more regional profdes for a population of other recipients in a particular geographic area based on the regional general operational settings, or generating one or more global profdes for a large population of other recipients across multiple geographic regions based on the global general operational settings.

20. The method of any of claims 1-19, wherein analyzing the one or more current operational settings of the recipient relative to at least one of the general normative data and in-clinic normative data comprises: generating a degree of variance measure for the one or more current operational settings of the recipient relative to a per-clinic model map, or relative to a regional modelmap or a global model map, with respect to at least one of the one or more current operational settings.

21. The method of any of claims 1-19, further comprising: evaluating the one or more current operational settings of the recipient relative to the general normative data and the in-clinic normative data for the given population of similarly situated other recipients to flag one or more outliers or to flag one or more clinics with a substantial degree of fitting variation.

22. The method of claim 21, wherein evaluating the one or more current operational settings of the recipient relative to the general normative data and in-clinic normative data for the given population of similarly situated other recipients to flag one or more outliers comprises: comparing the one or more current operational settings of the recipient to one or more per-clinic model maps, one or more regional model maps, or one or more global model maps; and determining whether the one or more current operational settings of the recipient is within a certain acceptable tolerance range compared to the one or more per-clinic model maps, the one or more regional model maps, or the one or more global model maps.

23. The method of claim 22, wherein evaluating the one or more current operational settings of the recipient relative to the general normative data and in-clinic normative data for the given population of similarly situated other recipients to flag one or more clinics with a substantial degree of fitting variation comprises: comparing the one or more per-clinic model maps with the one or more regional model maps or the one or more global model maps; and determining whether the one or more per-clinic model maps are within a certain acceptable tolerance range compared to the one or more regional model maps or the one or more global model maps.

24. The method of any of claims 1-19, further comprising: generating and outputting, for display on a display device, one or more warnings, suggestions, or recommendations based on one or more confidence scores and a history of maps, actions, or adjustments for the recipient.

25. The method of claim 24, wherein generating and outputting the one or more warnings, suggestions, or recommendations comprises: differentiating between fitting issues and cognitive issues based on the one or more confidence scores.

26. The method of claim 24, wherein the one or more warnings, suggestions, or recommendations relates to increasing or decreasing levels, balancing, or activating or deactivating one or more particular electrodes.

27. The method of claim 24, wherein the one or more warnings, suggestions, or recommendations comprises a request for one or more of electrode loudness scaling (ELS) data, audiometric thresholds data, objective measurements data, and hearing performance outcomes data.

28. The method of claim 27, wherein the hearing performance outcomes data comprises one or more of consonant vowel consonant (CVC) scores and digit triple test (DTT) scores.

29. The method of claim 24, wherein the one or more warnings, suggestions, or recommendations comprises a request that one or more objective tests be performed for the recipient.

30. The method of claim 29, further comprising: obtaining objective measurements data as a result of the one or more objective tests, including one or more of transimpedance matrix (TIM) data, neural response telemetry data, and eSRT data.

31. The method of claim 30, further comprising: determining whether to unflag the one or more warnings, suggestions, or recommendations based on the objective measurements data that is obtained as the result of the one or more objective tests performed for the recipient.

32. The method of claim 24, wherein generating and outputting one or more warnings, suggestions, or recommendations comprises: generating and outputting a warning that the one or more current operational settings of the recipient is not within an expected target range or deviates from the general normative data and in-clinic normative data by at least a certain amount or degree.

33. The method of claim 24, wherein generating and outputting one or more warnings, suggestions, or recommendations comprises: generating and outputting a suggestion to adjust at least one of the one or more current operational settings.

34. The method of claim 24, wherein generating and outputting one or more warnings, suggestions, or recommendations comprises: generating and outputting a recommendation to change at least one of the one or more current operational settings when there is a substantial deviation between the one or more current operational settings of the recipient and the general normative data and in-clinic normative data.

35. The method of claim 24, further comprising: adjusting at least one of the one or more current operational settings to generate a subsequent map for the recipient; comparing adjusted operational settings of the subsequent map of the recipient with the general normative data and in-clinic normative data to generate one or more updated confidence scores; and outputting the subsequent map of the recipient and the one or more updated confidence scores for display on the display device.

36. The method of claim 35, further comprising: tracking changes in the one or more confidence scores as adjustments are made to the one or more current operational settings.

37. The method of claim 24, further comprising:using a trained machine learning model to determine one or more recommended changes to at least one of the one or more current operational settings based on the one or more confidence scores and the history of maps, actions, or adjustments for the recipient; and automatically applying the one or more recommended changes to the at least one of the one or more current operational settings.

38. The method of any of claims 1-19, further comprising: determining one or more adjustments to the one or more current operational settings based on the analyzing of the one or more current operational settings of the implantable medical device relative to the at least one of the general normative data and the in-clinic normative data; and transmitting the one or more adjustments to the one or more current operational settings to the implantable medical device for implementation.

39. The method of any of claims 1-19, further comprising: determining one or more adjustments to the one or more current operational settings based on the analyzing of the one or more current operational settings of the implantable medical device relative to the at least one of the general normative data and the in-clinic normative data; and reconfiguring the implantable medical device with one or more adjusted operational settings according to the one or more adjustments to the one or more current operational settings.

40. The method of any of claims 1-19, further comprising: generating instructions to perform one or more objective tests or one or more subjective tests in relation to at least one of the one or more current operational settings; obtaining results of the one or more objective tests or the one or more subjective tests; and outputting a suggested change to the least one of the one or more current operational settings based on the results of the one or more objective tests or the one or more subjective tests.

41. The method of any of claims 1-19, wherein outputting data representing the analyzing of the one or more current operational settings of the implantable medical device relative to the at least one of the general normative data and the in-clinic normative data comprises: generating an output that at least one of categorizes or grades the one or more current operational settings of the implantable medical device.

42. A method comprising: obtaining operational settings for a recipient of an implantable medical device; generating a current map for the recipient based on the operational settings; generating at least one of a per-clinic model map for a particular clinic or a general model map for a given population of similarly situated other recipients; and displaying the current map of the recipient relative to at least one of the per-clinic model map or the general model map via a user interface.

43. The method of claim 42, further comprising: generating the per-clinic model map for the particular clinic and the general model map for the given population of similarly situated other recipients; and displaying the current map of the recipient relative to both the per-clinic model map and the general model map via the user interface.

44. The method of claim 42 or 43, further comprising: determining one or more adjustments to one or more operational settings of the implantable medical device based on a map confidence score or a fitting quality rating for the current map of the recipient; and communicating with the implantable medical device to implement the one or more adjustments to the one or more operational settings of the implantable medical device.

45. One or more non-transitory computer readable storage media comprising instructions that, when executed by a processor, cause the processor to: obtain a current map of a recipient during a fitting process of an implantable medical device; analyze the current map of the recipient compared to general normative data for a given population and in-clinic normative data for a particular clinic;generate a fitting quality rating or score for the current map of the recipient based on results of analyzing the current map of the recipient compared to the general normative data for the given population and the in-clinic normative data for the particular clinic; and cause the fitting quality rating or score for the current map of the recipient to be displayed via a user interface of a display device.

46. The one or more non-transitory computer readable storage media of claim 45, wherein the instructions when executed cause the processor to: generate one or more warnings, suggestions, or recommendations with respect to the current map of the recipient based on the fitting quality rating or score; and cause the one or more warnings, suggestions, or recommendations with respect to the current map of the recipient to be displayed, along with the fitting quality rating or score, via the user interface of the display device.

47. The one or more non-transitory computer readable storage media of claim 45 or 46, wherein the instructions when execute cause the processor to: determine one or more adjustments to one or more operational settings of the implantable medical device based on the fitting quality rating or score for the current map of the recipient; and cause the one or more adjustments to the one or more operational settings of the implantable medical device to be made on the implantable medical device.

48. A system comprising: a display screen configured to display a user interface; a memory storing instructions; and at least one processor operably coupled to the display screen and the memory, and configured to execute the instructions to: obtain a current map of a recipient during a fitting process of an implantable medical device; analyze the current map of the recipient compared to general normative data for a given population and in-clinic normative data for a particular clinic to determine a fitting quality for the current map of the recipient; generate one or more warnings, suggestions, or recommendations with respect to the current map of the recipient based on the fitting quality; anddisplay the one or more warnings, suggestions, or recommendations with respect to the current map of the recipient via the user interface displayed on the display screen.

49. The system of claim 48, wherein the at least one processor is configured to execute the instructions to: generate a rating or score representing the fitting quality of the current map of the recipient; and display the rating or score representing the fitting quality of the current map of the recipient, along with the one or more warnings, suggestions, or recommendations, via the user interface displayed on the display screen.

50. The system of claim 48, wherein the at least one processor is configured to execute the instructions to: determine one or more adjustments to one or more operational settings of the implantable medical device based on the one or more warnings, suggestions, or recommendations with respect to the current map of the recipient; and communicate with the implantable medical device to implement the one or more adjustments to the one or more operational settings of the implantable medical device.

Images